Pith. sign in

REVIEW 8 cited by

Mamba or RWKV: Exploring High-Quality and High-Efficiency Segment Anything Model

Not yet reviewed by Pith; the record is open.

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 2406.19369 v1 pith:4ZAZQKUJ submitted 2024-06-27 cs.CV

classification cs.CV
keywords segmentationefficienthigh-qualitymodelmodelsrwkv-samachievesattention
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Transformer-based segmentation methods face the challenge of efficient inference when dealing with high-resolution images. Recently, several linear attention architectures, such as Mamba and RWKV, have attracted much attention as they can process long sequences efficiently. In this work, we focus on designing an efficient segment-anything model by exploring these different architectures. Specifically, we design a mixed backbone that contains convolution and RWKV operation, which achieves the best for both accuracy and efficiency. In addition, we design an efficient decoder to utilize the multiscale tokens to obtain high-quality masks. We denote our method as RWKV-SAM, a simple, effective, fast baseline for SAM-like models. Moreover, we build a benchmark containing various high-quality segmentation datasets and jointly train one efficient yet high-quality segmentation model using this benchmark. Based on the benchmark results, our RWKV-SAM achieves outstanding performance in efficiency and segmentation quality compared to transformers and other linear attention models. For example, compared with the same-scale transformer model, RWKV-SAM achieves more than 2x speedup and can achieve better segmentation performance on various datasets. In addition, RWKV-SAM outperforms recent vision Mamba models with better classification and semantic segmentation results. Code and models will be publicly available.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. PointDGRWKV: Generalizing RWKV-like Architecture to Unseen Domains for Point Cloud Classification

    cs.CV 2025-08 conditional novelty 6.0 of 10

    PointDGRWKV applies RWKV-like attention to domain-generalized point cloud classification, adding a geometric token shift and key-distribution alignment, and reports state-of-the-art accuracy on PointDA-10 and PointDG-3to1.

  2. GDSR: Global-Detail Integration through Dual-Branch Network with Wavelet Losses for Remote Sensing Image Super-Resolution

    eess.IV 2024-12 conditional novelty 6.0 of 10

    A dual-branch RWKV-CNN super-resolution network with a multi-scale wavelet loss reports up to 0.11 dB PSNR gain over HAT on remote sensing benchmarks at a fraction of the compute.

  3. StyleRWKV: High-Quality and High-Efficiency Style Transfer with RWKV-like Architecture

    cs.CV 2024-12 conditional novelty 6.0 of 10

    StyleRWKV applies recurrent RWKV-style attention with deformable shifting and skip scanning to achieve fast, high-quality arbitrary style transfer.

  4. EMOv2: Pushing 5M Vision Model Frontier

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A 5M-parameter backbone with shared-weight spanning window attention sets new accuracy records across classification, detection, and generation benchmarks.

  5. Med-URWKV{\dag}: Toward Enhanced Pretrained Pure VRWKV Models for Medical Image Segmentation

    eess.IV 2025-06 conditional novelty 5.0 of 10

    Pretrained pure VRWKV encoders paired with pure VRWKV decoders match or beat CNN, ViT, and Mamba baselines, with a small model plus FAWA and MSCF modules reaching 88% average Dice.

  6. Linear Attention Modeling for Learned Image Compression

    cs.CV 2025-02 conditional novelty 5.0 of 10

    LALIC replaces transformer and Mamba blocks in learned image compression with bidirectional RWKV linear-attention blocks, reporting BD-rate gains over VTM-9.1 while keeping decoder latency moderate.

  7. Optimized Vessel Segmentation: A Structure-Agnostic Approach with Small Vessel Enhancement and Morphological Correction

    eess.IV 2024-11 conditional novelty 5.0 of 10

    OVS-Net, a SAM-based vessel segmentation framework with a micro-vessel enhancement branch and morphology-correction post-processing, reports higher Dice and better connectivity than six SAM baselines and 17 expert mod...

  8. A Survey of RWKV

    cs.CL 2024-12 conditional novelty 3.0 of 10

    A review of the RWKV architecture, its versions, applications, benchmarks, and open-source ecosystem; it presents no new experimental results.

Pith tools