MetaSAug: Meta Semantic Augmentation for Long-Tailed Visual Recognition
arXiv:2103.12579
Abstract
Real-world training data usually exhibits long-tailed distribution, where several majority classes have a significantly larger number of samples than the remaining minority classes. This imbalance degrades the performance of typical supervised learning algorithms designed for balanced training sets. In this paper, we address this issue by augmenting minority classes with a recently proposed implicit semantic data augmentation (ISDA) algorithm, which produces diversified augmented samples by translating deep features along many semantically meaningful directions. Importantly, given that ISDA estimates the class-conditional statistics to obtain semantic directions, we find it ineffective to do this on minority classes due to the insufficient training data. To this end, we propose a novel approach to learn transformed semantic directions with meta-learning automatically. In specific, the augmentation strategy during training is dynamically optimized, aiming to minimize the loss on a small balanced validation set, which is approximated via a meta update step. Extensive empirical results on CIFAR-LT-10/100, ImageNet-LT, and iNaturalist 2017/2018 validate the effectiveness of our method.
Accepted at CVPR 2021
References in corpus (19)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Prototypical Networks for Few-shot Learning
- mixup: Beyond Empirical Risk Minimization
- A systematic study of the class imbalance problem in convolutional neural networks
- Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour
- Densely Connected Convolutional Networks
- Improved Training of Wasserstein GANs
- Focal Loss for Dense Object Detection
- Learning to Reweight Examples for Robust Deep Learning
- Data Augmentation Generative Adversarial Networks
- Meta-Learning for Semi-Supervised Few-Shot Classification
- Decoupling Representation and Classifier for Long-Tailed Recognition
- Class-Balanced Loss Based on Effective Number of Samples
- What is the Effect of Importance Weighting in Deep Learning?
- BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition
- Large-Scale Long-Tailed Recognition in an Open World
- Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective
- Distribution-Balanced Loss for Multi-Label Classification in Long-Tailed Datasets
- Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks