CVDec 27, 2017

Consensus-based Sequence Training for Video Captioning

arXiv:1712.09532v122 citations
Originality Highly original
AI Analysis

This work addresses the problem of slow and unstable training for video captioning models, offering a more efficient method for researchers and practitioners in computer vision and natural language processing.

The authors tackled the computational cost and convergence issues of reinforcement learning for video captioning by proposing a fast RL-based pre-training algorithm and using consensus among ground-truth captions as a baseline reward, achieving a CIDEr score improvement from 47.3 to 54.2 on the MSRVTT benchmark.

Captioning models are typically trained using the cross-entropy loss. However, their performance is evaluated on other metrics designed to better correlate with human assessments. Recently, it has been shown that reinforcement learning (RL) can directly optimize these metrics in tasks such as captioning. However, this is computationally costly and requires specifying a baseline reward at each step to make training converge. We propose a fast approach to optimize one's objective of interest through the REINFORCE algorithm. First we show that, by replacing model samples with ground-truth sentences, RL training can be seen as a form of weighted cross-entropy loss, giving a fast, RL-based pre-training algorithm. Second, we propose to use the consensus among ground-truth captions of the same video as the baseline reward. This can be computed very efficiently. We call the complete proposal Consensus-based Sequence Training (CST). Applied to the MSRVTT video captioning benchmark, our proposals train significantly faster than comparable methods and establish a new state-of-the-art on the task, improving the CIDEr score from 47.3 to 54.2.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes