AI Paper Atlas

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

DiscoBox: Weakly Supervised Instance Segmentation and Semantic Correspondence From Box Supervision

Shiyi Lan, Zhiding Yu, Christopher Choy, Subhashree Radhakrishnan, Guilin Liu, Yuke Zhu, Larry S. Davis, Anima Anandkumar

ICCV 2021 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised semantic segmentation · 122 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
add self-consistency loss L_con to the teacher (ablation)DiscoBox YOLACT++ ResNet-50-DCN · VOC12 valAP50: 43.3 -> 62.0Improved
add self-consistency loss L_con to the teacher (ablation)DiscoBox SOLOv2 ResNet-50 · VOC12 valAP50: 42.1 -> 58.1Improved
add dense contrastive loss L_nce (ablation)DiscoBox YOLACT++ ResNet-50-DCN · VOC12 valAP50: 62.0 -> 63.6Improved
add dense contrastive loss L_nce (ablation)DiscoBox SOLOv2 ResNet-50 · VOC12 valAP50: 58.1 -> 59.8Improved
add dense contrastive loss L_nce (ablation)DiscoBox YOLACT++ ResNet-50-DCN · VOC12 valAP75: 33.5 -> 34.1Improved
add dense NCE loss during training (teacher still used at inference) (ablation)DiscoBox · PASCAL 3D+AP: 30.9 -> 31.7Improved
use structured teacher for correspondence instead of SCOT matching (ablation)DiscoBox- · PASCAL 3D+AP: 29.3 -> 30.9Improved
scale backbone from ResNet-50 to ResNet-101-DCNDiscoBox SOLOv2 · COCO test-devmask AP: 32.0 -> 35.8Improved
scale backbone from ResNet-101-DCN to ResNeXt-101-DCNDiscoBox SOLOv2 · COCO test-devmask AP: 35.8 -> 37.9Improved
use SOLOv2 instead of YOLACT++ as task network (ResNet-50)DiscoBox · VOC12 valAP50: 63.6 -> 59.8Hurt
vary loss weights (ablation)DiscoBox · VOC12 and PASCAL 3D+APNo clear effect

Later papers that compared with this method

5 later accepted papers report DiscoBox as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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