An Empirical Study of CLIP for Text-based Person Search

TL;DR

This paper conducts a comprehensive empirical study of CLIP for text-based person search, establishing a strong baseline and analyzing design choices, generalization, and compression to guide future research in this cross-modal retrieval task.

Contribution

It is the first to systematically evaluate CLIP for TBPS, providing a straightforward baseline and insights into design, generalization, and model compression.

Findings

CLIP achieves strong performance with simple design choices

Data augmentation and loss functions significantly impact results

TBPS-CLIP generalizes well and can be compressed effectively

Abstract

Text-based Person Search (TBPS) aims to retrieve the person images using natural language descriptions. Recently, Contrastive Language Image Pretraining (CLIP), a universal large cross-modal vision-language pre-training model, has remarkably performed over various cross-modal downstream tasks due to its powerful cross-modal semantic learning capacity. TPBS, as a fine-grained cross-modal retrieval task, is also facing the rise of research on the CLIP-based TBPS. In order to explore the potential of the visual-language pre-training model for downstream TBPS tasks, this paper makes the first attempt to conduct a comprehensive empirical study of CLIP for TBPS and thus contribute a straightforward, incremental, yet strong TBPS-CLIP baseline to the TBPS community. We revisit critical design considerations under CLIP, including data augmentation and loss function. The model, with the aforementioned designs and practical training tricks, can attain satisfactory performance without any sophisticated modules. Also, we conduct the probing experiments of TBPS-CLIP in model generalization and model compression, demonstrating the effectiveness of TBPS-CLIP from various aspects. This work is expected to provide empirical insights and highlight future CLIP-based TBPS research.