Pith. sign in

REVIEW 4 cited by

Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic 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 2305.05803 v4 pith:VXWSC4GM submitted 2023-05-09 cs.CV cs.AIcs.LG

Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentation

classification cs.CV cs.AIcs.LG
keywords modelpseudo-labelsmethodssegmentationsemanticsupervisedwsssannotation
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Weakly supervised semantic segmentation (WSSS) aims to bypass the need for laborious pixel-level annotation by using only image-level annotation. Most existing methods rely on Class Activation Maps (CAM) to derive pixel-level pseudo-labels and use them to train a fully supervised semantic segmentation model. Although these pseudo-labels are class-aware, indicating the coarse regions for particular classes, they are not object-aware and fail to delineate accurate object boundaries. To address this, we introduce a simple yet effective method harnessing the Segment Anything Model (SAM), a class-agnostic foundation model capable of producing fine-grained instance masks of objects, parts, and subparts. We use CAM pseudo-labels as cues to select and combine SAM masks, resulting in high-quality pseudo-labels that are both class-aware and object-aware. Our approach is highly versatile and can be easily integrated into existing WSSS methods without any modification. Despite its simplicity, our approach shows consistent gain over the state-of-the-art WSSS methods on both PASCAL VOC and MS-COCO datasets.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 4 Pith papers

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

  1. AVA-Bench: Atomic Visual Ability Benchmark for Vision Foundation Models

    cs.CV 2025-06 unverdicted novelty 7.0

    AVA-Bench evaluates vision foundation models by disentangling 14 atomic visual abilities with aligned training-test distributions to reveal precise ability fingerprints.

  2. Top-P Sensor Selection for Target Localization

    cs.IT 2026-04 unverdicted novelty 5.0

    The paper analyzes top-p versus top-1 hypothesis inclusion under sequential testing, proposes a geometry-aware sensor selection algorithm, and validates it on real testbed data for target localization.

  3. Exploring SAM Supervision for Fine-Grained UAV Target Segmentation under Data Scarcity

    cs.CV 2026-07 conditional novelty 4.5

    A two-stage SAM3 pseudo-label pipeline trains lightweight IPS-Seg to near-teacher IoU on UAV targets under full annotation scarcity, with strong accuracy-efficiency trade-offs.

  4. Top-P Sensor Selection for Target Localization

    cs.IT 2026-04 unverdicted novelty 4.0

    Top-p sequential hypothesis testing can identify a short list of likely nearest sensors more usefully than top-1 selection, with a geometry-aware algorithm validated on testbed data.