Pith. sign in

REVIEW 16 cited by

MambaVision: A Hybrid Mamba-Transformer Vision Backbone

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.08083 v2 pith:N3APXQDF submitted 2024-07-10 cs.CV

Ali Hatamizadeh , Jan Kautz This is my paper
classification cs.CV
keywords mambavisionmambavisionarchitecturebackbonehybridmamba-transformerperformance
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We propose a novel hybrid Mamba-Transformer backbone, MambaVision, specifically tailored for vision applications. Our core contribution includes redesigning the Mamba formulation to enhance its capability for efficient modeling of visual features. Through a comprehensive ablation study, we demonstrate the feasibility of integrating Vision Transformers (ViT) with Mamba. Our results show that equipping the Mamba architecture with self-attention blocks in the final layers greatly improves its capacity to capture long-range spatial dependencies. Based on these findings, we introduce a family of MambaVision models with a hierarchical architecture to meet various design criteria. For classification on the ImageNet-1K dataset, MambaVision variants achieve state-of-the-art (SOTA) performance in terms of both Top-1 accuracy and throughput. In downstream tasks such as object detection, instance segmentation, and semantic segmentation on MS COCO and ADE20K datasets, MambaVision outperforms comparably sized backbones while demonstrating favorable performance. Code: https://github.com/NVlabs/MambaVision

Discussion (0). Sign in to comment.

Forward citations

Cited by 16 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 27 citations worldwide. Full citation record

  1. Sign Language Question Answering: A New Task, Benchmark, and Baseline for Sign Language Understanding

    cs.AI 2026-07 conditional novelty 6.0 of 10

    Sign Language QA benchmarks are introduced from PHOENIX14T and CSL-Daily via template-generated questions, and a question-conditioned baseline outperforms video-language and cascaded baselines.

  2. Catch-Only-One: Non-Transferable Examples for Model-Specific Authorization

    cs.LG 2025-10 conditional novelty 6.0 of 10

    Non-transferable examples add perturbations in an authorized model's low-sensitivity subspace, keeping that model's accuracy nearly intact while collapsing the accuracy of all other tested models.

  3. How Can Mamba Learn In Context with Outliers and Generalize Provably?

    cs.LG 2025-10 conditional novelty 6.0 of 10

    A simplified one-layer Mamba provably learns in-context binary classification tolerating outlier fractions approaching 1, whereas a linear Transformer can only tolerate α < 1/2.

  4. VAMPIRE: Uncovering Vessel Directional and Morphological Information from OCTA Images for Cardiovascular Disease Risk Factor Prediction

    cs.CV 2025-07 conditional novelty 6.0 of 10

    VAMPIRE predicts CVD risk and four blood-related conditions from OCTA images using a vessel-following Mamba module and morphology text enhancement, outperforming existing backbones on a new OCTA-CVD dataset.

  5. Training-free Token Reduction for Vision Mamba

    cs.CV 2025-07 conditional novelty 6.0 of 10

    MTR uses Mamba's timescale parameter Δ as a token importance score to merge unimportant tokens, giving training-free inference speedups with small accuracy loss.

  6. MUG: Pseudo Labeling Augmented Audio-Visual Mamba Network for Audio-Visual Video Parsing

    cs.CV 2025-07 conditional novelty 6.0 of 10

    MUG combines manually corrected pseudo-labels, cross-modal random track recombination, and a Mamba-Transformer network to reach new state-of-the-art F1 scores on the LLP audio-visual video parsing benchmark.

  7. EAMamba: Efficient All-Around Vision State Space Model for Image Restoration

    cs.CV 2025-06 conditional novelty 6.0 of 10

    EAMamba introduces channel-grouped multi-head selective scanning whose cost does not grow with the number of scan directions, and reports 31-89% FLOPs reductions with comparable PSNR across denoising, super-resolution...

  8. ENA: Efficient N-dimensional Attention

    cs.LG 2025-08 conditional novelty 5.0 of 10

    ENA combines linear recurrence with hardware-friendly sliding tile attention to model images and videos efficiently, claiming Transformer-level accuracy at roughly 70% attention sparsity.

  9. MoMa: Modulating Mamba for Adapting Image Foundation Models to Video Recognition

    cs.CV 2025-06 conditional novelty 5.0 of 10

    MoMa adapts frozen CLIP to video by injecting Mamba-computed scale and bias into each layer, improving accuracy and efficiency on multiple action recognition benchmarks.

  10. HTMNet: A Hybrid Network with Transformer-Mamba Bottleneck Multimodal Fusion for Transparent and Reflective Objects Depth Completion

    cs.CV 2025-05 conditional novelty 5.0 of 10

    HTMNet combines a CNN-Transformer encoder, a Transformer-Mamba bottleneck fusion block, and a multi-scale attention decoder to improve depth completion for transparent and reflective objects, claiming state-of-the-art...

  11. Semi-Supervised State-Space Model with Dynamic Stacking Filter for Real-World Video Deraining

    cs.CV 2025-05 conditional novelty 5.0 of 10

    The paper introduces a dual-branch state-space video deraining model with a dynamic stacking filter and semi-supervised median stacking loss, showing top PSNR across three benchmarks and new downstream task gains on a...

  12. FR-Mamba: Time-Series Physical Field Reconstruction Based on State Space Model

    cs.LG 2025-05 conditional novelty 5.0 of 10

    A hybrid Mamba-FNO architecture is presented for time-series physical field reconstruction, reporting a mean absolute error of 0.31e-4 on a 2D cylinder flow benchmark, about one-third of the previous transformer-based method.

  13. A Controlled Visual-Backbone Benchmark for Multimodal Short-Term Solar Irradiance Forecasting

    eess.IV 2026-07 conditional novelty 4.0 of 10

    Under one fixed multimodal 10-min irradiance forecaster, VMamba-S and Swin-B nearly tie best Folsom RMSE (~65.4 W/m²) over smart persistence, while NREL’s tiny matched split favors persistence.

  14. VCMamba: Bridging Convolutions with Multi-Directional Mamba for Efficient Visual Representation

    cs.CV 2025-09 conditional novelty 4.0 of 10

    VCMamba reports that using convolutional feed-forward blocks for the first three stages followed by multi-directional Mamba blocks in the final stage yields 82.6% ImageNet-1K and 47.1 ADE20K mIoU at 31.5M parameters, ...

  15. HybridTM: Combining Transformer and Mamba for 3D Semantic Segmentation

    cs.CV 2025-07 conditional novelty 4.0 of 10

    A new 3D semantic segmentation architecture that interleaves attention and Mamba operators within each layer achieves small but consistent gains on indoor and outdoor benchmarks.

  16. BrainMT: A Hybrid Mamba-Transformer Architecture for Modeling Long-Range Dependencies in Functional MRI Data

    cs.CV 2025-06 conditional novelty 4.0 of 10

    BrainMT, a Mamba-transformer hybrid with a temporal-first scan, is claimed to outperform prior models on fMRI-based sex and intelligence prediction.

Pith tools