Multi-Scale and Multi-Layer Contrastive Learning for Domain Generalization

Abstract

During the past decade, deep neural networks have led to fast-paced progress and significant achievements in computer vision problems, for both academia and industry. Yet despite their success, state-of-the-art image classification approaches fail to generalize well in previously unseen visual contexts, as required by many real-world applications. In this paper, we focus on this domain generalization (DG) problem and argue that the generalization ability of deep convolutional neural networks can be improved by taking advantage of multi-layer and multi-scaled representations of the network. We introduce a framework that aims at improving domain generalization of image classifiers by combining both low-level and high-level features at multiple scales, enabling the network to implicitly disentangle representations in its latent space and learn domain-invariant attributes of the depicted objects. Additionally, to further facilitate robust representation learning, we propose a novel objective function, inspired by contrastive learning, which aims at constraining the extracted representations to remain invariant under distribution shifts. We demonstrate the effectiveness of our method by evaluating on the domain generalization datasets of PACS, VLCS, Office-Home and NICO. Through extensive experimentation, we show that our model is able to surpass the performance of previous DG methods and consistently produce competitive and state-of-the-art results in all datasets

Manuscript accepted in: IEEE Transactions on Artificial Intelligence (March 2024)

References in corpus (23)

• Auto-Encoding Variational Bayes
• Distilling the Knowledge in a Neural Network
• Decoupled Weight Decay Regularization
• A Simple Framework for Contrastive Learning of Visual Representations
• Representation Learning with Contrastive Predictive Coding
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Bootstrap your own latent: A new approach to self-supervised Learning
• Learning Transferable Features with Deep Adaptation Networks
• Deep Visual Domain Adaptation: A Survey
• Shortcut Learning in Deep Neural Networks
• Domain Generalization: A Survey
• Disentangling by Factorising
• Domain Generalization via Invariant Feature Representation
• Do ImageNet Classifiers Generalize to ImageNet?
• Towards a Definition of Disentangled Representations
• Understanding disentangling in $\beta$-VAE
• On the Expressive Power of Deep Learning: A Tensor Analysis
• Improve Unsupervised Domain Adaptation with Mixup Training
• Towards Domain Generalization for ECG and EEG Classification: Algorithms and Benchmarks
• Revisiting Locally Supervised Learning: an Alternative to End-to-end Training
• Probable Domain Generalization via Quantile Risk Minimization
• Multi-layer Representation Learning for Robust OOD Image Classification
• CNN Feature Map Augmentation for Single-Source Domain Generalization

Cited by in corpus (1)

• Which Augmentation Should I Use? An Empirical Investigation of Augmentations for Self-Supervised Phonocardiogram Representation Learning