3 papers
cs.LG2023
Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity
Zhanpeng Zhou, Yongyi Yang, Xiaojiang Yang +2
Recent work has revealed many intriguing empirical phenomena in neural network training, despite the poorly understood and highly complex loss landscapes and training dynamics. One…
cs.CV2022
Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization
Xue Yang, Gefan Zhang, Xiaojiang Yang +5
Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects and an additional rotation angle parameter is used for rotated…
cs.LG2019
Towards Better Understanding of Disentangled Representations via Mutual Information
Xiaojiang Yang, Wendong Bi, Yitong Sun +2
Most existing works on disentangled representation learning are solely built upon an marginal independence assumption: all factors in disentangled representations should be statist…