Self supervision to distillation for long-tailed visual recognition
T Li, L Wang, G Wu - Proceedings of the IEEE/CVF …, 2021 - openaccess.thecvf.com
Deep learning has achieved remarkable progress for visual recognition on large-scale
balanced datasets but still performs poorly on real-world long-tailed data. Previous methods …
balanced datasets but still performs poorly on real-world long-tailed data. Previous methods …
Self Supervision to Distillation for Long-Tailed Visual Recognition
T Li, L Wang, G Wu - arXiv preprint arXiv:2109.04075, 2021 - arxiv.org
Deep learning has achieved remarkable progress for visual recognition on large-scale
balanced datasets but still performs poorly on real-world long-tailed data. Previous methods …
balanced datasets but still performs poorly on real-world long-tailed data. Previous methods …
Self Supervision to Distillation for Long-Tailed Visual Recognition
T Li, L Wang, G Wu - 2021 IEEE/CVF International Conference on …, 2021 - computer.org
Deep learning has achieved remarkable progress for visual recognition on large-scale
balanced datasets but still performs poorly on real-world long-tailed data. Previous methods …
balanced datasets but still performs poorly on real-world long-tailed data. Previous methods …
Self Supervision to Distillation for Long-Tailed Visual Recognition
T Li, L Wang, G Wu - arXiv e-prints, 2021 - ui.adsabs.harvard.edu
Deep learning has achieved remarkable progress for visual recognition on large-scale
balanced datasets but still performs poorly on real-world long-tailed data. Previous methods …
balanced datasets but still performs poorly on real-world long-tailed data. Previous methods …
Self Supervision to Distillation for Long-Tailed Visual Recognition
T Li, L Wang, G Wu - 2021 IEEE/CVF International Conference …, 2021 - ieeexplore.ieee.org
Deep learning has achieved remarkable progress for visual recognition on large-scale
balanced datasets but still performs poorly on real-world long-tailed data. Previous methods …
balanced datasets but still performs poorly on real-world long-tailed data. Previous methods …