AI Paper Atlas

Research map / Continual learning / Class-incremental

Novel Class Discovery without Forgetting

K J Joseph, Sujoy Paul, Gaurav Aggarwal, Soma Biswas, Piyush Rai, Kai Han, Vineeth N Balasubramanian

ECCV 2022 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 41 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 pseudo-latent replay (ablation)Ours · CIFAR-100-20-80All accuracy: 28.86 -> 67.24Improved
add pseudo-latent replay (ablation)Ours · CIFAR-10-5-5All accuracy: 62.6 -> 91.52Improved
add mutual information regularizer (ablation)Ours · CIFAR-100-20-80Unlab accuracy: 43.34 -> 49.67Improved
add mutual information regularizer (ablation)Ours · CIFAR-10-5-5All accuracy: 88.85 -> 91.52Improved
add mutual information regularizer (ablation)UNO · CIFAR-100-80unlabeled clustering accuracy: 89.31 -> 91.26Improved
add mutual information regularizer (ablation)UNO · CIFAR-100-50unlabeled clustering accuracy: 59.45 -> 61.23Improved
add mutual information regularizer (ablation)UNO · CIFAR-10-5unlabeled clustering accuracy: 94.15 -> 94.43Improved
raise KCI threshold tau from 0.8 to 0.99 (ablation)Ours · CIFAR-100-50-50 (generalized)Lab / Unlab accuracy: Lab 47.85 -> 62.76, Unlab 51.95 -> 36.42Mixed
sample mixing coefficient from Beta(100,1) instead of Beta(1,100) (ablation)Ours · CIFAR-100-80-20Unlab accuracy: 77.03 -> 12.76Hurt
sample mixing coefficient uniformly Beta(1,1) instead of Beta(1,100) (ablation)Ours · CIFAR-100-20-80All accuracy: 67.24 -> 65.91No clear effect
increase number of labeled classes (20 to 80 of CIFAR-100)Ours · CIFAR-100 (task-aware)Unlab accuracy: 49.67 -> 77.03Improved
replace UNO with OursUNO · CIFAR-100-20-80 (task-aware)All accuracy: 28.33 -> 67.24Improved

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