no code implementations • ECCV 2020 • Jiayan Qiu, Yiding Yang, Xinchao Wang, DaCheng Tao
This seemingly minor difference in fact makes the HVITA a much challenging task, as the restoration algorithm would have to not only infer the category of the object in total absentia, but also hallucinate an object of which the appearance is consistent with the background.
no code implementations • CVPR 2021 • Jiayan Qiu, Yiding Yang, Xinchao Wang, DaCheng Tao
What scene elements, if any, are indispensable for recognizing a scene?
no code implementations • 1 Apr 2021 • Junhui Yin, Jiayan Qiu, Siqing Zhang, Jiyang Xie, Zhanyu Ma, Jun Guo
Unsupervised person re-identification (re-ID) has become an important topic due to its potential to resolve the scalability problem of supervised re-ID models.
no code implementations • ECCV 2020 • Yiding Yang, Jiayan Qiu, Mingli Song, DaCheng Tao, Xinchao Wang
Prior gradient-based attribution-map methods rely on handcrafted propagation rules for the non-linear/activation layers during the backward pass, so as to produce gradients of the input and then the attribution map.
no code implementations • 13 Sep 2020 • Junhui Yin, Jiayan Qiu, Siqing Zhang, Zhanyu Ma, Jun Guo
To this end, we propose a Self-Supervised Knowledge Distillation (SSKD) technique containing two modules, the identity learning and the soft label learning.
1 code implementation • CVPR 2020 • Yiding Yang, Jiayan Qiu, Mingli Song, DaCheng Tao, Xinchao Wang
To enable the knowledge transfer from the teacher GCN to the student, we propose a local structure preserving module that explicitly accounts for the topological semantics of the teacher.
no code implementations • CVPR 2019 • Jiayan Qiu, Xinchao Wang, Stephen J. Maybank, Dacheng Tao
What can we tell from a single motion-blurred image?
no code implementations • 25 Jul 2017 • Yunhe Wang, Chang Xu, Jiayan Qiu, Chao Xu, DaCheng Tao
In contrast to directly recognizing subtle weights or filters as redundant in a given CNN, this paper presents an evolutionary method to automatically eliminate redundant convolution filters.