AI Paper Atlas

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

Efficient Discovery and Effective Evaluation of Visual Perceptual Similarity: A Benchmark and Beyond

Oren Barkan, Tal Reiss, Jonathan Weill, Ori Katz, Roy Hirsch, Itzik Malkiel, Noam Koenigstein

ICCV 2023 · Detection and segmentation › Open-set and few-shot detection · approach: Object-level representation learning · 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
label model-suggested top-k suspects (EDS) instead of random pairsvisual similarity labeling · DeepFashion in-catalogpositive discovery rate: 0.001 -> 0.848Improved
finetune with identity labels (ablation)Argus · Closed-catalog discoveryMicro ROC-AUC: 62.7 -> 62.3Hurt
finetune with identity labels (ablation)Argus · Closed-catalog discoveryHR@5: 82.5 -> 84.3Improved
finetune with category labels (ablation)BEiT · Closed-catalog discoveryMicro ROC-AUC: 75.5 -> 72.9Hurt
finetune with category labels (ablation)Argus · Closed-catalog discoveryMicro ROC-AUC: 62.7 -> 67.5Improved
supervised finetuning (CAT, ID, ID+C) (ablation)DINO · Image-in-the-wild discoveryMicro ROC-AUC: 70.8 -> 64.8 / 61.2 / 62.0Hurt
finetune with DINO's own self-supervised objective (ablation)DINO · Image-in-the-wild discoveryMicro ROC-AUC: 70.8 -> 71.8Improved
evaluate with HR@k/MRR@k on non-generator modelsbenchmark metrics · Closed-catalog discoveryHR@5: 92.3 (generator BEiT) vs 38.7 (BEiT CAT)Hurt
use ROC-AUC with leave-one-out ground truth subsets (ablation)evaluation metric · Closed-catalog discoverySpearman correlation: 0.94Improved

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