5k citations · 8.4k across the 35 of their papers we have counts for
37 papers
WOMD-LiDAR: Raw Sensor Dataset Benchmark for Motion Forecasting
Kan Chen, Runzhou Ge, Hang Qiu +12
Widely adopted motion forecasting datasets substitute the observed sensory inputs with higher-level abstractions such as 3D boxes and polylines. These sparse shapes are inferred th…
LidarAugment: Searching for Scalable 3D LiDAR Data Augmentations
Zhaoqi Leng, Guowang Li, Chenxi Liu +5
Data augmentations are important in training high-performance 3D object detectors for point clouds. Despite recent efforts on designing new data augmentations, perhaps surprisingly…
PseudoAugment: Learning to Use Unlabeled Data for Data Augmentation in Point Clouds
Zhaoqi Leng, Shuyang Cheng, Benjamin Caine +5
Data augmentation is an important technique to improve data efficiency and save labeling cost for 3D detection in point clouds. Yet, existing augmentation policies have so far been…
SWFormer: Sparse Window Transformer for 3D Object Detection in Point Clouds
Pei Sun, Mingxing Tan, Weiyue Wang +4
3D object detection in point clouds is a core component for modern robotics and autonomous driving systems. A key challenge in 3D object detection comes from the inherent sparse na…
LidarNAS: Unifying and Searching Neural Architectures for 3D Point Clouds
Chenxi Liu, Zhaoqi Leng, Pei Sun +5
Developing neural models that accurately understand objects in 3D point clouds is essential for the success of robotics and autonomous driving. However, arguably due to the higher-…
Regularized Contrastive Learning of Semantic Search
Mingxi Tan, Alexis Rolland, Andong Tian
Semantic search is an important task which objective is to find the relevant index from a database for query. It requires a retrieval model that can properly learn the semantics of…
PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functions
Zhaoqi Leng, Mingxing Tan, Chenxi Liu +4
Cross-entropy loss and focal loss are the most common choices when training deep neural networks for classification problems. Generally speaking, however, a good loss function can…
DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection
Yingwei Li, Adams Wei Yu, Tianjian Meng +10
Lidars and cameras are critical sensors that provide complementary information for 3D detection in autonomous driving. While prevalent multi-modal methods simply decorate raw lidar…
Occupancy Flow Fields for Motion Forecasting in Autonomous Driving
Reza Mahjourian, Jinkyu Kim, Yuning Chai +3
We propose Occupancy Flow Fields, a new representation for motion forecasting of multiple agents, an important task in autonomous driving. Our representation is a spatio-temporal g…
Revisiting Multi-Scale Feature Fusion for Semantic Segmentation
Tianjian Meng, Golnaz Ghiasi, Reza Mahjourian +2
It is commonly believed that high internal resolution combined with expensive operations (e.g. atrous convolutions) are necessary for accurate semantic segmentation, resulting in s…
Combined Scaling for Zero-shot Transfer Learning
Hieu Pham, Zihang Dai, Golnaz Ghiasi +9
We present a combined scaling method - named BASIC - that achieves 85.7% top-1 accuracy on the ImageNet ILSVRC-2012 validation set without learning from any labeled ImageNet exampl…
CoAtNet: Marrying Convolution and Attention for All Data Sizes
Zihang Dai, Hanxiao Liu, Quoc V. Le +1
Transformers have attracted increasing interests in computer vision, but they still fall behind state-of-the-art convolutional networks. In this work, we show that while Transforme…
MoViNets: Mobile Video Networks for Efficient Video Recognition
Dan Kondratyuk, Liangzhe Yuan, Yandong Li +4
We present Mobile Video Networks (MoViNets), a family of computation and memory efficient video networks that can operate on streaming video for online inference. 3D convolutional…
EfficientNetV2: Smaller Models and Faster Training
Mingxing Tan, Quoc V. Le
This paper introduces EfficientNetV2, a new family of convolutional networks that have faster training speed and better parameter efficiency than previous models. To develop this f…
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…
Robust and Accurate Object Detection via Adversarial Learning
Xiangning Chen, Cihang Xie, Mingxing Tan +3
Data augmentation has become a de facto component for training high-performance deep image classifiers, but its potential is under-explored for object detection. Noting that most s…
Rethinking Co-design of Neural Architectures and Hardware Accelerators
Yanqi Zhou, Xuanyi Dong, Berkin Akin +7
Neural architectures and hardware accelerators have been two driving forces for the progress in deep learning. Previous works typically attempt to optimize hardware given a fixed m…
Searching for Fast Model Families on Datacenter Accelerators
Sheng Li, Mingxing Tan, Ruoming Pang +4
Neural Architecture Search (NAS), together with model scaling, has shown remarkable progress in designing high accuracy and fast convolutional architecture families. However, as ne…
PyGlove: Symbolic Programming for Automated Machine Learning
Daiyi Peng, Xuanyi Dong, Esteban Real +7
Neural networks are sensitive to hyper-parameter and architecture choices. Automated Machine Learning (AutoML) is a promising paradigm for automating these choices. Current ML soft…
Training EfficientNets at Supercomputer Scale: 83% ImageNet Top-1 Accuracy in One Hour
Arissa Wongpanich, Hieu Pham, James Demmel +4
EfficientNets are a family of state-of-the-art image classification models based on efficiently scaled convolutional neural networks. Currently, EfficientNets can take on the order…
Efficient Scale-Permuted Backbone with Learned Resource Distribution
Xianzhi Du, Tsung-Yi Lin, Pengchong Jin +4
Recently, SpineNet has demonstrated promising results on object detection and image classification over ResNet model. However, it is unclear if the improvement adds up when combini…
Shape-Texture Debiased Neural Network Training
Yingwei Li, Qihang Yu, Mingxing Tan +5
Shape and texture are two prominent and complementary cues for recognizing objects. Nonetheless, Convolutional Neural Networks are often biased towards either texture or shape, dep…
Go Wide, Then Narrow: Efficient Training of Deep Thin Networks
Denny Zhou, Mao Ye, Chen Chen +6
For deploying a deep learning model into production, it needs to be both accurate and compact to meet the latency and memory constraints. This usually results in a network that is…
Smooth Adversarial Training
Cihang Xie, Mingxing Tan, Boqing Gong +2
It is commonly believed that networks cannot be both accurate and robust, that gaining robustness means losing accuracy. It is also generally believed that, unless making networks…