activity
20182024
most citedOne Million Scenes for Autonomous Driving: ONCE Dataset

133 citations · 304 across the 26 of their papers we have counts for

collaborators
Showing 2021 · cs.CVShow all

7 papers · 2 filters

cs.CV2021★ 133 cited

One Million Scenes for Autonomous Driving: ONCE Dataset

Jiageng Mao, Minzhe Niu, Chenhan Jiang +10

Current perception models in autonomous driving have become notorious for greatly relying on a mass of annotated data to cover unseen cases and address the long-tail problem. On th…

cs.CV2021★ 3 cited

Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation

Lewei Yao, Renjie Pi, Hang Xu +3

We propose Joint-DetNAS, a unified NAS framework for object detection, which integrates 3 key components: Neural Architecture Search, pruning, and Knowledge Distillation. Instead o…

cs.CV2021★ 4 cited

TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search

Yawen Duan, Xin Chen, Hang Xu +4

Recent breakthroughs of Neural Architecture Search (NAS) extend the field's research scope towards a broader range of vision tasks and more diversified search spaces. While existin…

cs.CV2021

Deeply Unsupervised Patch Re-Identification for Pre-training Object Detectors

Jian Ding, Enze Xie, Hang Xu +4

Unsupervised pre-training aims at learning transferable features that are beneficial for downstream tasks. However, most state-of-the-art unsupervised methods concentrate on learni…

cs.CV2021★ 25 cited

Segmenting Transparent Object in the Wild with Transformer

Enze Xie, Wenjia Wang, Wenhai Wang +4

This work presents a new fine-grained transparent object segmentation dataset, termed Trans10K-v2, extending Trans10K-v1, the first large-scale transparent object segmentation data…

cs.CV2021★ 16 cited

Loss Function Discovery for Object Detection via Convergence-Simulation Driven Search

Peidong Liu, Gengwei Zhang, Bochao Wang +4

Designing proper loss functions for vision tasks has been a long-standing research direction to advance the capability of existing models. For object detection, the well-establishe…