Boosting Discriminative Visual Representation Learning with Scenario-Agnostic Mixup
arXiv:2111.15454
Abstract
Mixup is a well-known data-dependent augmentation technique for DNNs, consisting of two sub-tasks: mixup generation and classification. However, the recent dominant online training method confines mixup to supervised learning (SL), and the objective of the generation sub-task is limited to selected sample pairs instead of the whole data manifold, which might cause trivial solutions. To overcome such limitations, we comprehensively study the objective of mixup generation and propose \textbf{S}cenario-\textbf{A}gnostic \textbf{Mix}up (SAMix) for both SL and Self-supervised Learning (SSL) scenarios. Specifically, we hypothesize and verify the objective function of mixup generation as optimizing local smoothness between two mixed classes subject to global discrimination from other classes. Accordingly, we propose -balanced mixup loss for complementary learning of the two sub-objectives. Meanwhile, a label-free generation sub-network is designed, which effectively provides non-trivial mixup samples and improves transferable abilities. Moreover, to reduce the computational cost of online training, we further introduce a pre-trained version, SAMix, achieving more favorable efficiency and generalizability. Extensive experiments on nine SL and SSL benchmarks demonstrate the consistent superiority and versatility of SAMix compared with existing methods.
arXiv commentPreprint version v3 with 9 pages main body and 8 pages appendix. The source code is available at \url{https://github.com/Westlake-AI/openmixup}
References in corpus (17)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- mixup: Beyond Empirical Risk Minimization
- Improved Baselines with Momentum Contrastive Learning
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- SGDR: Stochastic Gradient Descent with Warm Restarts
- Fine-Grained Visual Classification of Aircraft
- What Makes for Good Views for Contrastive Learning?
- Fast is better than free: Revisiting adversarial training
- Manifold Mixup: Better Representations by Interpolating Hidden States
- MINE: Mutual Information Neural Estimation
- A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets
- Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization
- FMix: Enhancing Mixed Sample Data Augmentation
- Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup
- i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning
- ResizeMix: Mixing Data with Preserved Object Information and True Labels
- A Unified Mixture-View Framework for Unsupervised Representation Learning