41 citations · 120 across the 12 of their papers we have counts for
12 papers
Mixture-of-Supernets: Improving Weight-Sharing Supernet Training with Architecture-Routed Mixture-of-Experts
Ganesh Jawahar, Haichuan Yang, Yunyang Xiong +10
Weight-sharing supernets are crucial for performance estimation in cutting-edge neural architecture search (NAS) frameworks. Despite their ability to generate diverse subnetworks w…
Self-positioning Point-based Transformer for Point Cloud Understanding
Jinyoung Park, Sanghyeok Lee, Sihyeon Kim +2
Transformers have shown superior performance on various computer vision tasks with their capabilities to capture long-range dependencies. Despite the success, it is challenging to…
Fast Point Cloud Generation with Straight Flows
Lemeng Wu, Dilin Wang, Chengyue Gong +6
Diffusion models have emerged as a powerful tool for point cloud generation. A key component that drives the impressive performance for generating high-quality samples from noise i…
PathFusion: Path-consistent Lidar-Camera Deep Feature Fusion
Lemeng Wu, Dilin Wang, Meng Li +4
Fusing 3D LiDAR features with 2D camera features is a promising technique for enhancing the accuracy of 3D detection, thanks to their complementary physical properties. While most…
Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference
Haoran You, Yunyang Xiong, Xiaoliang Dai +5
Vision Transformers (ViTs) have shown impressive performance but still require a high computation cost as compared to convolutional neural networks (CNNs), one reason is that ViTs'…
SageMix: Saliency-Guided Mixup for Point Clouds
Sanghyeok Lee, Minkyu Jeon, Injae Kim +2
Data augmentation is key to improving the generalization ability of deep learning models. Mixup is a simple and widely-used data augmentation technique that has proven effective in…
You Only Sample (Almost) Once: Linear Cost Self-Attention Via Bernoulli Sampling
Zhanpeng Zeng, Yunyang Xiong, Sathya N. Ravi +3
Transformer-based models are widely used in natural language processing (NLP). Central to the transformer model is the self-attention mechanism, which captures the interactions of…
Nyströmformer: A Nyström-Based Algorithm for Approximating Self-Attention
Yunyang Xiong, Zhanpeng Zeng, Rudrasis Chakraborty +4
Transformers have emerged as a powerful tool for a broad range of natural language processing tasks. A key component that drives the impressive performance of Transformers is the s…
MobileDets: Searching for Object Detection Architectures for Mobile Accelerators
Yunyang Xiong, Hanxiao Liu, Suyog Gupta +7
Inverted bottleneck layers, which are built upon depthwise convolutions, have been the predominant building blocks in state-of-the-art object detection models on mobile devices. In…
Resource Constrained Neural Network Architecture Search: Will a Submodularity Assumption Help?
Yunyang Xiong, Ronak Mehta, Vikas Singh
The design of neural network architectures is frequently either based on human expertise using trial/error and empirical feedback or tackled via large scale reinforcement learning…
ANTNets: Mobile Convolutional Neural Networks for Resource Efficient Image Classification
Yunyang Xiong, Hyunwoo J. Kim, Varsha Hedau
Deep convolutional neural networks have achieved remarkable success in computer vision. However, deep neural networks require large computing resources to achieve high performance.…
Building Bayesian Neural Networks with Blocks: On Structure, Interpretability and Uncertainty
Hao Henry Zhou, Yunyang Xiong, Vikas Singh
We provide simple schemes to build Bayesian Neural Networks (BNNs), block by block, inspired by a recent idea of computation skeletons. We show how by adjusting the types of blocks…