Deep learning models trained in a fully supervised manner have been shown to rely on so-called "shortcut" features. Shortcut features are inputs that are associated with the outcome of interest in the training data, but are either no longer associated or not present in testing or deployment settings. Here we provide experiments that show recent self-supervised models trained on images and text provide more robust image representations and reduce the model's reliance on visual shortcut features on a realistic medical imaging example. Additionally, we find that these self-supervised models "forget" shortcut features more quickly than fully supervised ones when fine-tuned on labeled data. Though not a complete solution, our experiments provide compelling evidence that self-supervised models trained on images and text provide some resilience to visual shortcut features.
Localising Shortcut Learning in Pixel Space via Ordinal Scoring Correlations for Attribution Representations (OSCAR)
School of Biomedical Engineering and Imaging Sciences, King’s College London（伦敦国王学院生物医学工程与成像科学系）；Department of Computer Science, University of Warwick（沃里克大学计算机科学系）
A Too-Good-to-be-True Prior to Reduce Shortcut Reliance
HSE University（俄罗斯高等经济大学）；University College London（伦敦大学学院）；Research Center Jülich（尤利希研究中心）；Heinrich Heine University Düsseldorf（海因里希·海涅大学杜塞尔多夫分校）；The Alan Turing Institute（阿兰·图灵研究所）
Deep Learning Applied to Chest X-Rays: Exploiting and Preventing Shortcuts
University of Michigan（密歇根大学）；Institute for Healthcare Policy & Innovation（医疗政策与创新研究所）；Department of Electrical Engineering and Computer Science（电气工程与计算机科学系）；Department of Radiology（放射科）；Department of Internal Medicine（内科）
Skull-stripping induces shortcut learning in MRI-based Alzheimer's disease classification
Department of Neurology, Medical University of Graz（格拉茨医科大学神经科）；Institute of Biomedical Imaging, Graz University of Technology（格拉茨技术大学生物医学成像研究所）；BioTechMed-Graz（格拉茨BioTechMed）
Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models
University of Science and Technology of China（中国科学技术大学）；State Key Lab of Cognitive Intelligence（认知智能国家重点实验室）；School of Computer Science and Technology（计算机科学与技术学院）
Beyond Classification: Structured Supervision Aligns Visual Evidence with Medical Semantics
Zhejiang University（浙江大学）；The Second Affiliated Hospital Zhejiang University（浙江大学医学院附属第二医院）；Transvascular Implantation Devices Research Institute and State Key Laboratory of Transvascular Implantation Devices（经血管植入器械研究院及经血管植入器械全国重点实验室）；Henan Normal University（河南师范大学）；University of Southampton（南安普顿大学）；School of Software Technology Zhejiang University（浙江大学软件学院）
Efficient Unsupervised Shortcut Learning Detection and Mitigation in Transformers
Goethe Universität（法兰克福歌德大学）；Philipps-Universität（马尔堡菲利普大学）；German Cancer Research Center (DKFZ)（德国癌症研究中心（DKFZ））；German Cancer Consortium (DKTK)（德国癌症联盟（DKTK））
ICON decomposition: Multivariate concept auditing reveals shortcuts that neural networks rely on
Hertie Institute for AI in Brain Health, University of Tübingen（蒂宾根大学赫蒂脑健康人工智能研究所）；Charité - Universitätsmedizin Berlin（柏林夏里特医学院）；Humboldt-Universität zu Berlin（柏林洪堡大学）；Tübingen AI Center, University of Tübingen（蒂宾根大学蒂宾根人工智能中心）；German Center for Mental Health (DZPG)（德国心理健康中心）；Fraunhofer Heinrich Hertz Institute（弗劳恩霍夫海因里希赫兹研究所）；Technische Universität Berlin（柏林工业大学）
High-Order Matching for One-Step Shortcut Diffusion Models
Middle Tennessee State University（中田纳西州立大学）；The University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of New South Wales（新南威尔士大学）；The University of Hong Kong（香港大学）；University of Wisconsin-Madison（威斯康星大学麦迪逊分校）；Tsinghua University（清华大学）；The Simons Institute for the Theory of Computing at UC Berkeley（加州大学伯克利分校西蒙斯理论计算研究所）；Anhui University（安徽大学）
MiMu: Mitigating Multiple Shortcut Learning Behavior of Transformers
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China（认知智能国家重点实验室，中国科学技术大学）；Hefei University of Technology（合肥工业大学）；iFLYTEK AI Research (Central China), iFLYTEK Co., Ltd（iFLYTEK中央研究院，iFLYTEK公司）
FiLoRA: Focus-and-Ignore LoRA for Controllable Feature Reliance
University of Melbourne, Melbourne, Australia；Brain Science Institute, Korea Institute of Science；Department of Computer Science；Engineering, Korea University, Seoul, Republic of Korea；Division of Bio-Medical Science \& Technology, University of Science；Technology KIST School, Seoul, Republic of Korea
SGD Provably Prioritizes a Shortcut Spurious Feature in the XOR Model
H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology（霍华德·米尔顿·斯图尔特工业与系统工程学院，佐治亚理工学院）；School of Electrical and Computer Engineering, Georgia Institute of Technology（电气与计算机工程学院，佐治亚理工学院）
