AI Paper Atlas

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

Learning to Find Common Objects Across Few Image Collections

Amirreza Shaban, Amir Rahimi, Shray Bansal, Stephen Gould, Byron Boots, Richard Hartley

ICCV 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Few-shot object detection · 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 learned unary potentials from the negative bag to pairwise-only inference (ablation)greedy structured inference · COCO co-localizationsuccess rate: 64.65 -> 65.34Improved
add learned unary potentials from the negative bag to pairwise-only inference (ablation)greedy structured inference · ILSVRC2013 co-localizationsuccess rate: 53.00 -> 55.18Improved
add pairwise potentials to unary-only selection (ablation)greedy structured inference · COCO co-localizationsuccess rate: 59.24 -> 65.34Improved
add pairwise potentials to unary-only selection (ablation)greedy structured inference · ILSVRC2013 co-localizationsuccess rate: 50.29 -> 55.18Improved
use learned softmax-weighted unary instead of no unary (ablation)Ours · miniImageNet (N=8, B=5, 10 negatives)success rate: 64.48 -> 72.49Improved
use learned temperature (SOFTMAX) instead of MEAN unary (ablation)Ours · miniImageNet (N=8, B=5, 10 negatives)success rate: 70.23 -> 72.49Improved
use learned temperature (SOFTMAX) instead of MAX unary (ablation)Ours · miniImageNet (N=8, B=5, 10 negatives)success rate: 71.76 -> 72.49Improved
use separate parameters for unary and pairwise relation modules instead of sharing (ablation)Ours · miniImageNet (N=8, B=5, 10 negatives)success rate: 69.35 -> 72.49Improved
replace cosine-similarity relation with learned relation network (ablation)Ours · miniImageNet (N=8, B=5, 10 negatives)success rate: 64.46 -> 72.49Improved
replace cosine-similarity relation with learned relation network (ablation)Ours · miniImageNet (N=16, B=5, 10 negatives)success rate: 66.78 -> 78.60Improved
use gated activation instead of ReLU in the relation embedding (ablation)relation network · miniImageNet 5-way 1-shotaccuracy: 56.43 -> 57.80Improved
use greedy merge-and-prune inference instead of TRWS (ablation)Ours · COCO co-localizationsuccess rate: 65.04 -> 65.34No clear effect

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