# A Better Variant of Self-Critical Sequence Training

arXiv: https://arxiv.org/abs/2003.09971 · HTML: https://mlsanity.com/paper/2003.09971/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Mar 2020.

## Built on by (most cited first, 23 of 23)

- [How Much Can CLIP Benefit Vision-and-Language Tasks?](https://mlsanity.com/paper/2107.06383/) (2021)
- [Fine-grained Image Captioning with CLIP Reward](https://mlsanity.com/paper/2205.13115/) (2022)
- [NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks](https://mlsanity.com/paper/2203.05081/) (2022)
- [Comprehending and Ordering Semantics for Image Captioning](https://mlsanity.com/paper/2206.06930/) (2022)
- [AVD2: Accident Video Diffusion for Accident Video Description](https://mlsanity.com/paper/2502.14801/) (2025)
- [Exploiting Multiple Sequence Lengths in Fast End to End Training for Image Captioning](https://mlsanity.com/paper/2208.06551/) (2022)
- [ReGen: Reinforcement Learning for Text and Knowledge Base Generation using Pretrained Language Models](https://mlsanity.com/paper/2108.12472/) (2021)
- [Reinforcement Learning-powered Semantic Communication via Semantic Similarity](https://mlsanity.com/paper/2108.12121/) (2021)
- [Semi-Autoregressive Transformer for Image Captioning](https://mlsanity.com/paper/2106.09436/) (2021)
- [Transcribing Natural Languages for The Deaf via Neural Editing Programs](https://mlsanity.com/paper/2112.09600/) (2021)
- [Image Captioning via Compact Bidirectional Architecture](https://mlsanity.com/paper/2201.01984/) (2022)
- [ACORT: A Compact Object Relation Transformer for Parameter Efficient Image Captioning](https://mlsanity.com/paper/2202.05451/) (2022)
- [When to Laugh and How Hard? A Multimodal Approach to Detecting Humor and its Intensity](https://mlsanity.com/paper/2211.01889/) (2022)
- [Generating Context-Aware Natural Answers for Questions in 3D Scenes](https://mlsanity.com/paper/2310.19516/) (2023)
- [End-to-End Supermask Pruning: Learning to Prune Image Captioning Models](https://mlsanity.com/paper/2110.03298/) (2021)
- [Exploring the sequence length bottleneck in the Transformer for Image Captioning](https://mlsanity.com/paper/2207.03327/) (2022)
- [A request for clarity over the End of Sequence token in the Self-Critical Sequence Training](https://mlsanity.com/paper/2305.12254/) (2023)
- [Goal-driven text descriptions for images](https://mlsanity.com/paper/2108.12575/) (2021)
- [Attribute Controllable Beautiful Caucasian Face Generation by Aesthetics Driven Reinforcement Learning](https://mlsanity.com/paper/2208.04517/) (2022)
- [Embedded Heterogeneous Attention Transformer for Cross-lingual Image Captioning](https://mlsanity.com/paper/2307.09915/) (2023)
- [Bounding and Filling: A Fast and Flexible Framework for Image Captioning](https://mlsanity.com/paper/2310.09876/) (2023)
- [Reinforcement Learning for Edit-Based Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/2405.01280/) (2024)
- [Variational Transformer: A Framework Beyond the Trade-off between Accuracy and Diversity for Image Captioning](https://mlsanity.com/paper/2205.14458/) (2022)

## Abstract (arXiv)

In this work, we present a simple yet better variant of Self-Critical Sequence Training. We make a simple change in the choice of baseline function in REINFORCE algorithm. The new baseline can bring better performance with no extra cost, compared to the greedy decoding baseline.