تقرير
Understanding Physical Dynamics with Counterfactual World Modeling
العنوان: | Understanding Physical Dynamics with Counterfactual World Modeling |
---|---|
المؤلفون: | Venkatesh, Rahul, Chen, Honglin, Feigelis, Kevin, Bear, Daniel M., Jedoui, Khaled, Kotar, Klemen, Binder, Felix, Lee, Wanhee, Liu, Sherry, Smith, Kevin A., Fan, Judith E., Yamins, Daniel L. K. |
سنة النشر: | 2023 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
الوصف: | The ability to understand physical dynamics is critical for agents to act in the world. Here, we use Counterfactual World Modeling (CWM) to extract vision structures for dynamics understanding. CWM uses a temporally-factored masking policy for masked prediction of video data without annotations. This policy enables highly effective "counterfactual prompting" of the predictor, allowing a spectrum of visual structures to be extracted from a single pre-trained predictor without finetuning on annotated datasets. We demonstrate that these structures are useful for physical dynamics understanding, allowing CWM to achieve the state-of-the-art performance on the Physion benchmark. Comment: ECCV 2024. Project page at: https://neuroailab.github.io/cwm-physics/ |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2312.06721 |
رقم الأكسشن: | edsarx.2312.06721 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |