相关论文: PinPoint: Prompting with Informative Interior Poin…

Multimodal Large Language Models (MLLMs) excel at broad visual understanding but still struggle with fine-grained perception, where decisive evidence is small and easily overwhelmed by global context. Recent "Thinking-with-Images" methods…

Vision-language models (VLMs) offer flexible object detection through natural language prompts but suffer from performance variability depending on prompt phrasing. In this paper, we introduce a method for automated prompt refinement using…

With the emergence of pretrained vision-language models (VLMs), considerable efforts have been devoted to fine-tuning them for downstream tasks. Despite the progress made in designing efficient fine-tuning methods, such methods require…

The recent trend in the Large Vision and Language model has brought a new change in how information extraction systems are built. VLMs have set a new benchmark with their State-of-the-art techniques in understanding documents and building…

This work proposes POMP, a prompt pre-training method for vision-language models. Being memory and computation efficient, POMP enables the learned prompt to condense semantic information for a rich set of visual concepts with over…

Pretrained biomedical vision-language models (VLMs) such as BioMedCLIP perform well on average but often degrade on challenging modalities where inter-class margins are small and acquisition-specific variations are pronounced, especially…

Multimodal language models (MLLMs) are increasingly paired with vision tools (e.g., depth, flow, correspondence) to enhance visual reasoning. However, despite access to these tool-generated visual cues, MLLMs often fail to benefit from…

Dual-encoder Vision-Language Models (VLMs) such as CLIP are often characterized as bag-of-words systems due to their poor performance on compositional benchmarks. We argue that this limitation may stem less from deficient representations…

Large language models (LLMs) contain substantial factual knowledge which is commonly elicited by multiple-choice question-answering prompts. Internally, such models process the prompt through multiple transformer layers, building varying…

Open-set image segmentation poses a significant challenge because existing methods often demand extensive training or fine-tuning and generally struggle to segment unified objects consistently across diverse text reference expressions.…

Foreground segmentation is a fundamental problem in computer vision, which includes salient object detection, forgery detection, defocus blur detection, shadow detection, and camouflage object detection. Previous works have typically relied…

The vision community is undergoing the unprecedented progress with the emergence of Vision-Language Pretraining Models (VLMs). Prompt learning plays as the holy grail of accessing VLMs since it enables their fast adaptation to downstream…

We present a Collaborative Agent-Based Framework for Multi-Image Reasoning. Our approach tackles the challenge of interleaved multimodal reasoning across diverse datasets and task formats by employing a dual-agent system: a language-based…

Foundation models, especially vision-language models (VLMs), offer compelling zero-shot object detection for applications like autonomous driving, a domain where manual labelling is prohibitively expensive. However, their detection latency…

Camouflaged object detection (COD) approaches heavily rely on pixel-level annotated datasets. Weakly-supervised COD (WSCOD) approaches use sparse annotations like scribbles or points to reduce annotation effort, but this can lead to…

Pretrained vision-language models (VLMs) such as CLIP have shown impressive generalization capability in downstream vision tasks with appropriate text prompts. Instead of designing prompts manually, Context Optimization (CoOp) has been…

Current open-source Large Multimodal Models (LMMs) excel at tasks such as open-vocabulary language grounding and segmentation but can suffer under false premises when queries imply the existence of something that is not actually present in…

Vision-Language Models (VLMs) often struggle with tasks that require fine-grained image understanding, such as scene-text recognition or document analysis, due to perception limitations and visual fragmentation. To address these challenges,…

Vision-language models (VLMs) have gained widespread attention for their strong zero-shot capabilities across numerous downstream tasks. However, these models assume that each test image's class label is drawn from a predefined label set…

In large vision-language models, visual tokens typically constitute the majority of input tokens, leading to substantial computational overhead. To address this, recent studies have explored pruning redundant or less informative visual…