CVMar 11, 2024

GRITv2: Efficient and Light-weight Social Relation Recognition

arXiv:2403.06895v1h-index: 2
Originality Incremental advance
AI Analysis

This work addresses the need for efficient and accurate social relation recognition models, particularly for deployment on resource-constrained mobile devices, and is incremental as it builds upon the existing GRIT benchmark.

The research tackled improving the Graph-based Relation Inference Transformer (GRIT) for social relation recognition, achieving a new state-of-the-art on the PISC dataset and compressing the model to 22MB for mobile deployment with maintained performance.

Our research focuses on the analysis and improvement of the Graph-based Relation Inference Transformer (GRIT), which serves as an important benchmark in the field. We conduct a comprehensive ablation study using the PISC-fine dataset, to find and explore improvement in efficiency and performance of GRITv2. Our research has provided a new state-of-the-art relation recognition model on the PISC relation dataset. We introduce several features in the GRIT model and analyse our new benchmarks in two versions: GRITv2-L (large) and GRITv2-S (small). Our proposed GRITv2-L surpasses existing methods on relation recognition and the GRITv2-S is within 2% performance gap of GRITv2-L, which has only 0.0625x the model size and parameters of GRITv2-L. Furthermore, we also address the need for model compression, an area crucial for deploying efficient models on resource-constrained platforms. By applying quantization techniques, we efficiently reduced the GRITv2-S size to 22MB and deployed it on the flagship OnePlus 12 mobile which still surpasses the PISC-fine benchmarks in performance, highlighting the practical viability and improved efficiency of our model on mobile devices.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes