We show that object detectors can hallucinate and detect missing objects; potentially even accurately localized at their expected, but non-existing, position. This is particularly problematic for applications that rely on visual part verification: detecting if an object part is present or absent. We show how popular object detectors hallucinate objects in a visual part verification task and introduce the first visual part verification dataset: DelftBikes, which has 10,000 bike photographs, with 22 densely annotated parts per image, where some parts may be missing. We explicitly annotated an extra object state label for each part to reflect if a part is missing or intact. We propose to evaluate visual part verification by relying on recall and compare popular object detectors on DelftBikes.
Visual hallucination detection in large vision-language models via evidential conflict
Beijing Key Lab of Traffic Data Mining(北京交通数据挖掘与具身智能重点实验室);State Key Laboratory of Advanced Rail Autonomous Operation(先进轨道交通自主运行国家重点实验室);School of Computer Science and Technology(计算机科学与技术学院);Beijing Jiaotong University(北京交通大学);School of Automation and Intelligence(自动化与智能学院);School of Electronic and Information Engineering(电子与信息工程学院)
Locate-then-Sparsify: Attribution Guided Sparse Strategy for Visual Hallucination Mitigation
State Key Lab. of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences(中国科学院人工智能安全国家重点实验室,计算技术研究所);School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences(中国科学院大学先进交叉科学学院);School of Computer Science and Technology, University of Chinese Academy of Sciences(中国科学院大学计算机科学与技术学院)
本文提出了一种名为Locate-Then-Sparsify for Feature Steering (LTS-FS)的框架,通过定位和稀疏化策略,根据每层与幻觉的相关性调整特征引导强度,从而有效缓解视觉语言模型中的幻觉问题,同时保持良好的性能。
Hallucination Detection and Correction in Medical VLMs via Counter-Evidence Verification
College of Computer Science, Sichuan University(四川大学计算机科学学院);Yong Loo Lin School of Medicine, National University of Singapore(新加坡国立大学杨潞龄医学院);Key Laboratory of Data Protection and Intelligent Management, Ministry of Education, Sichuan University(四川大学数据保护与智能管理教育部重点实验室);National Key Laboratory of Autonomous Intelligent Unmanned Systems, Beijing Institute of Technology(北京理工大学自主智能无人系统国家重点实验室);Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR)(新加坡科技研究局高性能计算研究所)
SeeMe: Mitigating Hallucinations in Large Vision-Language Models through Effective Visual Token Engineering
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University(北京大学计算机科学学院多媒体信息处理国家重点实验室);University of Pennsylvania(宾夕法尼亚大学);University of Electronic Science and Technology of China(电子科技大学);Nanyang Technological University(南洋理工大学);Tsinghua University(清华大学);The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳));De Artificial Intelligence Lab(德人工智能实验室)
Same Attention, Different Truths: Put Logit-Lens over Visual Attention to Detect and Mitigate LVLM Object Hallucination
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);Institute of Automation, Chinese Academy of Science(中国科学院自动化研究所);Hong Kong University of Science and Technology(香港科技大学)
Semantic-Spatial Agreement Verification for Mitigating Object Hallucination in Multimodal Large Language Models
Qilu University of Technology (Shandong Academy of Sciences)(齐鲁工业大学(山东省科学院));Shandong Computer Science Center (National Supercomputer Center in Jinan)(山东省计算中心(国家超级计算济南中心));China Telecom Digital Intelligence Technology Co., Ltd.(中国电信数字智能科技有限公司);Shenyang Aerospace University(沈阳航空航天大学)
CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs
Tsinghua University(清华大学);Pengcheng Laboratory(鹏城实验室);Carnegie Mellon University(卡内基梅隆大学);University of California, Berkeley(加州大学伯克利分校);The University of Texas at Dallas(德克萨斯大学达拉斯分校);Chang’an University(长安大学)
V-ITI: Mitigating Hallucinations in Multimodal Large Language Models via Visual Inference-Time Intervention
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络安全学院);Baidu Inc.(百度公司)
SAVE: Sparse Autoencoder-Driven Visual Information Enhancement for Mitigating Object Hallucination
Department of Electrical and Computer Engineering, Seoul National University(电子与计算机工程系,首尔国立大学);Daegu Gyeongbuk Institute of Science and Technology(大邱庆州科学技术院);IPAI, AIIS, ASRI, INMC, and ISRC, Seoul National University(IPAI、AIIS、ASRI、INMC 和 ISRC,首尔国立大学)
Beyond Visual Enhancement: Adaptive Multi-Context Steering to Mitigate LVLM Hallucinations
Shanghai Jiao Tong University(上海交通大学);Peking University(北京大学);Beijing University of Chemical Technology(北京化工大学);Nanjing University of Aeronautics and Astronautics(南京航空航天大学);University of Science and Technology of China(中国科学技术大学);Tsinghua University(清华大学)
FaithSCAN: Model-Driven Single-Pass Hallucination Detection for Faithful Visual Question Answering
Institute of Information Engineering, Chinese Academy of Sciences (CAS) and the School of Cyber Security, University of CAS(信息工程研究所、中国科学院(CAS)和安全学院、CAS大学)
Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy
School of Computer Science and Engineering, Southeast University, Nanjing, China(东南大学计算机科学与工程学院);School of Artificial Intelligence, Shenzhen University, Shenzhen, China(深圳大学人工智能学院);College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China(深圳大学计算机科学与软件工程学院);Engineering, South China University of Technology, Guangzhou, China(华南理工大学工程学院);National Engineering Laboratory for Big Data Systems Computing Technology, Shenzhen University, Shenzhen, China(深圳大学大数据系统计算技术国家工程实验室);Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, China(新一代人工智能技术及其交叉应用重点实验室(东南大学),中华人民共和国教育部)
Mitigating Visual Hallucinations via Semantic Curriculum Preference Optimization in MLLMs
School of Engineering, Westlake University, Hangzhou, China(西湖大学工程学院);School of Cyberspace Security, Nanjing University of Science and Technology, Nanjing, China(南京理工大学网络安全学院)