Pith. sign in

REVIEW 1 cited by

Evaluation Study on SAM 2 for Class-agnostic Instance-level Segmentation

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 2409.02567 v2 pith:L3G5WFPF submitted 2024-09-04 cs.CV

classification cs.CV
keywords segmentationsam2instanceperformanceclass-agnosticinstance-leveltasksanything
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Segment Anything Model (SAM) has demonstrated powerful zero-shot segmentation performance in natural scenes. The recently released Segment Anything Model 2 (SAM2) has further heightened researchers' expectations towards image segmentation capabilities. To evaluate the performance of SAM2 on class-agnostic instance-level segmentation tasks, we adopt different prompt strategies for SAM2 to cope with instance-level tasks for three relevant scenarios: Salient Instance Segmentation (SIS), Camouflaged Instance Segmentation (CIS), and Shadow Instance Detection (SID). In addition, to further explore the effectiveness of SAM2 in segmenting granular object structures, we also conduct detailed tests on the high-resolution Dichotomous Image Segmentation (DIS) benchmark to assess the fine-grained segmentation capability. Qualitative and quantitative experimental results indicate that the performance of SAM2 varies significantly across different scenarios. Besides, SAM2 is not particularly sensitive to segmenting high-resolution fine details. We hope this technique report can drive the emergence of SAM2-based adapters, aiming to enhance the performance ceiling of large vision models on class-agnostic instance segmentation tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Rethinking Detecting Salient and Camouflaged Objects in Unconstrained Scenes

    cs.CV 2024-12 conditional novelty 7.0 of 10

    A new dataset, model, and metric extend salient and camouflaged object detection to unconstrained scenes where the two object types can coexist.

Pith tools