pith. sign in

arxiv: 2605.22857 · v1 · pith:B5LGVTEGnew · submitted 2026-05-19 · 📡 eess.SP · cs.LG

JointHRRP-Net: A Statistically Constrained Decoupling Network for Joint Target and Jamming Recognition in Composite Jamming

Yunfei Zhao , Mei Liu , Shuowei Liu , Xunzhang Gao , Yujie Zhou This is my paper

Pith reviewed 2026-05-25 06:30 UTC · model grok-4.3

classification 📡 eess.SP cs.LG
keywords HRRPradar automatic target recognitioncomposite jammingdecoupling networkjoint recognitionstatistical constraintsmulti-label classification
0
0 comments X

The pith

JointHRRP-Net decouples target and jamming features in mixed HRRP using correlation-guided statistical constraints for joint recognition.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper proposes a network that first splits the entangled target and jamming signals in a high-resolution range profile into separate dominant branches. Correlation-guided constraints reduce shared information between branches while preserving useful cues for each. A multi-scale encoder then captures local peaks and range-cell relations, and a dual-expert head performs single-label target classification alongside multi-label jamming classification. This matters because active jamming normally buries target scattering peaks after pulse compression, degrading standard recognition. Experiments across signal-to-jamming and signal-to-noise ratios show gains over baselines, and open-set tests confirm the target branch still rejects unknown targets.

Core claim

The central claim is that a statistically constrained decoupling module can generate target-dominant and jamming-dominant latent branches from the mixed HRRP representation; correlation-guided constraints suppress redundant cross-branch information and alleviate feature entanglement, after which multi-scale temporal encoding and a dual-expert decision module enable accurate single-label target classification and multi-label jamming classification even under composite jamming.

What carries the argument

Statistically constrained decoupling module that produces target-dominant and jamming-dominant latent branches from mixed HRRP via correlation-guided statistical constraints.

If this is right

  • The network outperforms representative baselines on both target and composite jamming recognition across varied SJR and SNR conditions.
  • The learned target representation stays discriminative enough to reject unknown targets in open-set evaluation.
  • Multi-scale temporal encoding models both local scattering structures and long-range range-cell dependencies in the decoupled branches.
  • Dual-expert decision enables simultaneous single-label target classification and multi-label jamming classification from the same input.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same decoupling idea could apply to other entangled radar or sonar signals where one component masks another.
  • If the constraints prove reliable, training might require fewer clean target-only examples than current methods.
  • Real-time radar processors could adopt the branch structure to maintain performance during electronic attacks without separate detection stages.

Load-bearing premise

Correlation-guided statistical constraints on the decoupling module are enough to remove redundant cross-branch information and reduce target-jamming entanglement without losing necessary cues for either task.

What would settle it

If the correlation between the learned target and jamming branches stays high after training, or if recognition accuracy fails to exceed baselines at low signal-to-jamming ratios.

Figures

Figures reproduced from arXiv: 2605.22857 by Mei Liu, Shuowei Liu, Xunzhang Gao, Yujie Zhou, Yunfei Zhao.

Figure 1
Figure 1. Figure 1: Formation mechanism of an HRRP under composite jamming [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: t-SNE visualization under noise-free conditions. The left column [PITH_FULL_IMAGE:figures/full_fig_p003_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Illustrative range profiles of the four jamming templates adopted in [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Illustrative statistics of the constructed composite jamming dataset [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Overall architecture of JointHRRP-Net. (A) Formation of HRRP observations under composite jamming and additive noise. (B) Statistically constrained [PITH_FULL_IMAGE:figures/full_fig_p007_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Residual squeeze-and-excitation (ResSE) block. Three stacked 1-D [PITH_FULL_IMAGE:figures/full_fig_p007_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Confusion matrices for target recognition. Deeper diagonal color [PITH_FULL_IMAGE:figures/full_fig_p010_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Robustness evaluation of the proposed model under varying SNR and SJR conditions on the 12-class simulation dataset. [PITH_FULL_IMAGE:figures/full_fig_p012_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Recognition accuracy heatmaps under varying SNR and SJR condi [PITH_FULL_IMAGE:figures/full_fig_p012_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Comparison of closed-set accuracy and open-set AUROC across [PITH_FULL_IMAGE:figures/full_fig_p012_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Decoupling visualization atlas under different jamming complexities. Rows correspond to the number of active jamming types [PITH_FULL_IMAGE:figures/full_fig_p013_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: Distribution of average SI-SNR across ablation configurations. The [PITH_FULL_IMAGE:figures/full_fig_p014_12.png] view at source ↗
read the original abstract

High-resolution range profile (HRRP)-based radar automatic target recognition suffers from severe performance degradation in composite jamming environments. Active jamming introduces suppression- and deception-related components into the received range profile. After pulse compression, these components are coupled with target echoes in the HRRP domain, making target-related scattering peaks difficult to distinguish and weakening feature separability. To address this problem, this paper proposes JointHRRP-Net, a unified framework for joint target-jamming recognition. A statistically constrained decoupling module is first developed to generate target-dominant and jamming-dominant latent branches from the mixed HRRP representation. Correlation-guided statistical constraints are imposed to suppress redundant cross-branch information and alleviate target-jamming feature entanglement. A multi-scale temporal encoding module is then designed to model local scattering structures and long-range range-cell dependencies, followed by a dual-expert decision module for single-label target classification and multi-label jamming classification. Experiments under diverse signal-to-jamming ratio (SJR) and signal-to-noise ratio (SNR) levels demonstrate that JointHRRP-Net outperforms representative baseline methods in both target recognition and composite jamming recognition. Open-set evaluation further shows that the learned target representation remains discriminative for unknown-target rejection. These results demonstrate the effectiveness and robustness of JointHRRP-Net in composite jamming scenarios.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 1 minor

Summary. The manuscript proposes JointHRRP-Net, a unified deep network for joint target recognition and composite jamming identification from high-resolution range profiles (HRRP) in radar systems affected by active jamming. The architecture consists of a statistically constrained decoupling module that produces target-dominant and jamming-dominant latent branches via correlation-guided statistical constraints, a multi-scale temporal encoding module to capture local scattering structures and long-range dependencies, and a dual-expert decision module that performs single-label target classification alongside multi-label jamming classification. Experiments under varied SJR and SNR conditions are reported to show outperformance versus representative baselines in both recognition tasks, with additional open-set evaluation indicating that the learned target representation supports unknown-target rejection.

Significance. If the central claims hold after addressing the noted concerns, the work would provide a concrete engineering contribution to radar automatic target recognition under realistic jamming, by explicitly modeling and mitigating feature entanglement in the HRRP domain. The joint recognition formulation and open-set capability address practically relevant scenarios. The significance is tempered by the absence of controls that isolate the contribution of the proposed statistical constraints.

major comments (1)
  1. [Decoupling module] Decoupling module (described in the method section following the abstract): the central claim that correlation-guided statistical constraints suppress redundant cross-branch information and alleviate target-jamming entanglement without discarding useful cues is load-bearing for the performance advantage. No ablation is presented that removes or relaxes these constraints while re-measuring accuracy under the reported SJR/SNR conditions; therefore it remains unclear whether the observed gains originate from the constraints themselves or from the multi-scale temporal encoding and dual-expert modules.
minor comments (1)
  1. [Abstract] Abstract: the performance claims are stated qualitatively without any numerical metrics, baseline identifiers, or dataset characteristics; adding these would improve the standalone readability of the summary.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the constructive feedback. The concern regarding the lack of ablation for the statistical constraints in the decoupling module is valid, and we will incorporate the requested experiment in the revision.

read point-by-point responses

  1. Referee: [Decoupling module] Decoupling module (described in the method section following the abstract): the central claim that correlation-guided statistical constraints suppress redundant cross-branch information and alleviate target-jamming entanglement without discarding useful cues is load-bearing for the performance advantage. No ablation is presented that removes or relaxes these constraints while re-measuring accuracy under the reported SJR/SNR conditions; therefore it remains unclear whether the observed gains originate from the constraints themselves or from the multi-scale temporal encoding and dual-expert modules.

    Authors: We agree that an ablation isolating the correlation-guided statistical constraints is necessary to substantiate their contribution. In the revised manuscript we will add a controlled ablation that removes these constraints from the decoupling module (while retaining the multi-scale temporal encoding and dual-expert modules) and re-evaluate target and jamming recognition accuracy across the same SJR/SNR conditions reported in the original experiments. This will directly quantify the performance impact attributable to the constraints. revision: yes

Circularity Check

0 steps flagged

No circularity: empirical network design with no derivation chain

full rationale

The paper presents JointHRRP-Net as an empirical architecture (statistically constrained decoupling module + multi-scale temporal encoding + dual-expert decision) whose claims rest on experimental outperformance under SJR/SNR conditions and open-set rejection, not on any closed-form derivation or first-principles result. No equations appear that could reduce a prediction to its inputs by construction, no fitted parameters are relabeled as predictions, and no self-citation chain is invoked to justify uniqueness or an ansatz. The design choices are presented as motivated engineering decisions rather than mathematically forced outcomes, making the work self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available; no specific free parameters, axioms, or invented entities can be identified from the provided text.

pith-pipeline@v0.9.0 · 5775 in / 1120 out tokens · 21938 ms · 2026-05-25T06:30:29.945291+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

59 extracted references · 59 canonical work pages

  1. [1]

    Deep gaussian hidden markov network for robust hrrp sequence modeling and target recognition,

    M. Liu, X. Gao, X. Qiu, and Y . Liu, “Deep gaussian hidden markov network for robust hrrp sequence modeling and target recognition,”IEEE Transactions on Aerospace and Electronic Systems, vol. 61, no. 6, pp. 19 068–19 083, 2025

    work page 2025

  2. [2]

    A prior-knowledge-guided neural network based on supervised contrastive learning for radar hrrp recognition,

    Q. Liu, X. Zhang, and Y . Liu, “A prior-knowledge-guided neural network based on supervised contrastive learning for radar hrrp recognition,” IEEE Transactions on Aerospace and Electronic Systems, vol. 60, no. 3, pp. 2854–2873, 2024

    work page 2024

  3. [3]

    A dual-polarization feature fusion network for radar automatic target recognition based on hrrp sequences,

    Y . Zhou, S. Liu, H.-W. Gao, H. Lin, G. Wei, X. Wang, and X.-M. Pan, “A dual-polarization feature fusion network for radar automatic target recognition based on hrrp sequences,”IEEE Transactions on Aerospace and Electronic Systems, vol. 61, no. 5, pp. 14 642–14 655, 2025

    work page 2025

  4. [4]

    A threshold insensitive open-set recognition scheme for aav targets based on hrrp,

    S. Tao, M. Mei, J. Luo, L. Yan, and X. Huang, “A threshold insensitive open-set recognition scheme for aav targets based on hrrp,”IEEE Transactions on Aerospace and Electronic Systems, vol. 61, no. 2, pp. 4766–4775, 2025

    work page 2025

  5. [5]

    Radar jamming recognition: Models, methods, and prospects,

    Z. Wang, Z. Guo, G. Shu, and N. Li, “Radar jamming recognition: Models, methods, and prospects,”IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 18, pp. 3315– 3343, 2025

    work page 2025

  6. [6]

    Prior-guided lightweight noise- robust multi-label radar composite interference recognition network,

    Y . Zhao, M. Liu, X. Gao, and S. Liu, “Prior-guided lightweight noise- robust multi-label radar composite interference recognition network,” Journal of Radars, 2026, online First

    work page 2026

  7. [7]

    D 2AF-Net: A dual-domain adaptive fusion method for radar deception jamming recognition,

    W. Zheng, J. Shi, Y . Li, Z. Huang, Z. Zhang, and Z. Li, “D 2AF-Net: A dual-domain adaptive fusion method for radar deception jamming recognition,”IEEE Transactions on Aerospace and Electronic Systems, vol. 61, no. 10, pp. 13 662–13 676, 2025

    work page 2025

  8. [8]

    Ship HRRP target recognition against decoy jamming based on CNN-BiLSTM-SE model,

    L. Wu, S. Hu, J. Xu, and Z. Liu, “Ship HRRP target recognition against decoy jamming based on CNN-BiLSTM-SE model,”IET Radar, Sonar & Navigation, vol. 18, no. 2, pp. 361–378, 2024

    work page 2024

  9. [9]

    Radar HRRP target recognition model based on a stacked CNN–Bi-RNN with attention mechanism,

    M. Pan, A. Liu, Y . Yu, P. Wang, J. Li, Y . Liu, S. Lv, and H. Zhu, “Radar HRRP target recognition model based on a stacked CNN–Bi-RNN with attention mechanism,”IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–14, 2022

    work page 2022

  10. [10]

    Target-attentional cnn for radar automatic target recognition with HRRP,

    J. Chen, L. Du, G. Guo, L. Yin, and D. Wei, “Target-attentional cnn for radar automatic target recognition with HRRP,”Signal Processing, vol. 196, p. 108497, 2022

    work page 2022

  11. [11]

    Surrounding prototype loss for radar hrrp open set target recognition,

    Z. Xia, P. Wang, G. Dong, and H. Liu, “Surrounding prototype loss for radar hrrp open set target recognition,”IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1–5, 2022

    work page 2022

  12. [12]

    Radar hrrp open set recognition based on extreme value distribution,

    X. Ziheng, W. Penghui, D. Ganggang, and L. Hongwei, “Radar hrrp open set recognition based on extreme value distribution,”IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1–16, 2023

    work page 2023

  13. [13]

    Radar hrrp statistical recognition: Parametric model and model selection,

    L. Du, H. Liu, and Z. Bao, “Radar hrrp statistical recognition: Parametric model and model selection,”IEEE Transactions on Signal Processing, vol. 56, no. 5, pp. 1931–1944, 2008

    work page 1931

  14. [14]

    Variational temporal deep generative model for radar hrrp target recognition,

    D. Guo, B. Chen, W. Chen, C. Wang, H. Liu, and M. Zhou, “Variational temporal deep generative model for radar hrrp target recognition,”IEEE Transactions on Signal Processing, vol. 68, pp. 5795–5809, 2020

    work page 2020

  15. [15]

    Radar hrrp target recognition based on concatenated deep neural networks,

    K. Liao, J. Si, F. Zhu, and X. He, “Radar hrrp target recognition based on concatenated deep neural networks,”IEEE Access, vol. 6, pp. 29 211– 29 218, 2018

    work page 2018

  16. [16]

    Space target classification with corrupted hrrp sequences based on temporal–spatial feature aggregation network,

    Y .-P. Zhang, L. Zhang, L. Kang, H. Wang, Y . Luo, and Q. Zhang, “Space target classification with corrupted hrrp sequences based on temporal–spatial feature aggregation network,”IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1–18, 2023. PREPRINT 15

    work page 2023

  17. [17]

    Position embedding-free trans- former for radar hrrp target recognition,

    Y . Diao, S. Liu, X. Gao, and A. Liu, “Position embedding-free trans- former for radar hrrp target recognition,” in2022 IEEE International Geoscience and Remote Sensing Symposium(IGARSS), 2022, pp. 1896– 1899

    work page 2022

  18. [18]

    Msdp-net: A multi-scale domain perception network for hrrp target recognition,

    H. Li, X. Li, Z. Xu, X. Jin, and F. Su, “Msdp-net: A multi-scale domain perception network for hrrp target recognition,”Remote Sensing, vol. 17, no. 15, 2025

    work page 2025

  19. [19]

    Attention is all you need,

    A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, and I. Polosukhin, “Attention is all you need,” inAdvances in Neural Information Processing Systems(NIPS), vol. 30, 2017

    work page 2017

  20. [20]

    Continuous learning method of radar HRRP based on CV AE-GAN,

    X. Li, W. Ouyang, M. Pan, S. Lv, and Q. Ma, “Continuous learning method of radar HRRP based on CV AE-GAN,”IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1–19, 2023

    work page 2023

  21. [21]

    HRRPGraphNet: Make HRRPs to be graphs for efficient target recognition,

    L. Chen, X. Sun, Z. Pan, Q. Liu, Z. Wang, X. Su, Z. Liu, and P. Hu, “HRRPGraphNet: Make HRRPs to be graphs for efficient target recognition,”Electronics Letters, vol. 60, p. e70088, 2024

    work page 2024

  22. [22]

    HRRPGraphNet++: Dynamic graph neural network with meta-learning for few-shot HRRP radar target recognition,

    L. Chen, Z. Pan, Q. Liu, and P. Hu, “HRRPGraphNet++: Dynamic graph neural network with meta-learning for few-shot HRRP radar target recognition,”Remote Sensing, vol. 17, no. 12, p. 2108, 2025

    work page 2025

  23. [23]

    End-to-end radar HRRP target recog- nition based on integrated denoising and recognition network,

    X. Liu, L. Wang, and X. Bai, “End-to-end radar HRRP target recog- nition based on integrated denoising and recognition network,”Remote Sensing, vol. 14, no. 20, p. 5254, 2022

    work page 2022

  24. [24]

    Domain-adaptive hrrp generation using two-stage denoising diffusion probability model,

    Q. Zhou, Y . Wang, X. Zhang, L. Zhang, and T. Long, “Domain-adaptive hrrp generation using two-stage denoising diffusion probability model,” IEEE Geoscience and Remote Sensing Letters, vol. 21, pp. 1–5, 2024

    work page 2024

  25. [25]

    Noise-robust radar hrrp target sequential recognition based on correlative scattering centers,

    K. Su, L. Gong, G. Wang, and L. Zhang, “Noise-robust radar hrrp target sequential recognition based on correlative scattering centers,”IEEE Geoscience and Remote Sensing Letters, vol. 20, pp. 1–5, 2023

    work page 2023

  26. [26]

    Radar deception jamming recognition based on weighted ensemble CNN with transfer learning,

    Q. Lv, Y . Quan, W. Feng, M. Sha, S. Dong, and M. Xing, “Radar deception jamming recognition based on weighted ensemble CNN with transfer learning,”IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–11, 2022

    work page 2022

  27. [27]

    Few-shot radar jamming recognition network via time-frequency self-attention and global knowledge distillation,

    Z. Luo, Y . Cao, T.-S. Yeo, Y . Wang, and F. Wang, “Few-shot radar jamming recognition network via time-frequency self-attention and global knowledge distillation,”IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1–12, 2023

    work page 2023

  28. [28]

    Automatic modulation recognition of compound signals using a deep multi-label classifier: A case study with radar jamming signals,

    M. Zhu, Y . Li, Z. Pan, and J. Yang, “Automatic modulation recognition of compound signals using a deep multi-label classifier: A case study with radar jamming signals,”Signal Processing, vol. 169, p. 107393, 2020

    work page 2020

  29. [29]

    Jrnet: Jamming recognition networks for radar compound suppression jamming signals,

    Q. Qu, S. Wei, S. Liu, J. Liang, and J. Shi, “Jrnet: Jamming recognition networks for radar compound suppression jamming signals,”IEEE Transactions on Vehicular Technology, vol. 69, no. 12, pp. 15 035– 15 045, 2020

    work page 2020

  30. [30]

    Multilabel deep learning-based lightweight radar compound jamming recognition method,

    Q. Lv, H. Fan, J. Liu, Y . Zhao, M. Xing, and Y . Quan, “Multilabel deep learning-based lightweight radar compound jamming recognition method,”IEEE Transactions on Instrumentation and Measurement, vol. 73, pp. 1–15, 2024

    work page 2024

  31. [31]

    Sdhc: Joint semantic-data guided hierarchical classification for fine-grained hrrp target recognition,

    Y . Liu, T. Long, L. Zhang, Y . Wang, X. Zhang, and Y . Li, “Sdhc: Joint semantic-data guided hierarchical classification for fine-grained hrrp target recognition,”IEEE Transactions on Aerospace and Electronic Systems, vol. 60, no. 4, pp. 3993–4009, 2024

    work page 2024

  32. [32]

    Noise robust recognition method based on scatterer pattern for radar hrrp data,

    H. He, L. Du, P. Wang, and H. Liu, “Noise robust recognition method based on scatterer pattern for radar hrrp data,” in2016 IEEE In- ternational Conference on Acoustics, Speech and Signal Processing (ICASSP), 2016, pp. 2324–2328

    work page 2016

  33. [33]

    Radar hrrp target recognition based on deep one-dimensional residual-inception network,

    C. Guo, Y . He, H. Wang, T. Jian, and S. Sun, “Radar hrrp target recognition based on deep one-dimensional residual-inception network,” IEEE Access, vol. 7, pp. 9191–9204, 2019

    work page 2019

  34. [34]

    Deep learning for hrrp-based target recog- nition in multistatic radar systems,

    J. Lund ´en and V . Koivunen, “Deep learning for hrrp-based target recog- nition in multistatic radar systems,” in2016 IEEE Radar Conference (RadarConf), 2016, pp. 1–6

    work page 2016

  35. [35]

    Radar hrrp target recognition method based on multi-input convolutional gated recurrent unit with cascaded feature fusion,

    Z. Zeng, J. Sun, Z. Han, and W. Hong, “Radar hrrp target recognition method based on multi-input convolutional gated recurrent unit with cascaded feature fusion,”IEEE Geoscience and Remote Sensing Letters, vol. 19, pp. 1–5, 2022

    work page 2022

  36. [36]

    Waveform adaptation for target classification using hrrp in a cognitive framework,

    M. Warnke and S. Br ¨uggenwirth, “Waveform adaptation for target classification using hrrp in a cognitive framework,”IEEE Transactions on Aerospace and Electronic Systems, vol. 59, no. 4, pp. 3695–3712, 2023

    work page 2023

  37. [37]

    Prior information-assisted few-shot hrrp recognition based on task-wise shrinkage quadratic dis- criminant analysis,

    J. Li, W. Guo, F. Wei, T. Zhang, and W. Yu, “Prior information-assisted few-shot hrrp recognition based on task-wise shrinkage quadratic dis- criminant analysis,”IEEE Transactions on Aerospace and Electronic Systems, vol. 60, no. 6, pp. 9354–9368, 2024

    work page 2024

  38. [38]

    A novel radar target recognition method for open and imbalanced high-resolution range profile,

    X. Zhang, W. Wang, X. Zheng, and Y . Wei, “A novel radar target recognition method for open and imbalanced high-resolution range profile,”Digital Signal Processing, vol. 118, p. 103212, 2021

    work page 2021

  39. [39]

    Hrrpseqnet: Open- set recognition of space target motions using hrrp sequences,

    Y . Zhang, X. Feng, H. Yin, X. Wei, and H. Yan, “Hrrpseqnet: Open- set recognition of space target motions using hrrp sequences,”IEEE Transactions on Aerospace and Electronic Systems, vol. 61, no. 3, pp. 7481–7496, 2025

    work page 2025

  40. [40]

    Ecapl: Open set recognition on hrrp through expansive consistency-aware prototypes,

    J. Chen, W. Li, S. Li, B. Tian, and Z. Chen, “Ecapl: Open set recognition on hrrp through expansive consistency-aware prototypes,” IEEE Transactions on Aerospace and Electronic Systems, vol. 61, no. 6, pp. 17 377–17 397, 2025

    work page 2025

  41. [41]

    Osfsm: A systematic open set framework for radar automatic target recognition using hrrp,

    W. Li, B. Tian, J. Ma, P. Huang, and S. Xu, “Osfsm: A systematic open set framework for radar automatic target recognition using hrrp,”IEEE Transactions on Aerospace and Electronic Systems, vol. 61, no. 5, pp. 12 350–12 365, 2025

    work page 2025

  42. [42]

    Spatial distribution learning with multivariate extreme value boundary for radar hrrp open set recognition,

    W. Li, S. Li, J. Chen, B. Tian, S. Xu, and Z. Chen, “Spatial distribution learning with multivariate extreme value boundary for radar hrrp open set recognition,”IEEE Transactions on Aerospace and Electronic Systems, vol. 61, no. 3, pp. 6444–6459, 2025

    work page 2025

  43. [43]

    Open-set recognition: A good closed-set classifier is all you need,

    S. Vaze, K. Han, A. Vedaldi, and A. Zisserman, “Open-set recognition: A good closed-set classifier is all you need,” inInternational Conference on Learning Representations(ICLR), 2022

    work page 2022

  44. [44]

    Sar jamming recognition via discriminative feature distance metrics under imbalanced sample,

    X. Cen, Y . Li, X. Wu, Y . Wang, and M. Xing, “Sar jamming recognition via discriminative feature distance metrics under imbalanced sample,” IEEE Transactions on Geoscience and Remote Sensing, vol. 62, pp. 1– 15, 2024

    work page 2024

  45. [45]

    Multi-label radar compound jamming signal recognition using complex-valued CNN with jamming class representation fusion,

    Y . Meng, L. Yu, and Y . Wei, “Multi-label radar compound jamming signal recognition using complex-valued CNN with jamming class representation fusion,”Remote Sensing, vol. 15, no. 21, p. 5180, 2023

    work page 2023

  46. [46]

    Research on multi-feature fusion and lightweight recognition for radar compound jamming,

    W. Zha, J. Cao, H. Wang, and W. Yu, “Research on multi-feature fusion and lightweight recognition for radar compound jamming,”Sensors, vol. 26, no. 4, p. 1296, 2026

    work page 2026

  47. [47]

    Fine-grained recognition and suppression of isrj based on unet-a,

    Y . Wu, L. Duan, L. Yang, Z. Liu, M. Xing, and Y . Quan, “Fine-grained recognition and suppression of isrj based on unet-a,”IEEE Geoscience and Remote Sensing Letters, vol. 21, pp. 1–5, 2024

    work page 2024

  48. [48]

    Recognition of radar compound jamming based on convolutional neural network,

    H. Zhou, L. Wang, and Z. Guo, “Recognition of radar compound jamming based on convolutional neural network,”IEEE Transactions on Aerospace and Electronic Systems, vol. 59, no. 6, pp. 7380–7394, 2023

    work page 2023

  49. [49]

    Sar waveform and mismatched filter design for countering interrupted-sampling repeater jamming,

    K. Zhou, D. Li, S. Quan, T. Liu, Y . Su, and F. He, “Sar waveform and mismatched filter design for countering interrupted-sampling repeater jamming,”IEEE Transactions on Geoscience and Remote Sensing, vol. 60, pp. 1–14, 2022

    work page 2022

  50. [50]

    Improved sar interrupted-sampling repeater jamming countermeasure based on waveform agility and mismatched filter design,

    K. Zhou, Y . Su, D. Wang, H. Ma, L. Liu, and C. Li, “Improved sar interrupted-sampling repeater jamming countermeasure based on waveform agility and mismatched filter design,”IEEE Transactions on Geoscience and Remote Sensing, vol. 61, pp. 1–16, 2023

    work page 2023

  51. [51]

    Radar signal intrapulse modulation recognition based on a denoising-guided disentangled network,

    X. Zhang, J. Zhang, T. Luo, T. Huang, Z. Tang, Y . Chen, J. Li, and D. Luo, “Radar signal intrapulse modulation recognition based on a denoising-guided disentangled network,”Remote Sensing, vol. 14, no. 5, p. 1252, 2022

    work page 2022

  52. [52]

    Joint design of transmit waveform and mismatch filter in the presence of interrupted sampling repeater jamming,

    K. Zhou, D. Li, Y . Su, and T. Liu, “Joint design of transmit waveform and mismatch filter in the presence of interrupted sampling repeater jamming,”IEEE Signal Processing Letters, vol. 27, pp. 1610–1614, 2020

    work page 2020

  53. [53]

    A novel strategy for pulse radar hrrp reconstruction based on randomly interrupted transmitting and receiving in radio frequency simulation,

    X. Liu, J. Liu, F. Zhao, X. Ai, and G. Wang, “A novel strategy for pulse radar hrrp reconstruction based on randomly interrupted transmitting and receiving in radio frequency simulation,”IEEE Transactions on Antennas and Propagation, vol. 66, no. 5, pp. 2569–2580, 2018

    work page 2018

  54. [54]

    Noise robust hrrp sequence recognition based on a deep unfolded go decomposition network,

    M. Liu, X. Gao, and Z. Zhang, “Noise robust hrrp sequence recognition based on a deep unfolded go decomposition network,”Signal Process- ing, vol. 230, p. 109876, 2025

    work page 2025

  55. [55]

    Squeeze-and-excitation networks,

    J. Hu, L. Shen, S. Albanie, G. Sun, and E. Wu, “Squeeze-and-excitation networks,”IEEE Transactions on Pattern Analysis and Machine Intelli- gence, vol. 42, no. 8, pp. 2011–2023, 2020

    work page 2011

  56. [56]

    Efficiently modeling long sequences with structured state spaces,

    A. Gu, K. Goel, and C. R ´e, “Efficiently modeling long sequences with structured state spaces,” inInternational Conference on Learning Representations(ICLR), 2022

    work page 2022

  57. [57]

    On the parameterization and initialization of diagonal state space models,

    A. Gu, K. Goel, A. Gupta, and C. R ´e, “On the parameterization and initialization of diagonal state space models,” inAdvances in Neural Information Processing Systems(Neurips), vol. 35, 2022, pp. 35 971– 35 983

    work page 2022

  58. [58]

    Mamba: Linear-time sequence modeling with selec- tive state spaces,

    A. Gu and T. Dao, “Mamba: Linear-time sequence modeling with selec- tive state spaces,” inFirst Conference on Language Modeling(COLM), 2024

    work page 2024

  59. [59]

    Towards open set deep networks,

    A. Bendale and T. E. Boult, “Towards open set deep networks,” in2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 1563–1572

    work page 2016