scst

GAN-based image captioning on MS-COCO: a CNN encoder-decoder generator with an RNN discriminator, refined via Self-Critical Sequence Training (SCST). B.Sc. thesis implementing Chen et al., AAAI 2019.

nlp reinforcement-learning computer-vision deep-learning tensorflow keras lstm generative-adversarial-network gan image-captioning image-to-text inceptionv3 scst encoder-decoder ms-coco

Updated Jun 30, 2026
Jupyter Notebook

Kirtan132003 / ada-use

Star

🌍 Explore and analyze ADA data with this user-friendly tool that simplifies access and insights into blockchain metrics.

machine-learning kernel server storage chatbot plotly cuda stock-price-prediction object-detection knowledge-base cs-education adas scsi scst usermode ada-developers-academy hcmus plotly-dash

Updated Aug 29, 2026

AbdelrahmanSaadIdress / visual-attention-captioner

Star

PyTorch image captioning: ResNet50 encoder + Bahdanau attention + LSTM decoder, trained in two stages — cross-entropy warmup then CIDEr-optimized Self-Critical Sequence Training (SCST). Outperforms Show, Attend and Tell (Xu et al., 2015) on Flickr30k. Gradio demo included.

meteor pytorch image-captioning attention-mechanism cider scst bleu self-critical-sequence-training flickr30k

Updated Jul 22, 2026
Python

Improve this page

Add a description, image, and links to the scst topic page so that developers can more easily learn about it.

Curate this topic

Add this topic to your repo

To associate your repository with the scst topic, visit your repo's landing page and select "manage topics."

Learn more