72 citations · 201 across the 12 of their papers we have counts for
12 papers
How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers?
Gregory Holste, Ziyu Jiang, Ajay Jaiswal +12
Pruning has emerged as a powerful technique for compressing deep neural networks, reducing memory usage and inference time without significantly affecting overall performance. Howe…
Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling
Haotao Wang, Ziyu Jiang, Yuning You +5
Graph neural networks (GNNs) have found extensive applications in learning from graph data. However, real-world graphs often possess diverse structures and comprise nodes and edges…
Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations
Ziyu Jiang, Yinpeng Chen, Mengchen Liu +5
Recently, both Contrastive Learning (CL) and Mask Image Modeling (MIM) demonstrate that self-supervision is powerful to learn good representations. However, naively combining them…
Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK
Hongru Yang, Ziyu Jiang, Ruizhe Zhang +2
We study training one-hidden-layer ReLU networks in the neural tangent kernel (NTK) regime, where the networks' biases are initialized to some constant rather than zero. We prove t…
MViT: Mixture-of-Experts Vision Transformer for Efficient Multi-task Learning with Model-Accelerator Co-design
Hanxue Liang, Zhiwen Fan, Rishov Sarkar +6
Multi-task learning (MTL) encapsulates multiple learned tasks in a single model and often lets those tasks learn better jointly. However, when deploying MTL onto those real-world s…
Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study
Gregory Holste, Song Wang, Ziyu Jiang +5
Imaging exams, such as chest radiography, will yield a small set of common findings and a much larger set of uncommon findings. While a trained radiologist can learn the visual pre…
Improving Contrastive Learning on Imbalanced Seed Data via Open-World Sampling
Ziyu Jiang, Tianlong Chen, Ting Chen +1
Contrastive learning approaches have achieved great success in learning visual representations with few labels of the target classes. That implies a tantalizing possibility of scal…
Self-Damaging Contrastive Learning
Ziyu Jiang, Tianlong Chen, Bobak Mortazavi +1
The recent breakthrough achieved by contrastive learning accelerates the pace for deploying unsupervised training on real-world data applications. However, unlabeled data in realit…
Robust Pre-Training by Adversarial Contrastive Learning
Ziyu Jiang, Tianlong Chen, Ting Chen +1
Recent work has shown that, when integrated with adversarial training, self-supervised pre-training can lead to state-of-the-art robustness In this work, we improve robustness-awar…
E2-Train: Training State-of-the-art CNNs with Over 80% Energy Savings
Yue Wang, Ziyu Jiang, Xiaohan Chen +4
Convolutional neural networks (CNNs) have been increasingly deployed to edge devices. Hence, many efforts have been made towards efficient CNN inference in resource-constrained pla…
ArcticNet: A Deep Learning Solution to Classify Arctic Wetlands
Ziyu Jiang, Kate Von Ness, Julie Loisel +1
Arctic environments are rapidly changing under the warming climate. Of particular interest are wetlands, a type of ecosystem that constitutes the most effective terrestrial long-te…
Collaborative Global-Local Networks for Memory-Efficient Segmentation of Ultra-High Resolution Images
Wuyang Chen, Ziyu Jiang, Zhangyang Wang +2
Segmentation of ultra-high resolution images is increasingly demanded, yet poses significant challenges for algorithm efficiency, in particular considering the (GPU) memory limits.…