Pruning Convolutional Neural Networks with Self-Supervision

Abstract

Convolutional neural networks trained without supervision come close to matching performance with supervised pre-training, but sometimes at the cost of an even higher number of parameters. Extracting subnetworks from these large unsupervised convnets with preserved performance is of particular interest to make them less computationally intensive. Typical pruning methods operate during training on a task while trying to maintain the performance of the pruned network on the same task. However, in self-supervised feature learning, the training objective is agnostic on the representation transferability to downstream tasks. Thus, preserving performance for this objective does not ensure that the pruned subnetwork remains effective for solving downstream tasks. In this work, we investigate the use of standard pruning methods, developed primarily for supervised learning, for networks trained without labels (i.e. on self-supervised tasks). We show that pruned masks obtained with or without labels reach comparable performance when re-trained on labels, suggesting that pruning operates similarly for self-supervised and supervised learning. Interestingly, we also find that pruning preserves the transfer performance of self-supervised subnetwork representations.

References in corpus (9)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• SGDR: Stochastic Gradient Descent with Warm Restarts
• Rethinking the Value of Network Pruning
• Data-Efficient Image Recognition with Contrastive Predictive Coding
• Learning Representations by Maximizing Mutual Information Across Views
• Compressing Neural Networks with the Hashing Trick
• Contrastive Multiview Coding
• Linear Mode Connectivity and the Lottery Ticket Hypothesis
• Soft Weight-Sharing for Neural Network Compression

Cited by in corpus (4)

• Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
• Parameter Efficient Multimodal Transformers for Video Representation Learning
• Rethinking Bottleneck Structure for Efficient Mobile Network Design
• KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints