Contrastive Language-Image Pre-training (CLIP) has been shown to have limitations in its fine-grained dense feature representation, due to its pre-training focusing on matching the whole image to a text description. Considering the large data and computational burden in pre-training a vision-language model from scratch, a series of works aim to enhance the fine-grained ability of CLIP through a fine-tuning scheme.
The paper explores whether CLIP embeddings can detect AI-generated images by using a frozen CLIP model to extract visual embeddings and training lightweight classifiers on top. On the CIFAKE benchmark, the approach achieves 95% accuracy without language reasoning, and 85% accuracy after few-shot adaptation with 20% of the data. Certain image types, such as wide-angle photographs and oil paintings, remain challenging, highlighting unexplored difficulties in AI-generated image classification.
By Ziyang Ou
ProCAP introduces a probabilistic cross-attentive prompt learning framework for vision-language models like CLIP, enabling improved cross-modal interaction without updating the backbone. It jointly learns visual and textual prompt tokens, linking them via stacked bidirectional multi-head cross-attention to refine each branch across prompt depth. The method incorporates Gaussian parameterization of prompt tokens, lightweight KL and L2 regularization, and a compact symmetric InfoNCE head to align image features with class-level text representations, achieving strong few-shot base-to-novel performance and competitive transfer results across multiple datasets and benchmarks.
By Hiwa Azeez Abbas, Fatemeh Daneshfar, Moloud Abdar
The paper introduces Preserve-and-Compose Training (PACT) for composed image retrieval, a task where a query image is modified by a textual instruction while preserving visual content from a reference image. PACT learns from image–text–text triplets, using target captions for supervision and visual evidence from the source image to maintain relevant details, without requiring target images or gallery updates. The authors also propose Chord scoring, which blends target similarity with source-relative directional agreement in a frozen image space, and demonstrate that this combined approach yields strong retrieval performance across multiple zero-shot CIR benchmarks and various backbones.
By Sehyun Kwon
arXiv:2503. 15639v2 Announce Type: replace-cross Abstract: Modern scene text recognition systems often depend on large end-to-end architectures that require extensive training and are prohibitively expensive for real-time scenarios.
By Ritabrata Chakraborty, Shivakumara Palaiahnakote, Umapada Pal, Cheng-Lin Liu
arXiv:2603.24528v2 Announce Type: replace
Abstract: Vision-language models like CLIP are trained with the objective of aligning text and image pairs. Beyond text prompts alone, recent works show that...
By Dipam Goswami, Simone Magistri, Gido M. van de Ven, Bart{\l}omiej Twardowski, Andrew D. Bagdanov, Tinne Tuytelaars, Joost van de Weijer
arXiv:2607. 00684v1 Announce Type: new Abstract: The classification accuracy of pretrained Vision-Language Models (VLMs) relies on the quality of the text prompts.
By Seokhee Jin, Changhwan Sung, Sunung Mun, Hoyoung Kim, Jungseul Ok
The paper introduces Language-driven Dense Semantic Adaptor (LDSA) for multi-label image classification with incomplete annotations. LDSA leverages multimodal pretrained CLIP models to extract prior-adaptive relationships, employing a densely contrastive adaptor for visual contrastive constraints and a language-driven interactive decoder with class-specific prompt tuning. Experiments show LDSA achieves state‑of‑the‑art performance on public benchmarks and reveals implicit semantic relationships through its learning scheme.
By Cheng Chen, Yifan Zhao, Jia Li
arXiv:2605. 13178v2 Announce Type: replace-cross Abstract: In large vision-language models, visual tokens typically constitute the majority of input tokens, leading to substantial computational overhead.
By Sangin Lee, Yukyung Choi
arXiv:2607. 00374v1 Announce Type: cross Abstract: Composed Image Retrieval (CIR) retrieves a target image from a reference image and a textual modification.
By Jingjing Zhang, Lei Zhang, Zheren Fu, Zhendong Mao
MLLMCLIP introduces a heterogeneous distillation framework that transfers multimodal knowledge from a generative Multimodal Large Language Model (MLLM) teacher directly into a discriminative CLIP student, eliminating the need for synthetic hard negatives. The method uses an attention-based per-layer token selection and a CKA-based distillation loss to bridge architectural differences between the two models. As a result, MLLMCLIP achieves state‑of‑the‑art compositional accuracy and improves zero‑shot classification and image‑text retrieval performance.
By Jongsuk Kim, Qiyu Wu, Zhuoyuan Mao, Hiromi Wakaki, Junmo Kim, Yuki Mitsufuji
arXiv:2107.11800v2 Announce Type: replace
Abstract: Scene text detection has become an important research area in computer vision. However, dynamic changes in scenes and the complex diversity of text...
By Pengwen Dai, Feiyang He, Chaolang Li, Xugong Qin, Wenqi Ren, Xiaochun Cao