AI Paper Atlas

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

Imagine by Reasoning: A Reasoning-Based Implicit Semantic Data Augmentation for Long-Tailed Classification

Xiaohua Chen, Yucan Zhou, Dayan Wu, Wanqian Zhang, Yu Zhou, Bo Li, Weiping Wang

AAAI 2022 · Label-efficient and robust learning › Recognition and long-tail · approach: Decoupled and calibrated long-tail training · 55 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 reasoning-based augmentation to transfer semantic transformations from similar classes (ablation)RISDA · CIFAR-100-LT λ=200error rate (%): 56.97 -> 55.24Improved
Add reasoning-based augmentation to transfer semantic transformations from similar classes (ablation)RISDA · CIFAR-100-LT λ=100error rate (%): 51.09 -> 49.84Improved
Add reasoning-based augmentation to transfer semantic transformations from similar classes (ablation)RISDA · CIFAR-100-LT λ=50error rate (%): 47.60 -> 46.16Improved
Add reasoning-based augmentation to transfer semantic transformations from similar classes (ablation)RISDA · CIFAR-100-LT λ=20error rate (%): 42.60 -> 41.33Improved
Add reasoning-based augmentation to transfer semantic transformations from similar classes (ablation)RISDA · CIFAR-100-LT λ=10error rate (%): 38.43 -> 37.62Improved
Add class re-weighting (ablation)RISDA · CIFAR-100-LT λ=200error rate (%): 36.82 -> 55.24Hurt
Add class re-weighting (ablation)RISDA · CIFAR-100-LT λ=100error rate (%): 42.76 -> 49.84Hurt
Add class re-weighting (ablation)RISDA · CIFAR-100-LT λ=50error rate (%): 46.98 -> 46.16Hurt
Add class re-weighting (ablation)RISDA · CIFAR-100-LT λ=20error rate (%): 54.40 -> 41.33Improved
Add class re-weighting (ablation)RISDA · CIFAR-100-LT λ=10error rate (%): 58.60 -> 37.62Improved
Transfer covariance from similar classes rather than using only class-specific covariance (ablation)Implicit augmentation on CIFAR-100-LT · CIFAR-100-LT λ=200, 100, 50, 20, 10error rate (%): 56.97, 51.09, 47.6, 42.6, 38.43 -> 55.24, 49.84, 46.16, 41.33, 37.62Improved
Use RISDA instead of MetaSAugLong-tailed classification · ImageNet-LTerror rate (%): 52.61 -> 49.31Improved

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