AI Paper Atlas

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

Local Aggregation for Unsupervised Learning of Visual Embeddings

Chengxu Zhuang, Alex Lin Zhai, Daniel Yamins

ICCV 2019 · Detection and segmentation › Open-set and few-shot detection · approach: Unsupervised object and part discovery · 425 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
use dynamic nearest-neighbor background N_4096 instead of all inputs (ablation)LA · ImageNet NN validation (ResNet-18)NN accuracy: 30.2 -> 35.7Improved
use dynamic nearest-neighbor background instead of fixed cluster-based background (ablation)LA · ImageNet NN validation (ResNet-18)NN accuracy: 33.2 -> 35.7Improved
use cluster-based close neighbors instead of nearest-neighbor close neighbors (ablation)LA · ImageNet NN validation (ResNet-18)NN accuracy: 0.1 -> 35.7Improved
use clustered close neighbors instead of only the point itself (ablation)LA · ImageNet NN validation (ResNet-18)NN accuracy: 33.9 -> 35.7Improved
increase number of clusterings H from 1 to 3 (ablation)LA · ImageNet NN validation (ResNet-18)NN accuracy: 35.7 -> 36.2Improved
increase number of clusterings H from 3 to 10 (ablation)LA · ImageNet NN validation (ResNet-18)NN accuracy: 36.2 -> 36.1No clear effect
increase number of clusters m from 10k to 30k with H=10 (ablation)LA · ImageNet NN validation (ResNet-18)NN accuracy: 36.1 -> 37.9Improved
replace k-means with DBSCAN for clustering (ablation)LA · ImageNetrepresentation qualityHurt
change background neighbor count k from 4096 to 2048 or 8192 (ablation)LA · ImageNet NN validation (ResNet-18)NN accuracy: 35.7 -> 35.4 (k=2048), 35.8 (k=8192)No clear effect
update clusterings more often (every 1000 steps) (ablation)LA · ImageNet NN validation (ResNet-18)NN accuracy: 35.7 -> 35.7No clear effect
cluster center-crop network outputs instead of memory bank (ablation)LA · ImageNet NN validation (ResNet-18)NN accuracy: 35.7 -> 35.8No clear effect
replace Instance Recognition objective with Local Aggregation on ResNet-50ResNet-50 · ImageNet linear readout conv5top-1 accuracy: 54.0 -> 60.2Improved

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