activity
20162023
most citedSqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud

57 citations · 257 across the 18 of their papers we have counts for

collaborators
Showing 2021Show all

5 papers · 1 filter

cs.LG20212 cited

Differentiable NAS Framework and Application to Ads CTR Prediction

Ravi Krishna, Aravind Kalaiah, Bichen Wu +4

Neural architecture search (NAS) methods aim to automatically find the optimal deep neural network (DNN) architecture as measured by a given objective function, typically some comb…

cs.CV20211 cited

Data-Efficient Language-Supervised Zero-Shot Learning with Self-Distillation

Ruizhe Cheng, Bichen Wu, Peizhao Zhang +2

Traditional computer vision models are trained to predict a fixed set of predefined categories. Recently, natural language has been shown to be a broader and richer source of super…

cs.RO20212 cited

You Only Group Once: Efficient Point-Cloud Processing with Token Representation and Relation Inference Module

Chenfeng Xu, Bohan Zhai, Bichen Wu +5

3D point-cloud-based perception is a challenging but crucial computer vision task. A point-cloud consists of a sparse, unstructured, and unordered set of points. To understand a po…

cs.LG20212 cited

Improving Context-Based Meta-Reinforcement Learning with Self-Supervised Trajectory Contrastive Learning

Bernie Wang, Simon Xu, Kurt Keutzer +2

Meta-reinforcement learning typically requires orders of magnitude more samples than single task reinforcement learning methods. This is because meta-training needs to deal with mo…

cs.CV202128 cited

Unbiased Teacher for Semi-Supervised Object Detection

Yen-Cheng Liu, Chih-Yao Ma, Zijian He +6

Semi-supervised learning, i.e., training networks with both labeled and unlabeled data, has made significant progress recently. However, existing works have primarily focused on im…