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/Feature Space Augmentation for Long-Tailed Data

Feature Space Augmentation for Long-Tailed Data

Peng Chu, Xiao Bian, Shaopeng Liu, Haibin Ling

2020-08-09ECCV 2020 8Image ClassificationLong-tail Learning
PaperPDF

Abstract

Real-world data often follow a long-tailed distribution as the frequency of each class is typically different. For example, a dataset can have a large number of under-represented classes and a few classes with more than sufficient data. However, a model to represent the dataset is usually expected to have reasonably homogeneous performances across classes. Introducing class-balanced loss and advanced methods on data re-sampling and augmentation are among the best practices to alleviate the data imbalance problem. However, the other part of the problem about the under-represented classes will have to rely on additional knowledge to recover the missing information. In this work, we present a novel approach to address the long-tailed problem by augmenting the under-represented classes in the feature space with the features learned from the classes with ample samples. In particular, we decompose the features of each class into a class-generic component and a class-specific component using class activation maps. Novel samples of under-represented classes are then generated on the fly during training stages by fusing the class-specific features from the under-represented classes with the class-generic features from confusing classes. Our results on different datasets such as iNaturalist, ImageNet-LT, Places-LT and a long-tailed version of CIFAR have shown the state of the art performances.

Results

TaskDatasetMetricValueModel
Image ClassificationPlaces-LTTop-1 Accuracy36.4Online Feature Augmentation
Image ClassificationImageNet-LTTop-1 Accuracy35.3Online Feature Augmentation
Few-Shot Image ClassificationPlaces-LTTop-1 Accuracy36.4Online Feature Augmentation
Few-Shot Image ClassificationImageNet-LTTop-1 Accuracy35.3Online Feature Augmentation
Generalized Few-Shot ClassificationPlaces-LTTop-1 Accuracy36.4Online Feature Augmentation
Generalized Few-Shot ClassificationImageNet-LTTop-1 Accuracy35.3Online Feature Augmentation
Long-tail LearningPlaces-LTTop-1 Accuracy36.4Online Feature Augmentation
Long-tail LearningImageNet-LTTop-1 Accuracy35.3Online Feature Augmentation
Generalized Few-Shot LearningPlaces-LTTop-1 Accuracy36.4Online Feature Augmentation
Generalized Few-Shot LearningImageNet-LTTop-1 Accuracy35.3Online Feature Augmentation

Related Papers

Automatic Classification and Segmentation of Tunnel Cracks Based on Deep Learning and Visual Explanations2025-07-18Adversarial attacks to image classification systems using evolutionary algorithms2025-07-17Efficient Adaptation of Pre-trained Vision Transformer underpinned by Approximately Orthogonal Fine-Tuning Strategy2025-07-17Federated Learning for Commercial Image Sources2025-07-17MUPAX: Multidimensional Problem Agnostic eXplainable AI2025-07-17Hashed Watermark as a Filter: Defeating Forging and Overwriting Attacks in Weight-based Neural Network Watermarking2025-07-15Transferring Styles for Reduced Texture Bias and Improved Robustness in Semantic Segmentation Networks2025-07-14FedGSCA: Medical Federated Learning with Global Sample Selector and Client Adaptive Adjuster under Label Noise2025-07-13