Training Strategies for Isolated Sign Language Recognition

TL;DR

This paper presents a comprehensive training pipeline with data augmentation, regression, and IoU-balanced loss for improved isolated sign language recognition, achieving state-of-the-art results across multiple benchmarks.

Contribution

It introduces a novel training pipeline tailored for ISLR that effectively handles data quality issues and sign variability, improving recognition accuracy.

Findings

Achieves state-of-the-art results on WLASL and Slovo datasets.

Each component of the pipeline contributes to performance improvements.

The pipeline adapts well to different datasets and architectures.

Abstract

Accurate recognition and interpretation of sign language are crucial for enhancing communication accessibility for deaf and hard of hearing individuals. However, current approaches of Isolated Sign Language Recognition (ISLR) often face challenges such as low data quality and variability in gesturing speed. This paper introduces a comprehensive model training pipeline for ISLR designed to accommodate the distinctive characteristics and constraints of the Sign Language (SL) domain. The constructed pipeline incorporates carefully selected image and video augmentations to tackle the challenges of low data quality and varying sign speeds. Including an additional regression head combined with IoU-balanced classification loss enhances the model's awareness of the gesture and simplifies capturing temporal information. Extensive experiments demonstrate that the developed training pipeline easily adapts to different datasets and architectures. Additionally, the ablation study shows that each proposed component expands the potential to consider ISLR task specifics. The presented strategies enhance recognition performance across various ISLR benchmarks and achieve state-of-the-art results on the WLASL and Slovo datasets.