Stack-Captioning: Coarse-to-Fine Learning for Image Captioning
This addresses the difficulty of training multi-stage image captioning models due to vanishing gradients, benefiting computer vision and natural language processing applications.
The paper tackles the problem of generating rich fine-grained image descriptions by proposing a coarse-to-fine multi-stage prediction framework with multiple decoders, achieving state-of-the-art performance on MSCOCO.
The existing image captioning approaches typically train a one-stage sentence decoder, which is difficult to generate rich fine-grained descriptions. On the other hand, multi-stage image caption model is hard to train due to the vanishing gradient problem. In this paper, we propose a coarse-to-fine multi-stage prediction framework for image captioning, composed of multiple decoders each of which operates on the output of the previous stage, producing increasingly refined image descriptions. Our proposed learning approach addresses the difficulty of vanishing gradients during training by providing a learning objective function that enforces intermediate supervisions. Particularly, we optimize our model with a reinforcement learning approach which utilizes the output of each intermediate decoder's test-time inference algorithm as well as the output of its preceding decoder to normalize the rewards, which simultaneously solves the well-known exposure bias problem and the loss-evaluation mismatch problem. We extensively evaluate the proposed approach on MSCOCO and show that our approach can achieve the state-of-the-art performance.