AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks

Zhiyang Chen, Yousong Zhu, Zhaowen Li, Fan Yang, Wei Li, Haixin Wang, Chaoyang Zhao, Liwei Wu, Rui Zhao, Jinqiao Wang, Ming Tang

NeurIPS 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 8 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 Prompted Visual Indicator (class prompt) (ablation)Deformable DETR · MS COCO detection, R50mAP: 44.5 -> 45.1Improved
add General Sequence Predictor with separate objectness (ablation)Obj2Seq with class prompt · MS COCO detection, R50mAP: 45.1 -> 45.7Improved
merge objectness into output sequence instead of separate branch (ablation)Obj2Seq · MS COCO detection, R50mAP: 45.1 -> 45.1No clear effect
initialize prompt vectors with CLIP text features (ablation)Obj2Seq · MS COCO detection, R50mAP: 45.4 -> 45.7Improved
fix CLIP prompt vectors during training (ablation)Obj2Seq · MS COCO detection, R50mAP: 45.7 -> 45.2Hurt
vary retention policy (top-K' categories 10 to 80) (ablation)Obj2Seq · MS COCO detection, R50mAP: 0.2%No clear effect
remove class existence score from final object score (ablation)Obj2Seq · retention policy shiftmAPHurt
add iterative box refinementObj2Seq · MS COCO detection, R50mAP: 45.7 -> 46.7Improved
add iterative box refinementDeformable DETR · MS COCO detection, R50mAP: 44.5 -> 46.3Improved
replace MLP head with General Sequence Predictor (ablation)baseline · MS COCO keypoints, 50 epochsAP: 57.2 -> 60.1Improved
train longer, 50 -> 150 epochsObj2Seq · MS COCO keypointsAP: 60.1 -> 65.0Improved
sequence predictor vs 2-Token head, multi-task (ablation)Obj2Seq · COCO human poseAP kps: 58.3 -> 60.5Improved

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