AI Paper Atlas

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

HASSOD: Hierarchical Adaptive Self-Supervised Object Detection

Shengcao Cao, Dhiraj Joshi, Liangyan Gui, Yu-Xiong Wang

NeurIPS 2023 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Pseudo-labeling for semi-supervised detection · 4 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
Use HASSOD instead of CutLERclass-agnostic object detection · Objects365 valBox AR: 35.8 -> 39.0Improved
Use HASSOD instead of CutLERclass-agnostic object detection and instance segmentation · LVIS v1.0 valMask AR: 20.2 -> 22.5Improved
Use HASSOD instead of CutLERclass-agnostic object detection and instance segmentation · SA-1B subsetMask AR: 17.0 -> 26.0Improved
Add hierarchical level prediction (ablation)HASSOD detector on MS-COCO+LVIS val2017 · MS-COCO+LVIS val2017Mask AR: 20.2 -> 20.6Improved
Add Mean Teacher self-training (ablation)HASSOD detector with level prediction · MS-COCO+LVIS val2017Mask AR: 20.6 -> 22.1Improved
Adaptively increase teacher-target weight and decrease initial-label weight (ablation)HASSOD with Mean Teacher · MS-COCO+LVIS val2017Mask AR: 22.1 -> 22.4Improved
Add post-processing to θmerge=0.1 clustering (ablation)hierarchical adaptive clustering pseudo-labels · MS-COCO+LVIS val2017 pseudo-labelsMask AR: 4.4 -> 4.1Hurt
Add post-processing to θmerge=0.2 clustering (ablation)hierarchical adaptive clustering pseudo-labels · MS-COCO+LVIS val2017 pseudo-labelsMask AR: 5.5 -> 5.3Hurt
Add post-processing to θmerge=0.4 clustering (ablation)hierarchical adaptive clustering pseudo-labels · MS-COCO+LVIS val2017 pseudo-labelsMask AR: 7.9 -> 7.8No clear effect
Ensemble pseudo-label masks from thresholds 0.1, 0.2, and 0.4 (ablation)hierarchical adaptive clustering · MS-COCO+LVIS val2017 pseudo-labelsMask AR: 7.8 -> 8.9Improved
Replace ViT-B/8 with ViT-B/16 for pseudo-label clustering at θmerge=0.2 (ablation)hierarchical adaptive clustering · MS-COCO+LVIS val2017 pseudo-labelsMask AR: 5.3 -> 3.8Hurt

Later papers that compared with this method

1 later accepted paper reports HASSOD as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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