This work aims to adapt large-scale pre-trained vision-language models, such
as contrastive language-image pretraining (CLIP), to enhance the performance of
object reidentification (Re-ID) across various supervision settings. Although
prompt learning has enabled a recent work named CLIP-ReID to achieve promising
performance, the underlying mechanisms and the necessity of prompt learning
remain unclear due to the absence of semantic labels in ReID tasks. In this
work, we first analyze the role prompt learning in CLIP-ReID and identify its
limitations. Based on our investigations, we propose a simple yet effective
approach to adapt CLIP for supervised object Re-ID. Our approach directly
fine-tunes the image encoder of CLIP using a prototypical contrastive learning
(PCL) loss, eliminating the need for prompt learning. Experimental results on
both person and vehicle Re-ID datasets demonstrate the competitiveness of our
method compared to CLIP-ReID. Furthermore, we extend our PCL-based CLIP
fine-tuning approach to unsupervised scenarios, where we achieve state-of-the
art performance.

這項研究旨在將大規模預先訓練的視覺語言模型，如對比語言 - 圖像預訓練（CLIP），適應各種監督設置下物體再識別（Re-ID）的表現提升。在本研究中，我們首先分析了 CLIP-ReID 中 prompt learning 的作用並確認了其限制。基於我們的調查，我們提出了一種簡單而有效的方法，通過使用原型對比學習（PCL）損失直接微調 CLIP 的圖像編碼器，從而消除了 prompt learning 的需要。在人物和車輛 Re-ID 數據集上的實驗結果證明了我們的方法與 CLIP-ReID 的競爭力。此外，我們將基於 PCL 的 CLIP 微調方法擴展到無監督場景，達到了最新的表現。