24 citations · 86 across the 17 of their papers we have counts for
18 papers
Bit-GraphBLAS: Bit-Level Optimizations of Matrix-Centric Graph Processing on GPU
Jou-An Chen, Hsin-Hsuan Sung, Xipeng Shen +3
In a general graph data structure like an adjacency matrix, when edges are homogeneous, the connectivity of two nodes can be sufficiently represented using a single bit. This insig…
SimIPU: Simple 2D Image and 3D Point Cloud Unsupervised Pre-Training for Spatial-Aware Visual Representations
Zhenyu Li, Zehui Chen, Ang Li +6
Pre-training has become a standard paradigm in many computer vision tasks. However, most of the methods are generally designed on the RGB image domain. Due to the discrepancy betwe…
GCoD: Graph Convolutional Network Acceleration via Dedicated Algorithm and Accelerator Co-Design
Haoran You, Tong Geng, Yongan Zhang +2
Graph Convolutional Networks (GCNs) have emerged as the state-of-the-art graph learning model. However, it can be notoriously challenging to inference GCNs over large graph dataset…
One Pass ImageNet
Huiyi Hu, Ang Li, Daniele Calandriello +1
We present the One Pass ImageNet (OPIN) problem, which aims to study the effectiveness of deep learning in a streaming setting. ImageNet is a widely known benchmark dataset that ha…
Semi-Supervised Vision Transformers
Zejia Weng, Xitong Yang, Ang Li +2
We study the training of Vision Transformers for semi-supervised image classification. Transformers have recently demonstrated impressive performance on a multitude of supervised l…
AEVA: Black-box Backdoor Detection Using Adversarial Extreme Value Analysis
Junfeng Guo, Ang Li, Cong Liu
Deep neural networks (DNNs) are proved to be vulnerable against backdoor attacks. A backdoor is often embedded in the target DNNs through injecting a backdoor trigger into training…
Unit Selection with Causal Diagram
Ang Li, Judea Pearl
The unit selection problem aims to identify a set of individuals who are most likely to exhibit a desired mode of behavior, for example, selecting individuals who would respond one…
Towards Adversarial Patch Analysis and Certified Defense against Crowd Counting
Qiming Wu, Zhikang Zou, Pan Zhou +3
Crowd counting has drawn much attention due to its importance in safety-critical surveillance systems. Especially, deep neural network (DNN) methods have significantly reduced esti…
Revisiting Prioritized Experience Replay: A Value Perspective
Ang A. Li, Zongqing Lu, Chenglin Miao
Experience replay enables off-policy reinforcement learning (RL) agents to utilize past experiences to maximize the cumulative reward. Prioritized experience replay that weighs exp…
PredCoin: Defense against Query-based Hard-label Attack
Junfeng Guo, Yaswanth Yadlapalli, Thiele Lothar +2
Many adversarial attacks and defenses have recently been proposed for Deep Neural Networks (DNNs). While most of them are in the white-box setting, which is impractical, a new clas…
A Bayesian Approach for Characterizing and Mitigating Gate and Measurement Errors
Muqing Zheng, Ang Li, Tamás Terlaky +1
Various noise models have been developed in quantum computing study to describe the propagation and effect of the noise which is caused by imperfect implementation of hardware. Ide…
Visual Localization Using Semantic Segmentation and Depth Prediction
Huanhuan Fan, Yuhao Zhou, Ang Li +3
In this paper, we propose a monocular visual localization pipeline leveraging semantic and depth cues. We apply semantic consistency evaluation to rank the image retrieval results…
Interference Exploitation via Symbol-Level Precoding: Overview, State-of-the-Art and Future Directions
Ang Li, Danilo Spano, Jevgenij Krivochiza +7
Interference is traditionally viewed as a performance limiting factor in wireless communication systems, which is to be minimized or mitigated. Nevertheless, a recent line of work…
Improved Knowledge Distillation via Teacher Assistant
Seyed-Iman Mirzadeh, Mehrdad Farajtabar, Ang Li +3
Despite the fact that deep neural networks are powerful models and achieve appealing results on many tasks, they are too large to be deployed on edge devices like smartphones or em…
FPDeep: Scalable Acceleration of CNN Training on Deeply-Pipelined FPGA Clusters
Tong Geng, Tianqi Wang, Ang Li +2
Deep Neural Networks (DNNs) have revolutionized numerous applications, but the demand for ever more performance remains unabated. Scaling DNN computations to larger clusters is gen…
Consistency-aware Shading Orders Selective Fusion for Intrinsic Image Decomposition
Yuanliu Liu, Ang Li, Zejian Yuan +2
We address the problem of decomposing a single image into reflectance and shading. The difficulty comes from the fact that the components of image---the surface albedo, the direct…
Interference Exploitation Precoding Made Practical: Closed-Form Solutions with Optimal Performance
Ang Li, Christos Masouros
In this paper, we propose closed-form precoding schemes with optimal performance for constructive interference (CI) exploitation in the multiuser multiple-input single-output (MU-M…
Interference Exploitation for Radar and Cellular Coexistence: The Power-Efficient Approach
Fan Liu, Christos Masouros, Ang Li +2
We propose a novel approach to enable the coexistence between Multi-Input-Multi-Output (MIMO) radar and downlink multi-user Multi-Input-Single-Output (MU-MISO) communication system…