AI Paper Atlas

Research map / Continual learning / Class-incremental

Proxy Anchor-based Unsupervised Learning for Continuous Generalized Category Discovery

Hyungmin Kim, Sungho Suh, Daehwan Kim, Daun Jeong, Hansang Cho, Junmo Kim

ICCV 2023 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 24 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 the fine split (noisy label learning) after the cosine-similarity initial split (ablation)CGCD framework · CUB-200 (ResNet-18)M_d: 36.47 -> 40.90Improved
add the fine split with ViT-B-16 backbone (ablation)CGCD framework · CUB-200 (ViT-B-16)M_all: 70.22 -> 72.51Improved
add proxy-anchor-based exemplar feature replay (ablation)CGCD framework · CUB-200 (ResNet-18)M_f (lower is better): 36.88 -> 15.47Improved
add proxy-anchor-based exemplar (vs none) (ablation)CGCD framework · CUB-200 (ResNet-18)M_d: 41.89 -> 40.90Hurt
use proxy-anchor exemplar instead of data mean and std exemplar (ablation)CGCD framework · CUB-200 (ResNet-18)M_all: 40.23 -> 54.75Improved
use proxy anchor loss instead of ArcFace (ablation)CGCD framework · CUB-200 (ResNet-18)M_d: 28.02 -> 40.90Improved
use proxy anchor loss instead of ProxyNCA++ (ablation)CGCD framework · CUB-200 (ResNet-18)M_f (lower is better): 8.85 -> 15.47Hurt
reduce the labeled fraction of classes (old:new from 9:1 to 5:5) (ablation)CGCD framework · CUB-200 (ResNet-18)M_all: 61.34 -> 45.28Hurt
run second incremental step (two-step setting)CGCD framework · CUB-200 two-stepold-class cluster accuracy: decreases by about 20%Hurt

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