no code implementations • 22 Mar 2024 • Jiayun Wang, Stella X. Yu, Yubei Chen
To address this gap, we introduce a new pose-estimation benchmark for assessing SSL geometric representations, which demands training without semantic or pose labels and achieving proficiency in both semantic and geometric downstream tasks.
no code implementations • 6 Dec 2023 • Rafal Kocielnik, Elyssa Y. Wong, Timothy N. Chu, Lydia Lin, De-An Huang, Jiayun Wang, Anima Anandkumar, Andrew J. Hung
This work offers an important first look at the feasibility of automated classification of real-world live surgical feedback based on text, audio, and video modalities.
no code implementations • 7 Dec 2022 • Tejasvi Kothapalli, Charlie Shou, Jennifer Ding, Jiayun Wang, Andrew D. Graham, Tatyana Svitova, Stella X. Yu, Meng C. Lin
Tear film instability is a known factor for DED, and is thought to be regulated in large part by the thin lipid layer that covers and stabilizes the tear film.
1 code implementation • 6 Sep 2022 • Jiayun Wang, Sangryul Jeon, Stella X. Yu, Xi Zhang, Himanshu Arora, Yu Lou
Taking this advantage, we synthesize a photo-realistic image by combining the structure of a sketch and the visual style of a reference photo.
no code implementations • 17 Aug 2022 • Ziwei Liu, Zhongqi Miao, Xiaohang Zhan, Jiayun Wang, Boqing Gong, Stella X. Yu
A practical recognition system must balance between majority (head) and minority (tail) classes, generalize across the distribution, and acknowledge novelty upon the instances of unseen classes (open classes).
1 code implementation • 15 Jul 2021 • Jiayun Wang, Yubei Chen, Stella X. Yu, Brian Cheung, Yann Lecun
We propose a drastically different approach to compact and optimal deep learning: We decouple the Degrees of freedom (DoF) and the actual number of parameters of a model, optimize a small DoF with predefined random linear constraints for a large model of arbitrary architecture, in one-stage end-to-end learning.
Ranked #97 on Image Classification on ObjectNet (using extra training data)
no code implementations • ICCV 2021 • Wentao Jiang, Ning Xu, Jiayun Wang, Chen Gao, Jing Shi, Zhe Lin, Si Liu
Given the cycle, we propose several free augmentation strategies to help our model understand various editing requests given the imbalanced dataset.
1 code implementation • 17 Jun 2020 • Jiayun Wang, Jierui Lin, Qian Yu, Runtao Liu, Yubei Chen, Stella X. Yu
Additionally, we propose a sketch standardization module to handle different sketch distortions and styles.
1 code implementation • Translational Vision Science & Technology 2019 • Jiayun Wang, Thao N. Yeh, Rudrasis Chakraborty, Stella X. Yu, Meng C. Lin
The development set was used to train and tune the deep learning model, while the evaluation set was used to evaluate the performance of the model.
1 code implementation • CVPR 2020 • Jiayun Wang, Yubei Chen, Rudrasis Chakraborty, Stella X. Yu
We develop an efficient approach to impose filter orthogonality on a convolutional layer based on the doubly block-Toeplitz matrix representation of the convolutional kernel instead of using the common kernel orthogonality approach, which we show is only necessary but not sufficient for ensuring orthogonal convolutions.
no code implementations • 23 Sep 2019 • Jiayun Wang
In this paper, we propose a coupled spatial-temporal attention (CSTA) model for skeleton-based action recognition, which aims to figure out the most discriminative joints and frames in spatial and temporal domains simultaneously.
1 code implementation • 26 Jun 2019 • Jiayun Wang, Rudrasis Chakraborty, Stella X. Yu
We propose a novel end-to-end approach to learn different non-rigid transformations of the input point cloud so that optimal local neighborhoods can be adopted at each layer.
1 code implementation • 24 Jun 2019 • Rudrasis Chakraborty, Jiayun Wang, Stella X. Yu
On RadioML, our model achieves comparable RF modulation classification accuracy at 10% of the baseline model size.
2 code implementations • CVPR 2019 • Ziwei Liu, Zhongqi Miao, Xiaohang Zhan, Jiayun Wang, Boqing Gong, Stella X. Yu
We define Open Long-Tailed Recognition (OLTR) as learning from such naturally distributed data and optimizing the classification accuracy over a balanced test set which include head, tail, and open classes.
1 code implementation • 5 Dec 2017 • Jiayun Wang, Patrick Virtue, Stella X. Yu
To address the overfitting problem in aerial image classification, we consider the neural network as successive transformations of an input image into embedded feature representations and ultimately into a semantic class label, and train neural networks to optimize image representations in the embedded space in addition to optimizing the final classification score.
no code implementations • 3 Jul 2017 • Jiayun Wang, Sanping Zhou, Jinjun Wang, Qiqi Hou
In this paper, we present a novel deep ranking model with feature learning and fusion by learning a large adaptive margin between the intra-class distance and inter-class distance to solve the person re-identification problem.
no code implementations • CVPR 2017 • Sanping Zhou, Jinjun Wang, Jiayun Wang, Yihong Gong, Nanning Zheng
One of the key issues for deep learning based person Re-ID is the selection of proper similarity comparison criteria, and the performance of learned features using existing criterion based on pairwise similarity is still limited, because only P2P distances are mostly considered.