Knowing When to Look: Adaptive Attention via A Visual Sentinel for Image Captioning
This addresses the inefficiency in attention mechanisms for image captioning by reducing unnecessary visual processing, though it is incremental as it builds on existing encoder-decoder frameworks.
The paper tackled the problem of forcing visual attention for every word in image captioning by proposing an adaptive attention model with a visual sentinel that decides when to attend to the image or sentinel, achieving new state-of-the-art results on COCO and Flickr30K datasets.
Attention-based neural encoder-decoder frameworks have been widely adopted for image captioning. Most methods force visual attention to be active for every generated word. However, the decoder likely requires little to no visual information from the image to predict non-visual words such as "the" and "of". Other words that may seem visual can often be predicted reliably just from the language model e.g., "sign" after "behind a red stop" or "phone" following "talking on a cell". In this paper, we propose a novel adaptive attention model with a visual sentinel. At each time step, our model decides whether to attend to the image (and if so, to which regions) or to the visual sentinel. The model decides whether to attend to the image and where, in order to extract meaningful information for sequential word generation. We test our method on the COCO image captioning 2015 challenge dataset and Flickr30K. Our approach sets the new state-of-the-art by a significant margin.