3.7k citations · 3.9k across the 14 of their papers we have counts for
15 papers
TCOVIS: Temporally Consistent Online Video Instance Segmentation
Junlong Li, Bingyao Yu, Yongming Rao +2
In recent years, significant progress has been made in video instance segmentation (VIS), with many offline and online methods achieving state-of-the-art performance. While offline…
Prominent Roles of Conditionally Invariant Components in Domain Adaptation: Theory and Algorithms
Keru Wu, Yuansi Chen, Wooseok Ha +1
Domain adaptation (DA) is a statistical learning problem that arises when the distribution of the source data used to train a model differs from that of the target data used to eva…
The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning
Nikhil Ghosh, Spencer Frei, Wooseok Ha +1
In this work, we investigate the dynamics of stochastic gradient descent (SGD) when training a single-neuron autoencoder with linear or ReLU activation on orthogonal data. We show…
SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference
Luciano Del Corro, Allie Del Giorno, Sahaj Agarwal +3
Autoregressive large language models (LLMs) have made remarkable progress in various natural language generation tasks. However, they incur high computation cost and latency result…
Learning Using Privileged Information for Zero-Shot Action Recognition
Zhiyi Gao, Yonghong Hou, Wanqing Li +2
Zero-Shot Action Recognition (ZSAR) aims to recognize video actions that have never been seen during training. Most existing methods assume a shared semantic space between seen and…
On the Learning Dynamics of Two-layer Nonlinear Convolutional Neural Networks
Bing Yu, Junzhao Zhang, Zhanxing Zhu
Convolutional neural networks (CNNs) have achieved remarkable performance in various fields, particularly in the domain of computer vision. However, why this architecture works wel…
No dialgebra has Gelfand-Kirillov dimension strictly between 1 and 2
Zerui Zhang, Yuqun Chen, Bing Yu
The Gelfand-Kirillov dimension measures the asymptotic growth rate of algebras. For every associative dialgebra , the quotient $\mathcal{A}_\mathcal{D}:=\mathcal{D}/\m…
3D Graph Convolutional Networks with Temporal Graphs: A Spatial Information Free Framework For Traffic Forecasting
Bing Yu, Mengzhang Li, Jiyong Zhang +1
Spatio-temporal prediction plays an important role in many application areas especially in traffic domain. However, due to complicated spatio-temporal dependency and high non-linea…
ST-UNet: A Spatio-Temporal U-Network for Graph-structured Time Series Modeling
Bing Yu, Haoteng Yin, Zhanxing Zhu
The spatio-temporal graph learning is becoming an increasingly important object of graph study. Many application domains involve highly dynamic graphs where temporal information is…
Tangent-Normal Adversarial Regularization for Semi-supervised Learning
Bing Yu, Jingfeng Wu, Jinwen Ma +1
Compared with standard supervised learning, the key difficulty in semi-supervised learning is how to make full use of the unlabeled data. A recently proposed method, virtual advers…
Load Balanced GANs for Multi-view Face Image Synthesis
Jie Cao, Yibo Hu, Bing Yu +2
Multi-view face synthesis from a single image is an ill-posed problem and often suffers from serious appearance distortion. Producing photo-realistic and identity preserving multi-…
The Anisotropic Noise in Stochastic Gradient Descent: Its Behavior of Escaping from Sharp Minima and Regularization Effects
Zhanxing Zhu, Jingfeng Wu, Bing Yu +2
Understanding the behavior of stochastic gradient descent (SGD) in the context of deep neural networks has raised lots of concerns recently. Along this line, we study a general for…
The Deep Ritz method: A deep learning-based numerical algorithm for solving variational problems
Weinan E, Bing Yu
We propose a deep learning based method, the Deep Ritz Method, for numerically solving variational problems, particularly the ones that arise from partial differential equations. T…
Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting
Bing Yu, Haoteng Yin, Zhanxing Zhu
Timely accurate traffic forecast is crucial for urban traffic control and guidance. Due to the high nonlinearity and complexity of traffic flow, traditional methods cannot satisfy…
Super quantum discord for general two qubit X states
Naihuan Jing, Bing Yu
The exact solutions of the super quantum discord are derived for general two qubit X states in terms of a one-variable function. Several exact solutions of the super quantum discor…