11 citations · 43 across the 12 of their papers we have counts for
14 papers
FlexUMM: Flexible Representation Learning for Unified Multimodal Models
Yinyi Luo, Haoyue Bai, Yi Ge +3
Unified multimodal models (UMMs) can integrate understanding and generation within a single backbone. However, it is commonly known that these two capabilities can cause conflictin…
The Physics Is the Network: Fast, Training-Free Neural Emulation
Luka Todorovic, Kaushal Gianchandani, Sai Ravela
Neural emulation need not require learning a substitute for known physics. We investigate PolyNets that couple a continuous-time neural representation of polynomial dynamics with a…
Towards Robust Out-of-Distribution Generalization: Data Augmentation and Neural Architecture Search Approaches
Haoyue Bai
Deep learning has been demonstrated with tremendous success in recent years. Despite so, its performance in practice often degenerates drastically when encountering out-of-distribu…
Improving Out-of-Distribution Robustness of Classifiers via Generative Interpolation
Haoyue Bai, Ceyuan Yang, Yinghao Xu +2
Deep neural networks achieve superior performance for learning from independent and identically distributed (i.i.d.) data. However, their performance deteriorates significantly whe…
Feed Two Birds with One Scone: Exploiting Wild Data for Both Out-of-Distribution Generalization and Detection
Haoyue Bai, Gregory Canal, Xuefeng Du +3
Modern machine learning models deployed in the wild can encounter both covariate and semantic shifts, giving rise to the problems of out-of-distribution (OOD) generalization and OO…
Voxel Transformer for 3D Object Detection
Jiageng Mao, Yujing Xue, Minzhe Niu +5
We present Voxel Transformer (VoTr), a novel and effective voxel-based Transformer backbone for 3D object detection from point clouds. Conventional 3D convolutional backbones in vo…
Pyramid R-CNN: Towards Better Performance and Adaptability for 3D Object Detection
Jiageng Mao, Minzhe Niu, Haoyue Bai +3
We present a flexible and high-performance framework, named Pyramid R-CNN, for two-stage 3D object detection from point clouds. Current approaches generally rely on the points or v…
NAS-OoD: Neural Architecture Search for Out-of-Distribution Generalization
Haoyue Bai, Fengwei Zhou, Lanqing Hong +3
Recent advances on Out-of-Distribution (OoD) generalization reveal the robustness of deep learning models against distribution shifts. However, existing works focus on OoD algorith…
OoD-Bench: Quantifying and Understanding Two Dimensions of Out-of-Distribution Generalization
Nanyang Ye, Kaican Li, Haoyue Bai +5
Deep learning has achieved tremendous success with independent and identically distributed (i.i.d.) data. However, the performance of neural networks often degenerates drastically…
Crowd Counting by Self-supervised Transfer Colorization Learning and Global Prior Classification
Haoyue Bai, Song Wen, S. -H. Gary Chan
Labeled crowd scene images are expensive and scarce. To significantly reduce the requirement of the labeled images, we propose ColorCount, a novel CNN-based approach by combining s…
Motion-guided Non-local Spatial-Temporal Network for Video Crowd Counting
Haoyue Bai, S. -H. Gary Chan
We study video crowd counting, which is to estimate the number of objects (people in this paper) in all the frames of a video sequence. Previous work on crowd counting is mostly on…
DecAug: Out-of-Distribution Generalization via Decomposed Feature Representation and Semantic Augmentation
Haoyue Bai, Rui Sun, Lanqing Hong +5
While deep learning demonstrates its strong ability to handle independent and identically distributed (IID) data, it often suffers from out-of-distribution (OoD) generalization, wh…
A Survey on Deep Learning-based Single Image Crowd Counting: Network Design, Loss Function and Supervisory Signal
Haoyue Bai, Jiageng Mao, S. -H. Gary Chan
Single image crowd counting is a challenging computer vision problem with wide applications in public safety, city planning, traffic management, etc. With the recent development of…
Crowd Counting on Images with Scale Variation and Isolated Clusters
Haoyue Bai, Song Wen, S. -H. Gary Chan
Crowd counting is to estimate the number of objects (e.g., people or vehicles) in an image of unconstrained congested scenes. Designing a general crowd counting algorithm applicabl…