Better Captioning with Sequence-Level Exploration

TL;DR

This paper identifies a limitation in current sequence-level learning for captioning, showing it favors precision over recall, and proposes an exploration term to improve recall, leading to better captioning performance.

Contribution

The paper introduces a sequence-level exploration term to balance precision and recall in captioning models, enhancing their ability to generate more comprehensive captions.

Findings

The current sequence-level objective mainly optimizes precision, neglecting recall.

Adding an exploration term improves recall in caption generation.

Experimental results demonstrate improved performance on video and image captioning datasets.

Abstract

Sequence-level learning objective has been widely used in captioning tasks to achieve the state-of-the-art performance for many models. In this objective, the model is trained by the reward on the quality of its generated captions (sequence-level). In this work, we show the limitation of the current sequence-level learning objective for captioning tasks from both theory and empirical result. In theory, we show that the current objective is equivalent to only optimizing the precision side of the caption set generated by the model and therefore overlooks the recall side. Empirical result shows that the model trained by this objective tends to get lower score on the recall side. We propose to add a sequence-level exploration term to the current objective to boost recall. It guides the model to explore more plausible captions in the training. In this way, the proposed objective takes both the precision and recall sides of generated captions into account. Experiments show the effectiveness of the proposed method on both video and image captioning datasets.