paper-with-me

홈 › Papers

Preventing Shortcuts in Adapter Training via Providing the Shortcuts

2025-10-23 · Anujraaj Argo Goyal, Guocheng Gordon Qian, Huseyin Coskun, Aarush Gupta, Himmy Tam, Daniil Ostashev, Ju Hu, Dhritiman Sagar, Sergey Tulyakov, Kfir Aberman, Kuan-Chieh Jackson Wang arxiv

Adapter-based training has emerged as a key mechanism for extending the capabilities of powerful foundation image generators, enabling personalized and stylized text-to-image synthesis. These adapters are typically trained to capture a specific target attribute, such as subject identity, using single-image reconstruction objectives. However, because the input image inevitably contains a mixture of visual factors, adapters are prone to entangle the target attribute with incidental ones, such as pose, expression, and lighting. This spurious correlation problem limits generalization and obstructs the model's ability to adhere to the input text prompt. In this work, we uncover a simple yet effective solution: provide the very shortcuts we wish to eliminate during adapter training. In Shortcut-Rerouted Adapter Training, confounding factors are routed through auxiliary modules, such as ControlNet or LoRA, eliminating the incentive for the adapter to internalize them. The auxiliary modules are then removed during inference. When applied to tasks like facial and full-body identity injection, our approach improves generation quality, diversity, and prompt adherence. These results point to a general design principle in the era of large models: when seeking disentangled representations, the most effective path may be to establish shortcuts for what should NOT be learned.

📄 PDF Abstract BibTeX arXiv:2510.20887

Code (0)

등록된 구현이 없습니다.

Tasks

Image Reconstruction

Similar Papers 제목 키워드 기반

Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation

2024-12-06 · David Steinmann, Felix Divo, Maurice Kraus, Antonia Wüst 외

Shortcuts, also described as Clever Hans behavior, spurious correlations, or confounders, present a significant challenge in machine learning and AI, critically affecting model generalization and robustness. Research in …

Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models

2024-02-19 · Tianjie Ju, Yijin Chen, Xinwei Yuan, Zhuosheng Zhang 외

Recent work has showcased the powerful capability of large language models (LLMs) in recalling knowledge and reasoning. However, the reliability of LLMs in combining these two capabilities into reasoning through multi-ho…

knowledge editing

Deep Learning Applied to Chest X-Rays: Exploiting and Preventing Shortcuts

2020-09-21 · Sarah Jabbour, David Fouhey, Ella Kazerooni, Michael W. Sjoding 외

While deep learning has shown promise in improving the automated diagnosis of disease based on chest X-rays, deep networks may exhibit undesirable behavior related to shortcuts. This paper studies the case of spurious cl…

AttributeRespiratory FailureTransfer Learning

Which Shortcut Solution Do Question Answering Models Prefer to Learn?

2022-11-29 · Kazutoshi Shinoda, Saku Sugawara, Akiko Aizawa

Question answering (QA) models for reading comprehension tend to learn shortcut solutions rather than the solutions intended by QA datasets. QA models that have learned shortcut solutions can achieve human-level performa…

Multiple-choiceQuestion AnsweringReading Comprehension

Exposing Image Classifier Shortcuts with Counterfactual Frequency (CoF) Tables

2024-05-24 · James Hinns, David Martens

The rise of deep learning in image classification has brought unprecedented accuracy but also highlighted a key issue: the use of 'shortcuts' by models. Such shortcuts are easy-to-learn patterns from the training data th…

counterfactualimage-classificationImage Classification