Pith. sign in

REVIEW 12 cited by

SAM2-Adapter: Evaluating & Adapting Segment Anything 2 in Downstream Tasks: Camouflage, Shadow, Medical Image Segmentation, and More

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 2408.04579 v2 pith:6WXNNOTZ submitted 2024-08-08 cs.CV

classification cs.CV
keywords sam2-adaptersegmentationmodelstasksanythingimagemedicalsam2
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The advent of large models, also known as foundation models, has significantly transformed the AI research landscape, with models like Segment Anything (SAM) achieving notable success in diverse image segmentation scenarios. Despite its advancements, SAM encountered limitations in handling some complex low-level segmentation tasks like camouflaged object and medical imaging. In response, in 2023, we introduced SAM-Adapter, which demonstrated improved performance on these challenging tasks. Now, with the release of Segment Anything 2 (SAM2), a successor with enhanced architecture and a larger training corpus, we reassess these challenges. This paper introduces SAM2-Adapter, the first adapter designed to overcome the persistent limitations observed in SAM2 and achieve new state-of-the-art (SOTA) results in specific downstream tasks including medical image segmentation, camouflaged (concealed) object detection, and shadow detection. SAM2-Adapter builds on the SAM-Adapter's strengths, offering enhanced generalizability and composability for diverse applications. We present extensive experimental results demonstrating SAM2-Adapter's effectiveness. We show the potential and encourage the research community to leverage the SAM2 model with our SAM2-Adapter for achieving superior segmentation outcomes. Code, pre-trained models, and data processing protocols are available at http://tianrun-chen.github.io/SAM-Adaptor/

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 12 Pith papers

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

  1. When Does Resolution Help a Frozen Backbone? Global Attention at Resolution Predicts Scalable Adaptation for Camouflaged and Marine Animal Segmentation

    cs.CV 2026-07 conditional novelty 6.5 of 10

    Global attention over a high-resolution token set, not capacity or pretraining, determines whether LoRA adapters convert resolution into accuracy on fine-grained segmentation.

  2. Refining Context-Entangled Content Segmentation via Curriculum Selection and Anti-Curriculum Promotion

    cs.CV 2026-02 conditional novelty 6.0 of 10

    A curriculum-then-anti-curriculum training schedule, ending with spectral low-pass fine-tuning, improves context-entangled segmentation across several datasets and backbones.

  3. Shape Distribution Matters: Shape-specific Mixture-of-Experts for Amodal Segmentation under Diverse Occlusions

    cs.CV 2025-08 conditional novelty 6.0 of 10

    ShapeMoE improves amodal segmentation by routing each object to a shape-specialized expert via a learned Gaussian shape distribution.

  4. SAMwave: Wavelet-Driven Feature Enrichment for Effective Adaptation of Segment Anything Model

    cs.CV 2025-07 conditional novelty 6.0 of 10

    Wavelet high-frequency features and real or complex adapters improve SAM and SAM2 on several low-level vision tasks, though gains depend on the wavelet family.

  5. SAM4D: Segment Anything in Camera and LiDAR Streams

    cs.CV 2025-06 conditional novelty 6.0 of 10

    SAM4D is a promptable model that segments and tracks objects across camera and LiDAR streams with cross-modal prompts, trained on pseudo-labels generated by an automated data engine.

  6. SafeClick: Error-Tolerant Interactive Segmentation of Any Medical Volumes via Hierarchical Expert Consensus

    eess.IV 2025-06 conditional novelty 6.0 of 10

    SafeClick adds a hierarchical expert consensus module to SAM 2 and MedSAM 2 that improves segmentation accuracy under imperfect prompts.

  7. SAM-I2V: Upgrading SAM to Support Promptable Video Segmentation with Less than 0.2% Training Cost

    cs.CV 2025-06 conditional novelty 6.0 of 10

    SAM-I2V upgrades SAM to video segmentation with three lightweight modules (temporal integrator, selective memory, memory prompts), reaching about 90% of SAM 2.1's average J&F at 0.2% of its training cost.

  8. Multimodal SAM-adapter for Semantic Segmentation

    cs.CV 2025-09 conditional novelty 5.0 of 10

    A side-tuning adapter injects RGB-plus-auxiliary-sensor fused features into SAM's encoder, reaching state-of-the-art semantic segmentation on DeLiVER, FMB, and MUSES.

  9. CRISP-SAM2: SAM2 with Cross-Modal Interaction and Semantic Prompting for Multi-Organ Segmentation

    eess.IV 2025-06 conditional novelty 5.0 of 10

    A text-guided SAM2 variant with cross-modal attention, semantic prompt generation, and a similarity-sorted memory bank achieves top Dice and surface scores on seven public multi-organ CT datasets.

  10. FAMSeg: Fetal Femur and Cranial Ultrasound Segmentation Using Feature-Aware Attention and Mamba Enhancement

    cs.CV 2025-06 reject novelty 5.0 of 10

    FAMSeg, a Mamba-enhanced encoder-decoder with strip convolutions and content-aware upsampling, reports the highest mIoU of 91.58 on a private fetal ultrasound dataset.

  11. SAMamba: Adaptive State Space Modeling with Hierarchical Vision for Infrared Small Target Detection

    cs.CV 2025-05 conditional novelty 5.0 of 10

    SAMamba, combining a frozen SAM2/Hiera encoder with Vision Mamba blocks and three lightweight modules, achieves state-of-the-art infrared small target detection on NUAA-SIRST, IRSTD-1k, and NUDT-SIRST.

  12. SASVi -- Segment Any Surgical Video

    eess.IV 2025-02 conditional novelty 5.0 of 10

    SASVi uses a Mask2Former overseer to automatically re-prompt SAM2 during surgical videos, improving temporal consistency of segmentations from scarce annotations on Cholec80, CATARACTS, and Cataract1k.

Pith tools