112 citations · 783 across the 45 of their papers we have counts for
12 papers · 1 filter
Teach-DETR: Better Training DETR with Teachers
Linjiang Huang, Kaixin Lu, Guanglu Song +4
In this paper, we present a novel training scheme, namely Teach-DETR, to learn better DETR-based detectors from versatile teacher detectors. We show that the predicted boxes from t…
DETRs with Collaborative Hybrid Assignments Training
Zhuofan Zong, Guanglu Song, Yu Liu
In this paper, we provide the observation that too few queries assigned as positive samples in DETR with one-to-one set matching leads to sparse supervision on the encoder's output…
Large-batch Optimization for Dense Visual Predictions
Zeyue Xue, Jianming Liang, Guanglu Song +4
Training a large-scale deep neural network in a large-scale dataset is challenging and time-consuming. The recent breakthrough of large-batch optimization is a promising way to tac…
Towards Robust Face Recognition with Comprehensive Search
Manyuan Zhang, Guanglu Song, Yu Liu +1
Data cleaning, architecture, and loss function design are important factors contributing to high-performance face recognition. Previously, the research community tries to improve t…
Unifying Visual Perception by Dispersible Points Learning
Jianming Liang, Guanglu Song, Biao Leng +1
We present a conceptually simple, flexible, and universal visual perception head for variant visual tasks, e.g., classification, object detection, instance segmentation and pose es…
Rethinking Robust Representation Learning Under Fine-grained Noisy Faces
Bingqi Ma, Guanglu Song, Boxiao Liu +1
Learning robust feature representation from large-scale noisy faces stands out as one of the key challenges in high-performance face recognition. Recent attempts have been made to…
TokenMix: Rethinking Image Mixing for Data Augmentation in Vision Transformers
Jihao Liu, Boxiao Liu, Hang Zhou +2
CutMix is a popular augmentation technique commonly used for training modern convolutional and transformer vision networks. It was originally designed to encourage Convolution Neur…
UniNet: Unified Architecture Search with Convolution, Transformer, and MLP
Jihao Liu, Xin Huang, Guanglu Song +2
Recently, transformer and multi-layer perceptron (MLP) architectures have achieved impressive results on various vision tasks. However, how to effectively combine those operators t…
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers
Jihao Liu, Xin Huang, Jinliang Zheng +2
In this paper, we propose Mixed and Masked AutoEncoder (MixMAE), a simple but efficient pretraining method that is applicable to various hierarchical Vision Transformers. Existing…
Meta Knowledge Distillation
Jihao Liu, Boxiao Liu, Hongsheng Li +1
Recent studies pointed out that knowledge distillation (KD) suffers from two degradation problems, the teacher-student gap and the incompatibility with strong data augmentations, m…
UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning
Kunchang Li, Yali Wang, Peng Gao +4
It is a challenging task to learn rich and multi-scale spatiotemporal semantics from high-dimensional videos, due to large local redundancy and complex global dependency between vi…
UniFormer: Unifying Convolution and Self-attention for Visual Recognition
Kunchang Li, Yali Wang, Junhao Zhang +5
It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolutio…