TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/ResLT: Residual Learning for Long-tailed Recognition

ResLT: Residual Learning for Long-tailed Recognition

Jiequan Cui, Shu Liu, Zhuotao Tian, Zhisheng Zhong, Jiaya Jia

2021-01-26Long-tail Learning
PaperPDFCode(official)CodeCodeCodeCode

Abstract

Deep learning algorithms face great challenges with long-tailed data distribution which, however, is quite a common case in real-world scenarios. Previous methods tackle the problem from either the aspect of input space (re-sampling classes with different frequencies) or loss space (re-weighting classes with different weights), suffering from heavy over-fitting to tail classes or hard optimization during training. To alleviate these issues, we propose a more fundamental perspective for long-tailed recognition, i.e., from the aspect of parameter space, and aims to preserve specific capacity for classes with low frequencies. From this perspective, the trivial solution utilizes different branches for the head, medium, and tail classes respectively, and then sums their outputs as the final results is not feasible. Instead, we design the effective residual fusion mechanism -- with one main branch optimized to recognize images from all classes, another two residual branches are gradually fused and optimized to enhance images from medium+tail classes and tail classes respectively. Then the branches are aggregated into final results by additive shortcuts. We test our method on several benchmarks, i.e., long-tailed version of CIFAR-10, CIFAR-100, Places, ImageNet, and iNaturalist 2018. Experimental results manifest the effectiveness of our method. Our code is available at https://github.com/jiequancui/ResLT.

Results

TaskDatasetMetricValueModel
Image ClassificationCIFAR-10-LT (ρ=10)Error Rate10.3ResLT
Image ClassificationImageNet-LTTop-1 Accuracy57.6ResLT(ResNeXt-50-3 experts)
Image ClassificationImageNet-LTTop-1 Accuracy55.1ResLT(ResNeXt101-32x4d)
Image ClassificationImageNet-LTTop-1 Accuracy52.9ResLT(ResNeXt50)
Few-Shot Image ClassificationCIFAR-10-LT (ρ=10)Error Rate10.3ResLT
Few-Shot Image ClassificationImageNet-LTTop-1 Accuracy57.6ResLT(ResNeXt-50-3 experts)
Few-Shot Image ClassificationImageNet-LTTop-1 Accuracy55.1ResLT(ResNeXt101-32x4d)
Few-Shot Image ClassificationImageNet-LTTop-1 Accuracy52.9ResLT(ResNeXt50)
Generalized Few-Shot ClassificationCIFAR-10-LT (ρ=10)Error Rate10.3ResLT
Generalized Few-Shot ClassificationImageNet-LTTop-1 Accuracy57.6ResLT(ResNeXt-50-3 experts)
Generalized Few-Shot ClassificationImageNet-LTTop-1 Accuracy55.1ResLT(ResNeXt101-32x4d)
Generalized Few-Shot ClassificationImageNet-LTTop-1 Accuracy52.9ResLT(ResNeXt50)
Long-tail LearningCIFAR-10-LT (ρ=10)Error Rate10.3ResLT
Long-tail LearningImageNet-LTTop-1 Accuracy57.6ResLT(ResNeXt-50-3 experts)
Long-tail LearningImageNet-LTTop-1 Accuracy55.1ResLT(ResNeXt101-32x4d)
Long-tail LearningImageNet-LTTop-1 Accuracy52.9ResLT(ResNeXt50)
Generalized Few-Shot LearningCIFAR-10-LT (ρ=10)Error Rate10.3ResLT
Generalized Few-Shot LearningImageNet-LTTop-1 Accuracy57.6ResLT(ResNeXt-50-3 experts)
Generalized Few-Shot LearningImageNet-LTTop-1 Accuracy55.1ResLT(ResNeXt101-32x4d)
Generalized Few-Shot LearningImageNet-LTTop-1 Accuracy52.9ResLT(ResNeXt50)

Related Papers

Mitigating Spurious Correlations with Causal Logit Perturbation2025-05-21LIFT+: Lightweight Fine-Tuning for Long-Tail Learning2025-04-17Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition2024-10-28Learning from Neighbors: Category Extrapolation for Long-Tail Learning2024-10-21Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition2024-10-08AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation2024-09-30Representation Norm Amplification for Out-of-Distribution Detection in Long-Tail Learning2024-08-20LTRL: Boosting Long-tail Recognition via Reflective Learning2024-07-17