Related papers: Mind-the-Glitch: Visual Correspondence for Detecti…

A fundamental aspect of the semantics of natural language is that novel meanings can be formed from the composition of previously known parts. Vision-language models (VLMs) have made significant progress in recent years, however, there is…

Contemporary large-scale visual language models (VLMs) exhibit strong representation capacities, making them ubiquitous for enhancing image and text understanding tasks. They are often trained in a contrastive manner on a large and diverse…

Visual grounding aims to align visual information of specific regions of images with corresponding natural language expressions. Current visual grounding methods leverage pre-trained visual and language backbones independently to obtain…

Beyond high-fidelity image synthesis, diffusion models have recently exhibited promising results in dense visual perception tasks. However, most existing work treats diffusion models as a standalone component for perception tasks, employing…

Leveraging the vision foundation models has emerged as a mainstream paradigm that improves the performance of image feature matching. However, previous works have ignored the misalignment when introducing the foundation models into feature…

Generative models have made it possible to synthesize highly realistic images, potentially providing an abundant data source for training machine learning models. Despite the advantages of these synthesizable data sources, the…

Learning visual representations with interpretable features, i.e., disentangled representations, remains a challenging problem. Existing methods demonstrate some success but are hard to apply to large-scale vision datasets like ImageNet. In…

This paper explores the possibility of learning custom tokens for representing new concepts in Vision-Language Models (VLMs). Our aim is to learn tokens that can be effective for both discriminative and generative tasks while composing well…

In the realm of image generation, creating customized images from visual prompt with additional textual instruction emerges as a promising endeavor. However, existing methods, both tuning-based and tuning-free, struggle with interpreting…

Recently, zero-shot multi-label classification has garnered considerable attention for its capacity to operate predictions on unseen labels without human annotations. Nevertheless, prevailing approaches often use seen classes as imperfect…

Multi-reference image generation aims to synthesize images from textual instructions while faithfully preserving subject identities from multiple reference images. Existing VLM-enhanced diffusion models commonly rely on decoupled visual…

Large-scale pre-trained Vision-Language Models (VLMs), such as CLIP, establish the correlation between texts and images, achieving remarkable success on various downstream tasks with fine-tuning. In existing fine-tuning methods, the…

Latent image representations arising from vision-language models have proved immensely useful for a variety of downstream tasks. However, their utility is limited by their entanglement with respect to different visual attributes. For…

Multi-view clustering has been empirically shown to improve learning performance by leveraging the inherent complementary information across multiple views of data. However, in real-world scenarios, collecting strictly aligned views is…

Recent advances in 3D generation have improved the fidelity and geometric details of synthesized 3D assets. However, due to the inherent ambiguity of single-view observations and the lack of robust global structural priors caused by limited…

Generative recommendation is emerging as a powerful paradigm that directly generates item predictions, moving beyond traditional matching-based approaches. However, current methods face two key challenges: token-item misalignment, where…

Accurate and stable feature matching is critical for computer vision tasks, particularly in applications such as Simultaneous Localization and Mapping (SLAM). While recent learning-based feature matching methods have demonstrated promising…

Evaluating single-concept personalization in text-to-image diffusion requires measuring both concept preservation, which captures identity fidelity to a reference, and prompt following, which captures whether the generated scene matches the…

Contrastive learning has achieved promising performance in the field of multi-view clustering recently. However, the positive and negative sample construction mechanisms ignoring semantic consistency lead to false negative pairs, limiting…

Multi-modal visual understanding of images with prompts involves using various visual and textual cues to enhance the semantic understanding of images. This approach combines both vision and language processing to generate more accurate…