17 citations · 39 across the 5 of their papers we have counts for
5 papers
Are All Losses Created Equal: A Neural Collapse Perspective
Jinxin Zhou, Chong You, Xiao Li +4
While cross entropy (CE) is the most commonly used loss to train deep neural networks for classification tasks, many alternative losses have been developed to obtain better empiric…
Sequence-to-Sequence Modeling for Action Identification at High Temporal Resolution
Aakash Kaku, Kangning Liu, Avinash Parnandi +7
Automatic action identification from video and kinematic data is an important machine learning problem with applications ranging from robotics to smart health. Most existing works…
Weakly-supervised High-resolution Segmentation of Mammography Images for Breast Cancer Diagnosis
Kangning Liu, Yiqiu Shen, Nan Wu +3
In the last few years, deep learning classifiers have shown promising results in image-based medical diagnosis. However, interpreting the outputs of these models remains a challeng…
Unsupervised Multimodal Video-to-Video Translation via Self-Supervised Learning
Kangning Liu, Shuhang Gu, Andres Romero +1
Existing unsupervised video-to-video translation methods fail to produce translated videos which are frame-wise realistic, semantic information preserving and video-level consisten…
An interpretable classifier for high-resolution breast cancer screening images utilizing weakly supervised localization
Yiqiu Shen, Nan Wu, Jason Phang +8
Medical images differ from natural images in significantly higher resolutions and smaller regions of interest. Because of these differences, neural network architectures that work…