33 citations · 178 across the 28 of their papers we have counts for
29 papers
MatchXML: An Efficient Text-label Matching Framework for Extreme Multi-label Text Classification
Hui Ye, Rajshekhar Sunderraman, Shihao Ji
The eXtreme Multi-label text Classification(XMC) refers to training a classifier that assigns a text sample with relevant labels from an extremely large-scale label set (e.g., mill…
FLSL: Feature-level Self-supervised Learning
Qing Su, Anton Netchaev, Hai Li +1
Current self-supervised learning (SSL) methods (e.g., SimCLR, DINO, VICReg,MOCOv3) target primarily on representations at instance level and do not generalize well to dense predict…
M-EBM: Towards Understanding the Manifolds of Energy-Based Models
Xiulong Yang, Shihao Ji
Energy-based models (EBMs) exhibit a variety of desirable properties in predictive tasks, such as generality, simplicity and compositionality. However, training EBMs on high-dimens…
Accounting for Temporal Variability in Functional Magnetic Resonance Imaging Improves Prediction of Intelligence
Yang Li, Xin Ma, Raj Sunderraman +2
Neuroimaging-based prediction methods for intelligence and cognitive abilities have seen a rapid development in literature. Among different neuroimaging modalities, prediction base…
APSNet: Attention Based Point Cloud Sampling
Yang Ye, Xiulong Yang, Shihao Ji
Processing large point clouds is a challenging task. Therefore, the data is often downsampled to a smaller size such that it can be stored, transmitted and processed more efficient…
Towards Bridging the Performance Gaps of Joint Energy-based Models
Xiulong Yang, Qing Su, Shihao Ji
Can we train a hybrid discriminative-generative model within a single network? This question has recently been answered in the affirmative, introducing the field of Joint Energy-ba…
Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Model
Xiulong Yang, Sheng-Min Shih, Yinlin Fu +2
Diffusion Denoising Probability Models (DDPM) and Vision Transformer (ViT) have demonstrated significant progress in generative tasks and discriminative tasks, respectively, and th…
ChiTransformer:Towards Reliable Stereo from Cues
Qing Su, Shihao Ji
Current stereo matching techniques are challenged by restricted searching space, occluded regions and sheer size. While single image depth estimation is spared from these challenge…
Generative Dynamic Patch Attack
Xiang Li, Shihao Ji
Adversarial patch attack is a family of attack algorithms that perturb a part of image to fool a deep neural network model. Existing patch attacks mostly consider injecting adversa…
JEM++: Improved Techniques for Training JEM
Xiulong Yang, Shihao Ji
Joint Energy-based Model (JEM) is a recently proposed hybrid model that retains strong discriminative power of modern CNN classifiers, while generating samples rivaling the quality…
Improving Text-to-Image Synthesis Using Contrastive Learning
Hui Ye, Xiulong Yang, Martin Takac +2
The goal of text-to-image synthesis is to generate a visually realistic image that matches a given text description. In practice, the captions annotated by humans for the same imag…
Dep-: Improving -based Network Sparsification via Dependency Modeling
Yang Li, Shihao Ji
Training deep neural networks with an regularization is one of the prominent approaches for network pruning or sparsification. The method prunes the network during training b…
Reducing Risk and Uncertainty of Deep Neural Networks on Diagnosing COVID-19 Infection
Krishanu Sarker, Sharbani Pandit, Anupam Sarker +2
Effective and reliable screening of patients via Computer-Aided Diagnosis can play a crucial part in the battle against COVID-19. Most of the existing works focus on developing sop…
Generative Max-Mahalanobis Classifiers for Image Classification, Generation and More
Xiulong Yang, Hui Ye, Yang Ye +2
Joint Energy-based Model (JEM) of Grathwohl et al. shows that a standard softmax classifier can be reinterpreted as an energy-based model (EBM) for the joint distribution p(x,y); t…
A Unified Plug-and-Play Framework for Effective Data Denoising and Robust Abstention
Krishanu Sarker, Xiulong Yang, Yang Li +2
The success of Deep Neural Networks (DNNs) highly depends on data quality. Moreover, predictive uncertainty makes high performing DNNs risky for real-world deployment. In this pape…
Adversarial Privacy Preserving Graph Embedding against Inference Attack
Kaiyang Li, Guangchun Luo, Yang Ye +3
Recently, the surge in popularity of Internet of Things (IoT), mobile devices, social media, etc. has opened up a large source for graph data. Graph embedding has been proved extre…
Learning with Multiplicative Perturbations
Xiulong Yang, Shihao Ji
Adversarial Training (AT) and Virtual Adversarial Training (VAT) are the regularization techniques that train Deep Neural Networks (DNNs) with adversarial examples generated by add…
Sparse Graph Attention Networks
Yang Ye, Shihao Ji
Graph Neural Networks (GNNs) have proved to be an effective representation learning framework for graph-structured data, and have achieved state-of-the-art performance on many prac…
Toward Filament Segmentation Using Deep Neural Networks
Azim Ahmadzadeh, Sushant S. Mahajan, Dustin J. Kempton +2
We use a well-known deep neural network framework, called Mask R-CNN, for identification of solar filaments in full-disk H-alpha images from Big Bear Solar Observatory (BBSO). The…
Neural Image Compression and Explanation
Xiang Li, Shihao Ji
Explaining the prediction of deep neural networks (DNNs) and semantic image compression are two active research areas of deep learning with a numerous of applications in decision-c…
Neural Plasticity Networks
Yang Li, Shihao Ji
Neural plasticity is an important functionality of human brain, in which number of neurons and synapses can shrink or expand in response to stimuli throughout the span of life. We…
-ARM: Network Sparsification via Stochastic Binary Optimization
Yang Li, Shihao Ji
We consider network sparsification as an -norm regularized binary optimization problem, where each unit of a neural network (e.g., weight, neuron, or channel, etc.) is attache…
Towards Robust Human Activity Recognition from RGB Video Stream with Limited Labeled Data
Krishanu Sarker, Mohamed Masoud, Saeid Belkasim +1
Human activity recognition based on video streams has received numerous attentions in recent years. Due to lack of depth information, RGB video based activity recognition performs…
Defense-VAE: A Fast and Accurate Defense against Adversarial Attacks
Xiang Li, Shihao Ji
Deep neural networks (DNNs) have been enormously successful across a variety of prediction tasks. However, recent research shows that DNNs are particularly vulnerable to adversaria…