AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

WPS-SAM: Towards Weakly-Supervised Part Segmentation with Foundation Models

Xin-Jian Wu, Ruisong Zhang, Jie Qin, Shijie Ma, Cheng-Lin Liu

ECCV 2024 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
learn part prompts end-to-end from SAM features with a distilled prompter, using only box labelsfully supervised part segmentation models · PartImageNet valmIoU (%): 65.24 -> 68.93Improved
replace Det-SAM detector pipeline with learned query-based prompter (ablation)Det-SAM (Faster-RCNN ResNet-50) · PartImageNet valmIoU (%): 63.7 -> 68.9Improved
use SAM encoder as detector backbone in Det-SAM (ablation)Det-SAM · PartImageNet valmIoU (%): 63.7 -> 54.6 (Faster-RCNN)Hurt
use direct prompter instead of SAM pseudo-label paradigm for training MaskFormer (ablation)MaskFormer Swin-B · PartImageNet valmIoU (%): 56.83 -> 68.93Improved
use bounding box labels instead of center point labels (ablation)WPS-SAM · PartImageNet valmIoU (%)Improved
increase number of queries from 25 to 50/75/100 (ablation)WPS-SAM prompter · PartImageNet valmIoU (%)Hurt
fine-tune the SAM encoder instead of freezing it (ablation)WPS-SAM · PartImageNet valmIoU (%): 68.93 -> 65.16Hurt
use query-based transformer prompter instead of anchor-based CNN (ablation)student prompter · PartImageNet valmIoU (%): 57.23 -> 68.93Improved
increase beta (matching/regression weight) from 1 to 20 with alpha 5, lambda_cls 10 (ablation)WPS-SAM losses · PartImageNet valmIoU (%): 61.93 -> 68.93Improved
increase beta to 50 (ablation)WPS-SAM losses · PartImageNet valmIoU (%): 68.93 -> 67.82Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy