112 citations · 783 across the 45 of their papers we have counts for
45 papers
Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising
Fu-Yun Wang, Wenshuo Chen, Guanglu Song +3
Leveraging large-scale image-text datasets and advancements in diffusion models, text-driven generative models have made remarkable strides in the field of image generation and edi…
RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths
Zeyue Xue, Guanglu Song, Qiushan Guo +4
Text-to-image generation has recently witnessed remarkable achievements. We introduce a text-conditional image diffusion model, termed RAPHAEL, to generate highly artistic images,…
Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction
Zhuofan Zong, Dongzhi Jiang, Guanglu Song +4
In this paper, we propose a new paradigm, named Historical Object Prediction (HoP) for multi-view 3D detection to leverage temporal information more effectively. The HoP approach i…
GeoMIM: Towards Better 3D Knowledge Transfer via Masked Image Modeling for Multi-view 3D Understanding
Jihao Liu, Tai Wang, Boxiao Liu +3
Multi-view camera-based 3D detection is a challenging problem in computer vision. Recent works leverage a pretrained LiDAR detection model to transfer knowledge to a camera-based s…
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…
Self-slimmed Vision Transformer
Zhuofan Zong, Kunchang Li, Guanglu Song +4
Vision transformers (ViTs) have become the popular structures and outperformed convolutional neural networks (CNNs) on various vision tasks. However, such powerful transformers bri…
INTERN: A New Learning Paradigm Towards General Vision
Jing Shao, Siyu Chen, Yangguang Li +24
Enormous waves of technological innovations over the past several years, marked by the advances in AI technologies, are profoundly reshaping the industry and the society. However,…
UniNet: Unified Architecture Search with Convolution, Transformer, and MLP
Jihao Liu, Hongsheng Li, Guanglu Song +2
Recently, transformer and multi-layer perceptron (MLP) architectures have achieved impressive results on various vision tasks. A few works investigated manually combining those ope…
FNAS: Uncertainty-Aware Fast Neural Architecture Search
Jihao Liu, Ming Zhang, Yangting Sun +4
Reinforcement learning (RL)-based neural architecture search (NAS) generally guarantees better convergence yet suffers from the requirement of huge computational resources compared…
Discriminability Distillation in Group Representation Learning
Manyuan Zhang, Guanglu Song, Hang Zhou +1
Learning group representation is a commonly concerned issue in tasks where the basic unit is a group, set, or sequence. Previously, the research community tries to tackle it by agg…
Complementary Boundary Generator with Scale-Invariant Relation Modeling for Temporal Action Localization: Submission to ActivityNet Challenge 2020
Haisheng Su, Jinyuan Feng, Hao Shao +6
This technical report presents an overview of our solution used in the submission to ActivityNet Challenge 2020 Task 1 (\textbf{temporal action localization/detection}). Temporal a…
1st place solution for AVA-Kinetics Crossover in AcitivityNet Challenge 2020
Siyu Chen, Junting Pan, Guanglu Song +6
This technical report introduces our winning solution to the spatio-temporal action localization track, AVA-Kinetics Crossover, in ActivityNet Challenge 2020. Our entry is mainly b…
Rotate-and-Render: Unsupervised Photorealistic Face Rotation from Single-View Images
Hang Zhou, Jihao Liu, Ziwei Liu +2
Though face rotation has achieved rapid progress in recent years, the lack of high-quality paired training data remains a great hurdle for existing methods. The current generative…