AI Paper Atlas

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

The Pursuit of Knowledge: Discovering and Localizing Novel Categories Using Dual Memory

Sai Saketh Rambhatla, Rama Chellappa, Abhinav Shrivastava

ICCV 2021 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 14 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
initialize semantic memory with known-class detector scores (ablation)Dual memory discovery · COCO mini-train (5000 imgs), semantic memory init ablationAuC@0.5: 2.31 -> 2.97Improved
initialize semantic memory with ground-truth overlap centroids instead of detector scores (ablation)Dual memory discovery · COCO mini-train (5000 imgs), semantic memory init ablation# discovered objects: 27 -> 30Improved
add merge step to memory consolidation (ablation)Dual memory discovery · COCO mini-train (5000 imgs), consolidation ablationAuC@0.5: 3.70 -> 3.80Improved
add refine step after merge (ablation)Dual memory discovery · COCO mini-train (5000 imgs), consolidation ablationAuC@0.5: 3.80 -> 4.02Improved
add refine step after merge (ablation)Dual memory discovery · COCO mini-train (5000 imgs), consolidation ablationCorLoc: 42.57 -> 41.20Hurt
add refine step after merge (ablation)Dual memory discovery · COCO mini-train (5000 imgs), consolidation ablationCorRet: 62.21 -> 65.88Improved
compare to K-means on full COCO train2014Dual memory discovery · COCO train2014 full (80k imgs), unknown classesAuC@0.2: 7.23 -> 9.11Improved
compare to FINCH on full COCO train2014Dual memory discovery · COCO train2014 full (80k imgs), unknown classes# discovered objects: 42 -> 46Improved
compare to OSD at 2.5k imagesDual memory discovery · COCO train2014 subset 2.5k imgsCorLoc: 6.62 -> 43.00Improved
compare to OSD at 2.5k imagesDual memory discovery · COCO train2014 subset 2.5k imgsCorRet: 80.00 -> 64.22Hurt
replace OSD proposals and features with Faster R-CNN onesOSD · COCO train2014 subset 2.5k imgsCorLoc: 6.62 -> 6.34Hurt
compare to rOSD at 20k imagesDual memory discovery · COCO train2014 subset 20k imgsCorLoc: 15.77 -> 41.41Improved

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