Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification

TL;DR

This paper introduces a deep neural network that leverages image-level supervision to model both semantic and spatial label relations, significantly enhancing multi-label image classification performance without requiring detailed spatial annotations.

Contribution

The proposed Spatial Regularization Network (SRN) uniquely captures spatial and semantic label relations using only image-level annotations, improving classification accuracy.

Findings

Outperforms state-of-the-art methods on three public datasets.

Effectively captures semantic and spatial label relations.

Improves classification performance with end-to-end training.

Abstract

Multi-label image classification is a fundamental but challenging task in computer vision. Great progress has been achieved by exploiting semantic relations between labels in recent years. However, conventional approaches are unable to model the underlying spatial relations between labels in multi-label images, because spatial annotations of the labels are generally not provided. In this paper, we propose a unified deep neural network that exploits both semantic and spatial relations between labels with only image-level supervisions. Given a multi-label image, our proposed Spatial Regularization Network (SRN) generates attention maps for all labels and captures the underlying relations between them via learnable convolutions. By aggregating the regularized classification results with original results by a ResNet-101 network, the classification performance can be consistently improved. The whole deep neural network is trained end-to-end with only image-level annotations, thus requires no additional efforts on image annotations. Extensive evaluations on 3 public datasets with different types of labels show that our approach significantly outperforms state-of-the-arts and has strong generalization capability. Analysis of the learned SRN model demonstrates that it can effectively capture both semantic and spatial relations of labels for improving classification performance.