206 citations · 486 across the 43 of their papers we have counts for
11 papers · 1 filter
FILIP: Fine-grained Interactive Language-Image Pre-Training
Lewei Yao, Runhui Huang, Lu Hou +7
Unsupervised large-scale vision-language pre-training has shown promising advances on various downstream tasks. Existing methods often model the cross-modal interaction either via…
SOFT: Softmax-free Transformer with Linear Complexity
Jiachen Lu, Jinghan Yao, Junge Zhang +6
Vision transformers (ViTs) have pushed the state-of-the-art for various visual recognition tasks by patch-wise image tokenization followed by self-attention. However, the employmen…
EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation
Chenhe Dong, Guangrun Wang, Hang Xu +3
Pre-trained language models have shown remarkable results on various NLP tasks. Nevertheless, due to their bulky size and slow inference speed, it is hard to deploy them on edge de…
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…
Adversarial Robustness for Unsupervised Domain Adaptation
Muhammad Awais, Fengwei Zhou, Hang Xu +4
Extensive Unsupervised Domain Adaptation (UDA) studies have shown great success in practice by learning transferable representations across a labeled source domain and an unlabeled…
MultiSiam: Self-supervised Multi-instance Siamese Representation Learning for Autonomous Driving
Kai Chen, Lanqing Hong, Hang Xu +2
Autonomous driving has attracted much attention over the years but turns out to be harder than expected, probably due to the difficulty of labeled data collection for model trainin…
Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-modal Pretraining
Xunlin Zhan, Yangxin Wu, Xiao Dong +5
Nowadays, customer's demands for E-commerce are more diversified, which introduces more complications to the product retrieval industry. Previous methods are either subject to sing…
NASOA: Towards Faster Task-oriented Online Fine-tuning with a Zoo of Models
Hang Xu, Ning Kang, Gengwei Zhang +3
Fine-tuning from pre-trained ImageNet models has been a simple, effective, and popular approach for various computer vision tasks. The common practice of fine-tuning is to adopt a…
G-DetKD: Towards General Distillation Framework for Object Detectors via Contrastive and Semantic-guided Feature Imitation
Lewei Yao, Renjie Pi, Hang Xu +3
In this paper, we investigate the knowledge distillation (KD) strategy for object detection and propose an effective framework applicable to both homogeneous and heterogeneous stud…
SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving
Jianhua Han, Xiwen Liang, Hang Xu +8
Aiming at facilitating a real-world, ever-evolving and scalable autonomous driving system, we present a large-scale dataset for standardizing the evaluation of different self-super…