Related papers: PinPoint: Prompting with Informative Interior Poin…

Vision-Language Models (VLMs) demonstrate impressive capabilities across multimodal tasks, yet exhibit systematic spatial reasoning failures, achieving only 49% (CLIP) to 54% (BLIP-2) accuracy on basic directional relationships. For safe…

Vision-language models (VLMs) like CLIP excel in zero-shot learning but often require resource-intensive training to adapt to new tasks. Prompt learning techniques, such as CoOp and CoCoOp, offer efficient adaptation but tend to overfit to…

Improving the generalization ability of Vision-Language Pre-trained Models (VLMs) under test-time data distribution shifts remains a critical challenge. The existing Test-Time Adaptation (TTA) methods fall short in fully leveraging the…

Vision-Language Models (VLMs) have demonstrated impressive world knowledge across a wide range of tasks, making them promising candidates for embodied reasoning applications. However, existing benchmarks primarily evaluate the embodied…

Medical Vision-Language Models (Med-VLMs) have demonstrated remarkable performance across diverse medical imaging tasks by leveraging large-scale image-text pretraining. However, their confidence calibration is largely unexplored, and so…

Foundation models such as the recently introduced Segment Anything Model (SAM) have achieved remarkable results in image segmentation tasks. However, these models typically require user interaction through handcrafted prompts such as…

Pixel-level segmentation is essential in remote sensing, where foundational vision models like CLIP and Segment Anything Model(SAM) have demonstrated significant capabilities in zero-shot segmentation tasks. Despite their advances,…

Vision-language models (VLMs) have advanced rapidly, but their ability to capture spatial relationships remains a blindspot. Current VLMs are typically built with contrastive language-image pretraining (CLIP) style image encoders. The…

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…

Pre-trained vision-language models are able to interpret visual concepts and language semantics. Prompt learning, a method of constructing prompts for text encoders or image encoders, elicits the potentials of pre-trained models and readily…

Prompt learning is an effective method to customize Vision-Language Models (VLMs) for various downstream tasks, involving tuning very few parameters of input prompt tokens. Recently, prompt pretraining in large-scale dataset (e.g.,…

Pixel-wise annotations are notoriously labourious and costly to obtain in the medical domain. To mitigate this burden, weakly supervised approaches based on bounding box annotations-much easier to acquire-offer a practical alternative.…

Video and audio inpainting for mixed audio-visual content has become a crucial task in multimedia editing recently. However, precisely removing an object and its corresponding audio from a video without affecting the rest of the scene…

Pre-trained vision-language models (VLMs) have shown impressive performance on various downstream tasks by utilizing knowledge learned from large data. In general, the performance of VLMs on target tasks can be further improved by prompt…

Pre-Trained Vision-Language Models (VL-PTMs) have shown promising capabilities in grounding natural language in image data, facilitating a broad variety of cross-modal tasks. However, we note that there exists a significant gap between the…

The Segment Anything Model (SAM) is a deep neural network foundational model designed to perform instance segmentation which has gained significant popularity given its zero-shot segmentation ability. SAM operates by generating masks based…

Can Vision-Language Models (VLMs) imagine the full scene from just a few views, like humans do? Humans form spatial mental models naturally, internal representations of unseen space, to reason about layout, perspective, and motion. Our…

Large pre-trained vision-language (VL) models can learn a new task with a handful of examples and generalize to a new task without fine-tuning. However, these VL models are hard to deploy for real-world applications due to their…

The recent advancements in large foundation models have driven the success of open-set image segmentation, a task focused on segmenting objects beyond predefined categories. Among various prompt types (such as points, boxes, texts, and…

Large-scale pretrained vision backbones have transformed computer vision by providing powerful feature extractors that enable various downstream tasks, including training-free approaches like visual prompting for semantic segmentation.…