CBEN provides paired optical-radar images with cloud occlusion, revealing 23-33 point AP drops in clear-sky trained models and 17-29 point relative gains when models are trained on cloudy data.
hub
Gradient-based learning applied to document recognition
14 Pith papers cite this work. Polarity classification is still indexing.
14
Pith papers citing it
hub tools
citation-role summary
dataset 1
method 1
citation-polarity summary
years
2026 14representative citing papers
DFBScanner detects backdoors by combining anomaly indicators from final-layer parameters into a Trojan clue score, reporting 97.17% true-positive rate, 0.95% false-positive rate, and 1 ms average detection time on a benchmark of over 5,000 models.
MANOJAVAM unifies matrix multiplication and SVD for PCA on FPGA with block-streaming systolic arrays and pipelined Jacobi-CORDIC, delivering up to 22.75x SVD speedup and 42.14x lower energy than an NVIDIA A6000 GPU.
AdaTracker enables zero-shot cross-embodiment active visual tracking by encoding embodiment constraints from history to modulate a context-aware policy.
FedACT schedules devices across concurrent FL jobs via alignment scoring and fairness to reduce average job completion time by up to 8.3x and raise accuracy by up to 44.5% versus baselines.
IAdaPID-ADG integrates non-increasing effective learning rates from AMSGrad and gradient-difference modulation from DiffGrad into AdaPID, yielding better convergence and stability than prior optimizers on MNIST, CIFAR10, IARC, and AnnoCerv.
LymphNode enforces default-deny access control on DNNs by injecting GSUAP into the feature space to neutralize utility for unauthorized queries and selectively restore it for authorized inputs carrying a stealthy credential, using under 100 samples from surrogate data.
DSS-USOD decomposes underwater image features into boundary-sensitive and region-coherent branches with a spatial coordination module and cooperative supervision for improved salient object detection under degradations.
DynGhost is a temporally-modelled transformer that uses quantum-aware training with realistic detector simulations and Anscombe normalization to outperform prior methods on dynamic and photon-starved ghost imaging tasks.
The paper introduces risk-consistent multiclass learning from random label-subset queries by deriving an unbiased risk estimator under ERM, plus non-negative and absolute-value corrections, with generalization bounds and consistency results.
Machine learning methods including denoising autoencoders, unsupervised interference mitigation, blind source separation, and certifiable classification are developed and experimentally validated to improve multi-species laser spectroscopy under complex conditions.
A transfer learning model using thermal images reaches 98.8% accuracy for recognizing breathing patterns.
AnyUser translates free-form sketches on images plus optional language into executable robot actions for domestic tasks using multimodal fusion and a hierarchical policy.
A complete pipeline for federated unlearning via knowledge distillation for efficient removal and a GAN-integrated classifier for visual evaluation of forgetting capacity.
citing papers explorer
-
CBEN -- A Multimodal Machine Learning Dataset for Cloud Robust Remote Sensing Image Understanding
CBEN provides paired optical-radar images with cloud occlusion, revealing 23-33 point AP drops in clear-sky trained models and 17-29 point relative gains when models are trained on cloudy data.
-
Lightweight and Fast Backdoor Model Detection
DFBScanner detects backdoors by combining anomaly indicators from final-layer parameters into a Trojan clue score, reporting 97.17% true-positive rate, 0.95% false-positive rate, and 1 ms average detection time on a benchmark of over 5,000 models.
-
MANOJAVAM: A Scalable, Unified FPGA Accelerator for Matrix Multiplication and Singular Value Decomposition in Principal Component Analysis
MANOJAVAM unifies matrix multiplication and SVD for PCA on FPGA with block-streaming systolic arrays and pipelined Jacobi-CORDIC, delivering up to 22.75x SVD speedup and 42.14x lower energy than an NVIDIA A6000 GPU.
-
AdaTracker: Learning Adaptive In-Context Policy for Cross-Embodiment Active Visual Tracking
AdaTracker enables zero-shot cross-embodiment active visual tracking by encoding embodiment constraints from history to modulate a context-aware policy.
-
FedACT: Concurrent Federated Intelligence across Heterogeneous Data Sources
FedACT schedules devices across concurrent FL jobs via alignment scoring and fairness to reduce average job completion time by up to 8.3x and raise accuracy by up to 44.5% versus baselines.
-
An Improved Adaptive PID Optimizer with Enhanced Convergence and Stability for Deep Learning
IAdaPID-ADG integrates non-increasing effective learning rates from AMSGrad and gradient-difference modulation from DiffGrad into AdaPID, yielding better convergence and stability than prior optimizers on MNIST, CIFAR10, IARC, and AnnoCerv.
-
LymphNode: A Plug-and-Play Access Control Method for Deep Neural Networks
LymphNode enforces default-deny access control on DNNs by injecting GSUAP into the feature space to neutralize utility for unauthorized queries and selectively restore it for authorized inputs carrying a stealthy credential, using under 100 samples from surrogate data.
-
Learning Dynamic Structural Specialization for Underwater Salient Object Detection
DSS-USOD decomposes underwater image features into boundary-sensitive and region-coherent branches with a spatial coordination module and cooperative supervision for improved salient object detection under degradations.
-
DynGhost: Temporally-Modelled Transformer for Dynamic Ghost Imaging with Quantum Detectors
DynGhost is a temporally-modelled transformer that uses quantum-aware training with realistic detector simulations and Anscombe normalization to outperform prior methods on dynamic and photon-starved ghost imaging tasks.
-
Risk-Consistent Multiclass Learning from Random Label-Subset Membership Queries
The paper introduces risk-consistent multiclass learning from random label-subset queries by deriving an unbiased risk estimator under ERM, plus non-negative and absolute-value corrections, with generalization bounds and consistency results.
-
Machine Learning Enhanced Laser Spectroscopy for Multi-Species Gas Detection in Complex and Harsh Environments
Machine learning methods including denoising autoencoders, unsupervised interference mitigation, blind source separation, and certifiable classification are developed and experimentally validated to improve multi-species laser spectroscopy under complex conditions.
-
BreathAI: Transfer Learning-Based Thermal Imaging for Automated Breathing Pattern Recognition
A transfer learning model using thermal images reaches 98.8% accuracy for recognizing breathing patterns.
-
AnyUser: Translating Sketched User Intent into Domestic Robots
AnyUser translates free-form sketches on images plus optional language into executable robot actions for domestic tasks using multimodal fusion and a hierarchical policy.
-
Forgetting to Witness: Efficient Federated Unlearning and Its Visible Evaluation
A complete pipeline for federated unlearning via knowledge distillation for efficient removal and a GAN-integrated classifier for visual evaluation of forgetting capacity.