AI Paper Atlas

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

SAFA: Sample-Adaptive Feature Augmentation for Long-Tailed Image Classification

Yan Hong, Jianfu Zhang, Zhongyi Sun, Ke Yan

ECCV 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training · 22 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 cycle reconstruction loss L_r (ablation)LDAM-DRW-SAFA · CIFAR-LT-100 rho=200top-1 error: 64.87 -> 57.53Improved
add cycle reconstruction loss L_r (ablation)LDAM-DRW-SAFA · CIFAR-LT-10 rho=200top-1 error: 31.21 -> 22.47Improved
add contrastive loss L_c (ablation)LDAM-DRW-SAFA · CIFAR-LT-100 rho=200top-1 error: 58.53 -> 57.53Improved
add head mode seeking loss (ablation)LDAM-DRW-SAFA · CIFAR-LT-100 rho=200top-1 error: 59.89 -> 57.53Improved
add head mode seeking loss (ablation)LDAM-DRW-SAFA · CIFAR-LT-100 rho=10top-1 error: 41.78 -> 40.89Improved
add tail mode seeking loss (ablation)LDAM-DRW-SAFA · CIFAR-LT-100 rho=200top-1 error: 58.87 -> 57.53Improved
add tail mode seeking loss (ablation)LDAM-DRW-SAFA · CIFAR-LT-100 rho=10top-1 error: 42.87 -> 40.89Improved
add SAFA to LDAM-DRW with ResNet-110 (ablation)LDAM-DRW · CIFAR-LT-100 rho=200top-1 error: 59.13 -> 55.17Improved
add SAFA to LDAM-DRW with DenseNet-40 (ablation)LDAM-DRW · CIFAR-LT-100 rho=200top-1 error: 58.96 -> 54.87Improved
add SAFA to LDAM-DRW with ResNet-32 at low imbalance (ablation)LDAM-DRW · CIFAR-LT-100 rho=10top-1 error: 41.22 -> 41.02Improved
add SAFA to cross-entropy via class-balanced lossCE loss · CIFAR-LT-100 rho=100top-1 error: 61.23 -> 54.13Improved
replace RSG with SAFALDAM-DRS · ImageNet-LTtop-1 accuracy: 51.8 -> 53.1Improved

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