Bowen Pan, Rameswar Panda, Yifan Jiang 0001, Zhangyang Wang, Rogério Feris, Aude Oliva. IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers. In Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, Jennifer Wortman Vaughan, editors, Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual. pages 24898-24911, 2021. [doi]
Abstract is missing.