Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification
This addresses the challenge of modeling spatial relations in multi-label images without spatial annotations, which is incremental by integrating spatial regularization into existing deep learning frameworks.
The paper tackles multi-label image classification by proposing a Spatial Regularization Network (SRN) that learns spatial and semantic relations between labels using only image-level supervision, achieving significant performance improvements over state-of-the-art methods on three public datasets.
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.