AI Paper Atlas

Research map / Detection and segmentation / Weakly supervised detection and segmentation

Unsupervised Object Localization with Representer Point Selection

Yeonghwan Song, Seokwoo Jang, Dina Katabi, Jeany Son

ICCV 2023 · Detection and segmentation › Weakly supervised detection and segmentation · approach: Weakly supervised object localization · 3 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
replace class-agnostic activation map with representer point selection inference (ablation)MoCo v2 ResNet50 · ImageNet-1K GT-Known LocGT-Known Loc: 61.19 -> 69.10Improved
replace class-agnostic activation map with representer point selection inference (ablation)MoCo v2 ResNet50 · CUB-200-2011 GT-Known LocGT-Known Loc: 86.93 -> 96.67Improved
apply representer point inference on top of trained C2AM (ablation)C2AM · CUB-200-2011 GT-Known LocGT-Known Loc: 89.90 -> 96.86Improved
apply representer point inference on top of DAOL (ablation)DAOL · ImageNet-1K GT-Known LocGT-Known Loc: 70.27 -> 70.97Improved
use a self-supervised backbone instead of supervised pretraining (ablation)Representer point selection · ImageNet-1K GT-Known LocGT-Known Loc: 63.22 -> 66.89Improved
compute foreground predictor from 0.1% instead of 100% of the data (ablation)Representer point selection (ViT-S) · ImageNet-1K GT-Known LocGT-Known Loc: 73.65 -> 73.67No clear effect
compute foreground predictor on CIFAR10 instead of the target dataset (ablation)Representer point selection (ViT-S) · CUB-200-2011 GT-Known LocGT-Known Loc: 91.62 -> 92.73No clear effect
transfer foreground predictor across datasets without retrainingRepresenter point selection vs C2AM · CUB-200-2011 GT-Known Loc, trained on CIFAR10GT-Known Loc: 73.18 -> 94.24Improved
use ViT-S DINO backbone instead of ResNet50 MoCo v2 (ablation)Representer point selection · CUB-200-2011 GT-Known LocGT-Known Loc: 96.67 -> 91.61Hurt
use a class-specific predictor w_c for ImageNet instead of class-agnostic (ablation)Representer point selection · ImageNet-1K GT-Known LocGT-Known Loc: 73.65 -> 74.44Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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