247 citations · 396 across the 13 of their papers we have counts for
13 papers
Vector Quantization Prompting for Continual Learning
Li Jiao, Qiuxia Lai, Yu Li +1
Continual learning requires to overcome catastrophic forgetting when training a single model on a sequence of tasks. Recent top-performing approaches are prompt-based methods that…
Evaluating Text-to-Image Generative Models: An Empirical Study on Human Image Synthesis
Muxi Chen, Yi Liu, Jian Yi +5
In this paper, we present an empirical study introducing a nuanced evaluation framework for text-to-image (T2I) generative models, applied to human image synthesis. Our framework c…
BIFRNet: A Brain-Inspired Feature Restoration DNN for Partially Occluded Image Recognition
Jiahong Zhang, Lihong Cao, Qiuxia Lai +2
The partially occluded image recognition (POIR) problem has been a challenge for artificial intelligence for a long time. A common strategy to handle the POIR problem is using the…
DeepSAT: An EDA-Driven Learning Framework for SAT
Min Li, Zhengyuan Shi, Qiuxia Lai +3
We present DeepSAT, a novel end-to-end learning framework for the Boolean satisfiability (SAT) problem. Unlike existing solutions trained on random SAT instances with relatively we…
What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradiction
Yijun Yang, Ruiyuan Gao, Yu Li +2
Adversarial examples (AEs) pose severe threats to the applications of deep neural networks (DNNs) to safety-critical domains, e.g., autonomous driving. While there has been a vast…
Information Bottleneck Approach to Spatial Attention Learning
Qiuxia Lai, Yu Li, Ailing Zeng +3
The selective visual attention mechanism in the human visual system (HVS) restricts the amount of information to reach visual awareness for perceiving natural scenes, allowing near…
SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interaction
Minhao Liu, Ailing Zeng, Muxi Chen +4
One unique property of time series is that the temporal relations are largely preserved after downsampling into two sub-sequences. By taking advantage of this property, we propose…
TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks
Yu Li, Min Li, Qiuxia Lai +2
Deep learning (DL) has achieved unprecedented success in a variety of tasks. However, DL systems are notoriously difficult to test and debug due to the lack of explainability of DL…
MixDefense: A Defense-in-Depth Framework for Adversarial Example Detection Based on Statistical and Semantic Analysis
Yijun Yang, Ruiyuan Gao, Yu Li +2
Machine learning with deep neural networks (DNNs) has become one of the foundation techniques in many safety-critical systems, such as autonomous vehicles and medical diagnosis sys…
T-WaveNet: Tree-Structured Wavelet Neural Network for Sensor-Based Time Series Analysis
Minhao Liu, Ailing Zeng, Qiuxia Lai +1
Sensor-based time series analysis is an essential task for applications such as activity recognition and brain-computer interface. Recently, features extracted with deep neural net…
DeepFuse: An IMU-Aware Network for Real-Time 3D Human Pose Estimation from Multi-View Image
Fuyang Huang, Ailing Zeng, Minhao Liu +2
In this paper, we propose a two-stage fully 3D network, namely \textbf{DeepFuse}, to estimate human pose in 3D space by fusing body-worn Inertial Measurement Unit (IMU) data and mu…
Understanding More about Human and Machine Attention in Deep Neural Networks
Qiuxia Lai, Salman Khan, Yongwei Nie +3
Human visual system can selectively attend to parts of a scene for quick perception, a biological mechanism known as Human attention. Inspired by this, recent deep learning models…
Salient Object Detection in the Deep Learning Era: An In-Depth Survey
Wenguan Wang, Qiuxia Lai, Huazhu Fu +3
As an essential problem in computer vision, salient object detection (SOD) has attracted an increasing amount of research attention over the years. Recent advances in SOD are predo…