SCA-CNN: Spatial and Channel-wise Attention in Convolutional Networks for Image Captioning
This work addresses the limitation of existing spatial-only attention models in image captioning, offering a more comprehensive approach for generating descriptive captions.
The authors tackled the problem of visual attention in image captioning by proposing SCA-CNN, which incorporates both spatial and channel-wise attention mechanisms, and it significantly outperformed state-of-the-art methods on benchmark datasets like Flickr8K, Flickr30K, and MSCOCO.
Visual attention has been successfully applied in structural prediction tasks such as visual captioning and question answering. Existing visual attention models are generally spatial, i.e., the attention is modeled as spatial probabilities that re-weight the last conv-layer feature map of a CNN encoding an input image. However, we argue that such spatial attention does not necessarily conform to the attention mechanism --- a dynamic feature extractor that combines contextual fixations over time, as CNN features are naturally spatial, channel-wise and multi-layer. In this paper, we introduce a novel convolutional neural network dubbed SCA-CNN that incorporates Spatial and Channel-wise Attentions in a CNN. In the task of image captioning, SCA-CNN dynamically modulates the sentence generation context in multi-layer feature maps, encoding where (i.e., attentive spatial locations at multiple layers) and what (i.e., attentive channels) the visual attention is. We evaluate the proposed SCA-CNN architecture on three benchmark image captioning datasets: Flickr8K, Flickr30K, and MSCOCO. It is consistently observed that SCA-CNN significantly outperforms state-of-the-art visual attention-based image captioning methods.