1.3k citations · 2.4k across the 21 of their papers we have counts for
10 papers · 1 filter
MapPrior: Bird's-Eye View Map Layout Estimation with Generative Models
Xiyue Zhu, Vlas Zyrianov, Zhijian Liu +1
Despite tremendous advancements in bird's-eye view (BEV) perception, existing models fall short in generating realistic and coherent semantic map layouts, and they fail to account…
SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer
Xuanyao Chen, Zhijian Liu, Haotian Tang +3
High-resolution images enable neural networks to learn richer visual representations. However, this improved performance comes at the cost of growing computational complexity, hind…
FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer
Zhijian Liu, Xinyu Yang, Haotian Tang +2
Transformer, as an alternative to CNN, has been proven effective in many modalities (e.g., texts and images). For 3D point cloud transformers, existing efforts focus primarily on p…
PVNAS: 3D Neural Architecture Search with Point-Voxel Convolution
Zhijian Liu, Haotian Tang, Shengyu Zhao +2
3D neural networks are widely used in real-world applications (e.g., AR/VR headsets, self-driving cars). They are required to be fast and accurate; however, limited hardware resour…
LocTex: Learning Data-Efficient Visual Representations from Localized Textual Supervision
Zhijian Liu, Simon Stent, Jie Li +2
Computer vision tasks such as object detection and semantic/instance segmentation rely on the painstaking annotation of large training datasets. In this paper, we propose LocTex th…
Point-Voxel CNN for Efficient 3D Deep Learning
Zhijian Liu, Haotian Tang, Yujun Lin +1
We present Point-Voxel CNN (PVCNN) for efficient, fast 3D deep learning. Previous work processes 3D data using either voxel-based or point-based NN models. However, both approaches…
Unsupervised Discovery of Parts, Structure, and Dynamics
Zhenjia Xu, Zhijian Liu, Chen Sun +4
Humans easily recognize object parts and their hierarchical structure by watching how they move; they can then predict how each part moves in the future. In this paper, we propose…
HAQ: Hardware-Aware Automated Quantization with Mixed Precision
Kuan Wang, Zhijian Liu, Yujun Lin +2
Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1…
Physical Primitive Decomposition
Zhijian Liu, William T. Freeman, Joshua B. Tenenbaum +1
Objects are made of parts, each with distinct geometry, physics, functionality, and affordances. Developing such a distributed, physical, interpretable representation of objects wi…
AMC: AutoML for Model Compression and Acceleration on Mobile Devices
Yihui He, Ji Lin, Zhijian Liu +3
Model compression is a critical technique to efficiently deploy neural network models on mobile devices which have limited computation resources and tight power budgets. Convention…