CVAIJan 31, 2023

NASiam: Efficient Representation Learning using Neural Architecture Search for Siamese Networks

arXiv:2302.00059v14 citationsh-index: 22Has Code
Originality Incremental advance
AI Analysis

This work addresses the need for efficient architecture design in self-supervised learning, offering an incremental improvement over existing methods like SimCLR and SimSiam.

The paper tackles the problem of improving self-supervised visual representation learning in Siamese networks by using differentiable Neural Architecture Search (NAS) to optimize multilayer perceptron projectors and predictors, achieving competitive performance on datasets like CIFAR-10, CIFAR-100, and ImageNet with only a few GPU hours.

Siamese networks are one of the most trending methods to achieve self-supervised visual representation learning (SSL). Since hand labeling is costly, SSL can play a crucial part by allowing deep learning to train on large unlabeled datasets. Meanwhile, Neural Architecture Search (NAS) is becoming increasingly important as a technique to discover novel deep learning architectures. However, early NAS methods based on reinforcement learning or evolutionary algorithms suffered from ludicrous computational and memory costs. In contrast, differentiable NAS, a gradient-based approach, has the advantage of being much more efficient and has thus retained most of the attention in the past few years. In this article, we present NASiam, a novel approach that uses for the first time differentiable NAS to improve the multilayer perceptron projector and predictor (encoder/predictor pair) architectures inside siamese-networks-based contrastive learning frameworks (e.g., SimCLR, SimSiam, and MoCo) while preserving the simplicity of previous baselines. We crafted a search space designed explicitly for multilayer perceptrons, inside which we explored several alternatives to the standard ReLU activation function. We show that these new architectures allow ResNet backbone convolutional models to learn strong representations efficiently. NASiam reaches competitive performance in both small-scale (i.e., CIFAR-10/CIFAR-100) and large-scale (i.e., ImageNet) image classification datasets while costing only a few GPU hours. We discuss the composition of the NAS-discovered architectures and emit hypotheses on why they manage to prevent collapsing behavior. Our code is available at https://github.com/aheuillet/NASiam.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes