AI Paper Atlas

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

GOOD: Exploring geometric cues for detecting objects in an open world

Haiwen Huang, Andreas Geiger, Dan Zhang

ICLR 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Open-set and unknown object detection · 5 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 depth-based pseudo boxes from geometry to RGB detector trainingOLN · COCO person→non-personAR_N@100: 16.5 -> 25.6Improved
Add depth- and normal-based pseudo boxes together (ablation)GOOD on COCO VOC→non-VOC · COCO VOC→non-VOCAR_N@100: 39.0 -> 39.3Improved
Use geometric pseudo boxes instead of RGB-only self-trainingOLN · COCO VOC→non-VOCAR_N@100: 37.4 -> 39.3Improved
Use geometric pseudo boxes instead of RGB-only self-trainingOLN · VOC→ADE20KAR_A@100: 29.2 -> 34.0Improved
Use geometry rather than edge-map pseudo labels (ablation)GOOD · COCO VOC→non-VOCAR_N@100: 38.1 -> 39.0Improved
Use geometry rather than pairwise-affinity pseudo labels (ablation)GOOD · COCO VOC→non-VOCAR_N@100: 37.1 -> 39.0Improved
Replace the SelfTrain-RGB backbone with stylized ImageNet-pretrained weights (ablation)SelfTrain-RGB · VOC→non-VOCAR_N@100: 37.4 -> 36.5Hurt
Use multi-scale augmentation to collect RGB pseudo boxes (ablation)SelfTrain-RGB · VOC→non-VOCAR_N@100: 37.4 -> 37.9Improved
Add RGB-based pseudo boxes to the depth-and-normal ensemble (ablation)GOOD-Both · VOC→ADE20KAR_A@100: 34.0 -> 33.3Hurt
Train the Phase-II detector with AutoAugment (ablation)GOOD · COCO VOC→non-VOCAR_N@100Improved
Train OLN with AutoAugment on base-class ground-truth boxes (ablation)OLN · COCO VOC→non-VOCAR_N@100Hurt
Stack RGB with geometric cues in Phase I (ablation)GOOD · Open-world benchmarksAR_N@100Hurt

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