Deep Attentional Structured Representation Learning for Visual Recognition
This addresses the need for more effective visual recognition in complex tasks by incorporating attention, though it is incremental as it builds on existing structured representation methods.
The paper tackles the problem of ignoring discriminative regions in deep structured representation learning for visual recognition by introducing an attentional framework that jointly predicts image class labels and attention maps, achieving state-of-the-art results on scene recognition and fine-grained categorization benchmarks.
Structured representations, such as Bags of Words, VLAD and Fisher Vectors, have proven highly effective to tackle complex visual recognition tasks. As such, they have recently been incorporated into deep architectures. However, while effective, the resulting deep structured representation learning strategies typically aggregate local features from the entire image, ignoring the fact that, in complex recognition tasks, some regions provide much more discriminative information than others. In this paper, we introduce an attentional structured representation learning framework that incorporates an image-specific attention mechanism within the aggregation process. Our framework learns to predict jointly the image class label and an attention map in an end-to-end fashion and without any other supervision than the target label. As evidenced by our experiments, this consistently outperforms attention-less structured representation learning and yields state-of-the-art results on standard scene recognition and fine-grained categorization benchmarks.