Related papers: Multi-Perspective Subimage CLIP with Keyword Guida…

Large Vision-Language Models (VLMs) face an inherent contradiction in image captioning: their powerful single-step generation capabilities often lead to a myopic decision-making process. This makes it difficult to maintain global narrative…

While multi-modal Visual Language Models (VLMs) have demonstrated significant success across various domains, the integration of VLMs into recommendation and retrieval systems remains a challenge, due to issues like training objective…

Recently, substantial advancements in pre-trained vision-language models have greatly enhanced the capabilities of multi-modal dialog systems. These models have demonstrated significant improvements by fine-tuning on downstream tasks.…

Despite the recent success of image-text contrastive models like CLIP and SigLIP, these models often struggle with vision-centric tasks that demand high-fidelity image understanding, such as counting, depth estimation, and fine-grained…

We focus on domain and class generalization problems in analyzing optical remote sensing images, using the large-scale pre-trained vision-language model (VLM), CLIP. While contrastively trained VLMs show impressive zero-shot generalization…

Language-image pre-training is an effective technique for learning powerful representations in general domains. However, when directly turning to person representation learning, these general pre-training methods suffer from unsatisfactory…

With the popularity of foundational models, parameter efficient fine tuning has become the defacto approach to leverage pretrained models to perform downstream tasks. Taking inspiration from recent advances in large language models, Visual…

A sliding-window inference strategy is commonly adopted in recent training-free open-vocabulary semantic segmentation methods to overcome limitation of the CLIP in processing high-resolution images. However, this approach introduces a new…

Unsupervised large-scale vision-language pre-training has shown promising advances on various downstream tasks. Existing methods often model the cross-modal interaction either via the similarity of the global feature of each modality which…

In this paper, we rethink sparse lexical representations for image retrieval. By utilizing multi-modal large language models (M-LLMs) that support visual prompting, we can extract image features and convert them into textual data, enabling…

Pre-trained Vision-Language Models (VLMs), like CLIP, exhibit strong generalization ability to downstream tasks but struggle in few-shot scenarios. Existing prompting techniques primarily focus on global text and image representations, yet…

Improving the safety of vision-language models like CLIP via fine-tuning often comes at a steep price, causing significant drops in their generalization performance. We find this trade-off stems from rigid alignment strategies that force…

Existing contrastive language-image pre-training aims to learn a joint representation by matching abundant image-text pairs. However, the number of image-text pairs in medical datasets is usually orders of magnitude smaller than that in…

The large-scale pretrained model CLIP, trained on 400 million image-text pairs, offers a promising paradigm for tackling vision tasks, albeit at the image level. Later works, such as DenseCLIP and LSeg, extend this paradigm to dense…

Large-scale vision-language models demonstrate strong multimodal alignment and generalization across diverse tasks. Among them, CLIP stands out as one of the most successful approaches. In this work, we extend the application of CLIP to…

CLIP models perform remarkably well on zero-shot classification and retrieval tasks. But recent studies have shown that learnt representations in CLIP are not well suited for dense prediction tasks like object detection, semantic…

Modular vision-language models (Vision-LLMs) align pretrained image encoders with (frozen) large language models (LLMs) and post-hoc condition LLMs to `understand' the image input. With the abundance of readily available high-quality…

Existing semantic segmentation approaches are often limited by costly pixel-wise annotations and predefined classes. In this work, we present CLIP-S$^4$ that leverages self-supervised pixel representation learning and vision-language models…

Remote Sensing Image-Text Retrieval (RSITR) is pivotal for knowledge services and data mining in the remote sensing (RS) domain. Considering the multi-scale representations in image content and text vocabulary can enable the models to learn…

Recent Vision-Language Models (VLMs) \textit{e.g.} CLIP have made great progress in video recognition. Despite the improvement brought by the strong visual backbone in extracting spatial features, CLIP still falls short in capturing and…