{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Daily Paper Cast","title":"Are Vision-Language Models Truly Understanding Multi-vision Sensor?","html":"","width":"100%","height":180,"duration":1490,"description":"\n 🤗 Upvotes: 9 | cs.CV\n\n Authors:\n Sangyun Chung, Youngjoon Yu, Youngchae Chee, Se Yeon Kim, Byung-Kwan Lee, Yong Man Ro\n\n Title:\n Are Vision-Language Models Truly Understanding Multi-vision Sensor?\n\n Arxiv:\n http://arxiv.org/abs/2412.20750v1\n\n Abstract:\n Large-scale Vision-Language Models (VLMs) have advanced by aligning vision inputs with text, significantly improving performance in computer vision tasks. Moreover, for VLMs to be effectively utilized in real-world applications, an understanding of diverse multi-vision sensor data, such as thermal, depth, and X-ray information, is essential. However, we find that current VLMs process multi-vision sensor images without deep understanding of sensor information, disregarding each sensor's unique physical properties. This limitation restricts their capacity to interpret and respond to complex questions requiring multi-vision sensor reasoning. To address this, we propose a novel Multi-vision Sensor Perception and Reasoning (MS-PR) benchmark, assessing VLMs on their capacity for sensor-specific reasoning. Moreover, we introduce Diverse Negative Attributes (DNA) optimization to enable VLMs to perform deep reasoning on multi-vision sensor tasks, helping to bridge the core information gap between images and sensor data. Extensive experimental results validate that the proposed DNA method can significantly improve the multi-vision sensor reasoning for VLMs.\n ","thumbnail_url":"https://img.transistorcdn.com/8lOVNnuwhrA3rxrDMv7Osu4j_t1-jORooO6NfGcQhcw/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS81Zjg1/YzRhODczMDU4MmE4/OGMwN2FiNDlmYzI2/MDliMi5qcGVn.webp","thumbnail_width":300,"thumbnail_height":300}