Sim-CLIP: Unsupervised Siamese Adversarial Fine-Tuning for Robust and Semantically-Rich Vision-Language Models

arXiv:2407.14971v3 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) rely heavily on pretrained vision encoders to support downstream tasks such as image captioning, visual question answering, and zero-shot classification. Despite their strong performance, these encoders remain hi