1 code implementation • 21 Nov 2023 • Boyang Yu, Aakash Kaku, Kangning Liu, Avinash Parnandi, Emily Fokas, Anita Venkatesan, Natasha Pandit, Rajesh Ranganath, Heidi Schambra, Carlos Fernandez-Granda
We applied the COBRA score to address a key limitation of current clinical evaluation of upper-body impairment in stroke patients.
no code implementations • 27 Apr 2023 • Kangning Liu, Yu-Chuan Su, Wei, Hong, Ruijin Cang, Xuhui Jia
The one-shot talking-head synthesis task aims to animate a source image to another pose and expression, which is dictated by a driving frame.
1 code implementation • CVPR 2023 • Kangning Liu, Weicheng Zhu, Yiqiu Shen, Sheng Liu, Narges Razavian, Krzysztof J. Geras, Carlos Fernandez-Granda
The framework employs a novel self-paced sampling strategy to ensure the accuracy of pseudo labels.
no code implementations • 4 Oct 2022 • Jinxin Zhou, Chong You, Xiao Li, Kangning Liu, Sheng Liu, Qing Qu, Zhihui Zhu
We extend such results and show through global solution and landscape analyses that a broad family of loss functions including commonly used label smoothing (LS) and focal loss (FL) exhibits Neural Collapse.
1 code implementation • 3 Nov 2021 • Aakash Kaku, Kangning Liu, Avinash Parnandi, Haresh Rengaraj Rajamohan, Kannan Venkataramanan, Anita Venkatesan, Audre Wirtanen, Natasha Pandit, Heidi Schambra, Carlos Fernandez-Granda
To address this, we propose a novel approach for high-resolution action identification, inspired by speech-recognition techniques, which is based on a sequence-to-sequence model that directly predicts the sequence of actions.
2 code implementations • CVPR 2022 • Sheng Liu, Kangning Liu, Weicheng Zhu, Yiqiu Shen, Carlos Fernandez-Granda
We discover a phenomenon that has been previously reported in the context of classification: the networks tend to first fit the clean pixel-level labels during an "early-learning" phase, before eventually memorizing the false annotations.
1 code implementation • 22 Sep 2021 • Xiaoxia Zhang, Quentin Duchemin, Kangning Liu, Sebastian Flassbeck, Cem Gultekin, Carlos Fernandez-Granda, Jakob Assländer
We find, however, that in heterogeneous parameter spaces, i. e. in spaces in which the variance of the estimated parameters varies considerably, good performance is hard to achieve and requires arduous tweaking of the loss function, hyper parameters, and the distribution of the training data in parameter space.
1 code implementation • 13 Jun 2021 • Kangning Liu, Yiqiu Shen, Nan Wu, Jakub Chłędowski, Carlos Fernandez-Granda, Krzysztof J. Geras
In cancer diagnosis, interpretability can be achieved by localizing the region of the input image responsible for the output, i. e. the location of a lesion.
no code implementations • 14 Apr 2020 • Kangning Liu, Shuhang Gu, Andres Romero, Radu Timofte
Existing unsupervised video-to-video translation methods fail to produce translated videos which are frame-wise realistic, semantic information preserving and video-level consistent.
1 code implementation • 13 Feb 2020 • Yiqiu Shen, Nan Wu, Jason Phang, Jungkyu Park, Kangning Liu, Sudarshini Tyagi, Laura Heacock, S. Gene Kim, Linda Moy, Kyunghyun Cho, Krzysztof J. Geras
In this work, we extend the globally-aware multiple instance classifier, a framework we proposed to address these unique properties of medical images.