13 citations · 29 across the 14 of their papers we have counts for
14 papers
A Spectral Perspective towards Understanding and Improving Adversarial Robustness
Binxiao Huang, Rui Lin, Chaofan Tao +1
Deep neural networks (DNNs) are incredibly vulnerable to crafted, imperceptible adversarial perturbations. While adversarial training (AT) has proven to be an effective defense app…
DyBit: Dynamic Bit-Precision Numbers for Efficient Quantized Neural Network Inference
Jiajun Zhou, Jiajun Wu, Yizhao Gao +7
To accelerate the inference of deep neural networks (DNNs), quantization with low-bitwidth numbers is actively researched. A prominent challenge is to quantize the DNN models into…
ODG-Q: Robust Quantization via Online Domain Generalization
Chaofan Tao, Ngai Wong
Quantizing neural networks to low-bitwidth is important for model deployment on resource-limited edge hardware. Although a quantized network has a smaller model size and memory foo…
PECAN: A Product-Quantized Content Addressable Memory Network
Jie Ran, Rui Lin, Jason Chun Lok Li +2
A novel deep neural network (DNN) architecture is proposed wherein the filtering and linear transform are realized solely with product quantization (PQ). This results in a natural…
MAP-Gen: An Automated 3D-Box Annotation Flow with Multimodal Attention Point Generator
Chang Liu, Xiaoyan Qian, Xiaojuan Qi +3
Manually annotating 3D point clouds is laborious and costly, limiting the training data preparation for deep learning in real-world object detection. While a few previous studies t…
Deformable Butterfly: A Highly Structured and Sparse Linear Transform
Rui Lin, Jie Ran, King Hung Chiu +2
We introduce a new kind of linear transform named Deformable Butterfly (DeBut) that generalizes the conventional butterfly matrices and can be adapted to various input-output dimen…
What Do Adversarially trained Neural Networks Focus: A Fourier Domain-based Study
Binxiao Huang, Chaofan Tao, Rui Lin +1
Although many fields have witnessed the superior performance brought about by deep learning, the robustness of neural networks remains an open issue. Specifically, a small adversar…
Compression of Generative Pre-trained Language Models via Quantization
Chaofan Tao, Lu Hou, Wei Zhang +5
The increasing size of generative Pre-trained Language Models (PLMs) has greatly increased the demand for model compression. Despite various methods to compress BERT or its variant…
EZCrop: Energy-Zoned Channels for Robust Output Pruning
Rui Lin, Jie Ran, Dongpeng Wang +2
Recent results have revealed an interesting observation in a trained convolutional neural network (CNN), namely, the rank of a feature map channel matrix remains surprisingly const…
AET-EFN: A Versatile Design for Static and Dynamic Event-Based Vision
Chang Liu, Xiaojuan Qi, Edmund Lam +1
The neuromorphic event cameras, which capture the optical changes of a scene, have drawn increasing attention due to their high speed and low power consumption. However, the event…
FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware Transformation
Chaofan Tao, Rui Lin, Quan Chen +3
Learning convolutional neural networks (CNNs) with low bitwidth is challenging because performance may drop significantly after quantization. Prior arts often discretize the networ…
S3-Net: A Fast and Lightweight Video Scene Understanding Network by Single-shot Segmentation
Yuan Cheng, Yuchao Yang, Hai-Bao Chen +2
Real-time understanding in video is crucial in various AI applications such as autonomous driving. This work presents a fast single-shot segmentation strategy for video scene under…
HOTCAKE: Higher Order Tucker Articulated Kernels for Deeper CNN Compression
Rui Lin, Ching-Yun Ko, Zhuolun He +5
The emerging edge computing has promoted immense interests in compacting a neural network without sacrificing much accuracy. In this regard, low-rank tensor decomposition constitut…
MiSC: Mixed Strategies Crowdsourcing
Ching-Yun Ko, Rui Lin, Shu Li +1
Popular crowdsourcing techniques mostly focus on evaluating workers' labeling quality before adjusting their weights during label aggregation. Recently, another cohort of models re…