Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations

Abstract

The learning of the deep networks largely relies on the data with human-annotated labels. In some label insufficient situations, the performance degrades on the decision boundary with high data density. A common solution is to directly minimize the Shannon Entropy, but the side effect caused by entropy minimization, i.e., reduction of the prediction diversity, is mostly ignored. To address this issue, we reinvestigate the structure of classification output matrix of a randomly selected data batch. We find by theoretical analysis that the prediction discriminability and diversity could be separately measured by the Frobenius-norm and rank of the batch output matrix. Besides, the nuclear-norm is an upperbound of the Frobenius-norm, and a convex approximation of the matrix rank. Accordingly, to improve both discriminability and diversity, we propose Batch Nuclear-norm Maximization (BNM) on the output matrix. BNM could boost the learning under typical label insufficient learning scenarios, such as semi-supervised learning, domain adaptation and open domain recognition. On these tasks, extensive experimental results show that BNM outperforms competitors and works well with existing well-known methods. The code is available at https://github.com/cuishuhao/BNM.

Accepted to CVPR 2020 as Oral

References in corpus (14)

• Semi-Supervised Classification with Graph Convolutional Networks
• Guaranteed Minimum-Rank Solutions of Linear Matrix Equations via Nuclear Norm Minimization
• Learning Transferable Features with Deep Adaptation Networks
• Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results
• Semi-Supervised Learning with Deep Generative Models
• Temporal Ensembling for Semi-Supervised Learning
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• Conditional Adversarial Domain Adaptation
• Unsupervised Domain Adaptation with Residual Transfer Networks
• CyCADA: Cycle-Consistent Adversarial Domain Adaptation
• MixMatch: A Holistic Approach to Semi-Supervised Learning
• Semi-Supervised Learning with Generative Adversarial Networks
• Bridging Theory and Algorithm for Domain Adaptation
• Zero-Shot Learning -- The Good, the Bad and the Ugly

Cited by in corpus (5)

• Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation
• Rethinking Distributional Matching Based Domain Adaptation
• Gradually Vanishing Bridge for Adversarial Domain Adaptation
• Domain Adaptation Techniques for Natural and Medical Image Classification
• Temporal Fusion Network for Temporal Action Localization:Submission to ActivityNet Challenge 2020 (Task E)