AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Automatically Discovering Novel Visual Categories With Adaptive Prototype Learning

Lu Zhang, Lu Qi, Xu Yang, Hong Qiao, Ming–Hsuan Yang, Zhiyong Liu

TPAMI 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 15 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 instance discrimination (DINO) (ablation)Ours · CIFAR100clustering accuracy: 64.7% -> 78.9%Improved
add instance discrimination (DINO) (ablation)Ours · CIFAR10clustering accuracy: 91.0% -> 96.0%Improved
add instance discrimination (DINO) (ablation)Ours · OmniGlotclustering accuracy: 89.5% -> 93.4%Improved
add category discrimination (online prototype learning) (ablation)Ours · CIFAR10clustering accuracy: 92.9% -> 96.0%Improved
add category discrimination (online prototype learning) (ablation)Ours · CIFAR100clustering accuracy: 72.8% -> 78.9%Improved
add category discrimination (online prototype learning) (ablation)Ours · OmniGlotclustering accuracy: 91.2% -> 93.4%Improved
add prototypical self-training (stage II) (ablation)Ours · CIFAR10clustering accuracy: 93.6% -> 96.0%Improved
add prototypical self-training (stage II) (ablation)Ours · CIFAR100clustering accuracy: 75.6% -> 78.9%Improved
add OPL to k-means pseudo labels (ablation)Ours · CIFAR10clustering accuracy: 91.1% -> 93.6%Improved
use offline k-means instead of online prototype labels (ablation)Ours · CIFAR10clustering accuracy: 90.5% -> 93.6%Improved
replace SimCLR/MoCo with DINO as self-supervised method (ablation)Ours · CIFAR100clustering accuracy: 61.8% -> 78.9%Improved
add the proposed method on top of DINO k-means (ablation)DINO · CIFAR100clustering accuracy: 69.6% -> 78.9%Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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