AI Paper Atlas

Research map / Continual learning / Class-incremental

Attaining Class-Level Forgetting in Pretrained Model Using Few Samples

Pravendra Singh, Pratik Mazumder, Mohammed Asad Karim

ECCV 2022 · Continual learning › Class-incremental · approach: Class-balanced knowledge retention · 1 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 excluded-class gradient-ascent loss to classification-only tuning (ablation)ERwP · CIFAR-100 ResNet-56FA_e: 66.50% -> 0.00%Improved
add knowledge distillation loss on remaining-class logits (ablation)ERwP · CIFAR-100 ResNet-56CA_ne: 6.45% -> 69.32%Improved
add knowledge distillation loss on remaining-class logits (ablation)ERwP · CIFAR-100 ResNet-56FPA_e: 24.40% -> 47.84%Hurt
use all identified relevant parameters instead of 25% of them (ablation)ERwP · CIFAR-100 ResNet-56FPA_e: 60.35% -> 47.84%Improved
use all identified relevant parameters instead of 50% of them (ablation)ERwP · CIFAR-100 ResNet-56FPA_e: 53.7% -> 47.84%Improved
set beta to 10 versus 8 (ablation)ERwP · CIFAR-100 ResNet-20CA_ne: 66.03% -> 66.84%Improved
set kappa to 2.0 versus 1.0 (ablation)ERwP · CIFAR-100 ResNet-20CA_ne: 66.05% -> 66.84%Improved
vary number of excluded classes from 5 to 40 (ablation)ERwP · CIFAR-100 ResNet-56FA_e: 0.00%No clear effect
use different augmentations (grayscale, flip, rotation, affine) to find relevant parameters (ablation)ERwP · CIFAR-100 ResNet-56FA_e after pruningNo clear effect
apply ERwP with full training data instead of limited (ablation)ERwP · CIFAR-100 ResNet-20FPA_e gap to FDR: 3.86% -> 2.79%Improved
apply ERwP with full training data instead of limited (ablation)ERwP · CIFAR-100 ResNet-56FPA_e gap to FDR: 2.44% -> 1.65%Improved
fine-tune on remaining-class limited data only (baseline 8) vs ERwPFOLNRC · CIFAR-100 ResNet-56FA_e: 66.90% -> 0.00%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