Self-Supervised Learning with an Information Maximization Criterion

16 Sep 2022  ·  Serdar Ozsoy, Shadi Hamdan, Sercan Ö. Arik, Deniz Yuret, Alper T. Erdogan ·

Self-supervised learning allows AI systems to learn effective representations from large amounts of data using tasks that do not require costly labeling. Mode collapse, i.e., the model producing identical representations for all inputs, is a central problem to many self-supervised learning approaches, making self-supervised tasks, such as matching distorted variants of the inputs, ineffective. In this article, we argue that a straightforward application of information maximization among alternative latent representations of the same input naturally solves the collapse problem and achieves competitive empirical results. We propose a self-supervised learning method, CorInfoMax, that uses a second-order statistics-based mutual information measure that reflects the level of correlation among its arguments. Maximizing this correlative information measure between alternative representations of the same input serves two purposes: (1) it avoids the collapse problem by generating feature vectors with non-degenerate covariances; (2) it establishes relevance among alternative representations by increasing the linear dependence among them. An approximation of the proposed information maximization objective simplifies to a Euclidean distance-based objective function regularized by the log-determinant of the feature covariance matrix. The regularization term acts as a natural barrier against feature space degeneracy. Consequently, beyond avoiding complete output collapse to a single point, the proposed approach also prevents dimensional collapse by encouraging the spread of information across the whole feature space. Numerical experiments demonstrate that CorInfoMax achieves better or competitive performance results relative to the state-of-the-art SSL approaches.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Self-Supervised Learning CIFAR-10 CorInfomax (ResNet18) Top-1 Accuracy 93.18 # 1
Self-Supervised Learning CIFAR-100 CorInfomax (ResNet18) Top-1 Accuracy 71.61 # 1
Self-Supervised Learning ImageNet-100 CorInfomax (ResNet50) Top-1 Accuracy 82.64 # 1
Self-Supervised Learning ImageNet-100 CorInfomax (ResNet18) Top-1 Accuracy 80.48 # 2
Self-Supervised Learning Tiny ImageNet CorInfomax (ResNet50) Top-1 Accuracy 54.86 # 1


No methods listed for this paper. Add relevant methods here