Incidental supervision from language has become a popular approach for learning generic visual representations that can be prompted to perform many recognition tasks in computer vision. We conduct an in-depth exploration of the CLIP model and show that its visual representation is often strongly biased towards solving some tasks more than others. Moreover, which task the representation will be biased towards is unpredictable, with little consistency across images. To resolve this task bias, we show how to learn a visual prompt that guides the representation towards features relevant to their task of interest. Our results show that these visual prompts can be independent of the input image and still effectively provide a conditioning mechanism to steer visual representations towards the desired task.
Rutgers University（罗格斯大学）；HPI / University of Potsdam（哈索·普拉特纳研究所/波茨坦大学）
Recent breakthroughs in self supervised training have led to a new class of pretrained vision language models. While there have been investigations of bias in multimodal models, they have mostly focused on gender and racial bias, giving much less attention to other relevant groups, such as minorities with regard to religion, nationality, sexual orientation, or disabilities. This is mainly due to lack of suitable benchmarks for such groups. We seek to address this gap by providing a visual and textual bias benchmark called MMBias, consisting of around 3,800 images and phrases covering 14 popula…
Ask Me Again Differently: GRAS for Measuring Bias in Vision Language Models on Gender, Race, Age, and Skin Tone
Guru Gobind Singh Indraprastha University（古鲁·戈宾德·辛格印度教普拉斯塔大学）；AI Institute, University of South Carolina（南卡罗来纳大学人工智能研究所）；University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Indian Institute of Technology Patna, India（印度理工学院帕纳布分校）
Vision-language models can encode societal biases and stereotypes, but there are challenges to measuring and mitigating these multimodal harms due to lacking measurement robustness and feature degradation. To address these challenges, we investigate bias measures and apply ranking metrics for image-text representations. We then investigate debiasing methods and show that prepending learned embeddings to text queries that are jointly trained with adversarial debiasing and a contrastive loss reduces various bias measures with minimal degradation to the image-text representation.
Towards Mitigating Modality Bias in Vision-Language Models for Temporal Action Localization
UVLab, Department of Computer Science, University of Warwick（华威大学计算机科学系UVLab）；Department of Automation, University of Cambridge（剑桥大学自动化系）；Department of Computer Science, The University of Sheffield（谢菲尔德大学计算机科学系）
GABInsight: Exploring Gender-Activity Binding Bias in Vision-Language Models
Sharif University of Technology（谢里夫理工大学）；Shamsipour Technical and Vocational College（沙姆西普尔技术与职业学院）；ecole polytechnique fédérale de lausanne (EPFL)（洛桑联邦理工学院）；IDIAP research institute（IDIAP研究所）
VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models
University of Southern California（南加州大学）；University of Bristol（布里斯托大学）；Centre National de la Recherche Scientifique（法国国家科学研究中心）；University of California, Los Angeles（加州大学洛杉矶分校）
debiaSAE: Benchmarking and Mitigating Vision-Language Model Bias
Johns Hopkins University（约翰斯·霍普金斯大学）；University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）；Harvard Medical School（哈佛医学院）；Mass General Brigham（麻省总医院布里格姆医疗系统）；Boston Children’s Hospital（波士顿儿童医院）
We explore the extent to which zero-shot vision-language models exhibit gender bias for different vision tasks. Vision models traditionally required task-specific labels for representing concepts, as well as finetuning; zero-shot models like CLIP instead perform tasks with an open-vocabulary, meaning they do not need a fixed set of labels, by using text embeddings to represent concepts. With these capabilities in mind, we ask: Do vision-language models exhibit gender bias when performing zero-shot image classification, object detection and semantic segmentation? We evaluate different vision-la…
VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model
Key Laboratory of AI Safety of CAS, Institute of Computing Technology (ICT)（中国科学院人工智能安全重点实验室，计算技术研究所）；University of Chinese Academy of Sciences (UCAS)（中国科学院大学）；Peking University（北京大学）
