AI Paper Atlas

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

"Idling Neurons, Appropriately Lenient Workload During Fine-tuning Leads to Better Generalization"

Hongjing Niu, Hanting Li, Bin Li, Feng Zhao

ECCV 2024 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias · 0 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 assistant model (AST) and temporary neuron inactivating (TNI) together to fine-tuning (ablation)ResNet-50 fine-tuning · CIFAR-10 retention after CIFAR-100 fine-tuningpre-train accuracy: 49.58 -> 59.30Improved
add AST+TNI (ablation)ResNet-50 fine-tuning · Unseen CIFAR-100 subsetaccuracy: 43.78 -> 51.62Improved
add AST+TNI (ablation)ResNet-50 fine-tuning · CIFAR-10.1accuracy: 40.52 -> 47.16Improved
add all three strategies (AST+LPF+TNI) versus a pairwise combination (ablation)ResNet-50 fine-tuning · CIFAR-10 (Table 2)accuracy: 60.04 -> 58.05Hurt
add TNI to fine-tuningResNet-50 fine-tuning · CUB-200-2011 (100%)accuracy: 78.01 -> 79.25Improved
add AST aloneResNet-50 fine-tuning · CUB-200-2011 (100%)accuracy: 78.01 -> 77.42No clear effect
add LPF alone (ablation)ResNet-50 fine-tuning · CIFAR-10 retention after CIFAR-100 fine-tuningpre-train accuracy: 49.58 -> 49.98No clear effect
apply the strategies to Swin-Transformer-TinySwin-T · ImageNet retention after CIFAR-10 fine-tuningaccuracy: 79.23 -> 82.29Improved
increase number of CIFAR-10 categories in target task (ablation)ImageNet-pretrained ResNet-18 · ImageNet retentionaccuracy on ImageNetHurt
increase fine-tuning sample size at fixed categories (ablation)ImageNet-pretrained ResNet-18 · ImageNet retentionaccuracy on ImageNetNo clear effect

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