Papers › A Better Variant of Self-Critical Sequence Training
A Better Variant of Self-Critical Sequence Training
Ruotian Luo
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Image Captioning | COCO Captions | Transformer_NSC | BLEU-1 | 80.7 | #24 of 41 | Archive leaderboard | report |
| Image Captioning | COCO Captions | Transformer_NSC | BLEU-2 | 65.6 | #24 of 41 | Archive leaderboard | report |
| Image Captioning | COCO Captions | Transformer_NSC | BLEU-3 | 51.3 | #24 of 41 | Archive leaderboard | report |
| Image Captioning | COCO Captions | Transformer_NSC | BLEU-4 | 39.4 | #24 of 41 | Archive leaderboard | report |
| Image Captioning | COCO Captions | Transformer_NSC | CIDER | 129.6 | #24 of 41 | Archive leaderboard | report |
| Image Captioning | COCO Captions | Transformer_NSC | METEOR | 28.9 | #24 of 41 | Archive leaderboard | report |
| Image Captioning | COCO Captions | Transformer_NSC | ROUGE-L | 58.7 | #24 of 41 | Archive leaderboard | report |
| Image Captioning | COCO Captions | Transformer_NSC | SPICE | 22.8 | #24 of 41 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections