Toward Deployable Bangla Sign Language Recognition with Expert-Validated Data and a Lightweight Attention-Based Model

Saad Ahmed, Md Khalid Syfullaha|August 6, 2026arXiv

Key Takeaway

You can build accurate, deployable sign language recognition systems from scratch without pretrained models—this lightweight attention-based approach matches heavy ImageNet models while using 8.5-68x fewer parameters and fitting in 0.48 MB on phones.

Summary

This paper introduces RSBdSL38, an expert-validated dataset of 10,874 images covering all 38 Bangla Sign Language hand signs, and a lightweight neural network (298K parameters) that achieves 96.37% accuracy while running on smartphones.

efficiency applications evaluation

Key Terms

attention-mechanism grouped-attention depthwise-convolution quantization grad-cam