CNNs with Multi-Level Attention for Domain Generalization

TL;DR

This paper introduces a novel CNN architecture with multi-level attention mechanisms designed to improve domain generalization in image classification, demonstrating superior performance on multiple benchmarks.

Contribution

The paper proposes a multi-level attention approach within CNNs to enhance robustness against out-of-distribution data in domain generalization tasks.

Findings

Outperforms previous methods on three of four benchmarks

Achieves second-best results on one benchmark

Demonstrates effectiveness of multi-level attention for domain robustness

Abstract

In the past decade, deep convolutional neural networks have achieved significant success in image classification and ranking and have therefore found numerous applications in multimedia content retrieval. Still, these models suffer from performance degradation when neural networks are tested on out-of-distribution scenarios or on data originating from previously unseen data Domains. In the present work, we focus on this problem of Domain Generalization and propose an alternative neural network architecture for robust, out-of-distribution image classification. We attempt to produce a model that focuses on the causal features of the depicted class for robust image classification in the Domain Generalization setting. To achieve this, we propose attending to multiple-levels of information throughout a Convolutional Neural Network and leveraging the most important attributes of an image by employing trainable attention mechanisms. To validate our method, we evaluate our model on four widely accepted Domain Generalization benchmarks, on which our model is able to surpass previously reported baselines in three out of four datasets and achieve the second best score in the fourth one.