577 citations · 2.7k across the 94 of their papers we have counts for
95 papers
Cross Modal Transformer: Towards Fast and Robust 3D Object Detection
Junjie Yan, Yingfei Liu, Jianjian Sun +4
In this paper, we propose a robust 3D detector, named Cross Modal Transformer (CMT), for end-to-end 3D multi-modal detection. Without explicit view transformation, CMT takes the im…
PETRv2: A Unified Framework for 3D Perception from Multi-Camera Images
Yingfei Liu, Junjie Yan, Fan Jia +5
In this paper, we propose PETRv2, a unified framework for 3D perception from multi-view images. Based on PETR, PETRv2 explores the effectiveness of temporal modeling, which utilize…
cosFormer: Rethinking Softmax in Attention
Zhen Qin, Weixuan Sun, Hui Deng +6
Transformer has shown great successes in natural language processing, computer vision, and audio processing. As one of its core components, the softmax attention helps to capture l…
One to Transfer All: A Universal Transfer Framework for Vision Foundation Model with Few Data
Yujie Wang, Junqin Huang, Mengya Gao +4
The foundation model is not the last chapter of the model production pipeline. Transferring with few data in a general way to thousands of downstream tasks is becoming a trend of t…
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,…
MQBench: Towards Reproducible and Deployable Model Quantization Benchmark
Yuhang Li, Mingzhu Shen, Jian Ma +6
Model quantization has emerged as an indispensable technique to accelerate deep learning inference. While researchers continue to push the frontier of quantization algorithms, exis…
Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
Yangguang Li, Feng Liang, Lichen Zhao +5
Recently, large-scale Contrastive Language-Image Pre-training (CLIP) has attracted unprecedented attention for its impressive zero-shot recognition ability and excellent transferab…
GLiT: Neural Architecture Search for Global and Local Image Transformer
Boyu Chen, Peixia Li, Chuming Li +6
We introduce the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition. Recently, transformers without CNN-based backbones a…
BN-NAS: Neural Architecture Search with Batch Normalization
Boyu Chen, Peixia Li, Baopu Li +5
We present BN-NAS, neural architecture search with Batch Normalization (BN-NAS), to accelerate neural architecture search (NAS). BN-NAS can significantly reduce the time required b…
Geometry Uncertainty Projection Network for Monocular 3D Object Detection
Yan Lu, Xinzhu Ma, Lei Yang +5
Geometry Projection is a powerful depth estimation method in monocular 3D object detection. It estimates depth dependent on heights, which introduces mathematical priors into the d…
PSViT: Better Vision Transformer via Token Pooling and Attention Sharing
Boyu Chen, Peixia Li, Baopu Li +6
In this paper, we observe two levels of redundancies when applying vision transformers (ViT) for image recognition. First, fixing the number of tokens through the whole network pro…
GAIA: A Transfer Learning System of Object Detection that Fits Your Needs
Xingyuan Bu, Junran Peng, Junjie Yan +2
Transfer learning with pre-training on large-scale datasets has played an increasingly significant role in computer vision and natural language processing recently. However, as the…
AutoSampling: Search for Effective Data Sampling Schedules
Ming Sun, Haoxuan Dou, Baopu Li +3
Data sampling acts as a pivotal role in training deep learning models. However, an effective sampling schedule is difficult to learn due to the inherently high dimension of paramet…
Efficient Transfer Learning via Joint Adaptation of Network Architecture and Weight
Ming Sun, Haoxuan Dou, Junjie Yan
Transfer learning can boost the performance on the targettask by leveraging the knowledge of the source domain. Recent worksin neural architecture search (NAS), especially one-shot…
Temporal Context Aggregation Network for Temporal Action Proposal Refinement
Zhiwu Qing, Haisheng Su, Weihao Gan +7
Temporal action proposal generation aims to estimate temporal intervals of actions in untrimmed videos, which is a challenging yet important task in the video understanding field.…
Real-Time Visual Object Tracking via Few-Shot Learning
Jinghao Zhou, Bo Li, Peng Wang +5
Visual Object Tracking (VOT) can be seen as an extended task of Few-Shot Learning (FSL). While the concept of FSL is not new in tracking and has been previously applied by prior wo…
Higher Performance Visual Tracking with Dual-Modal Localization
Jinghao Zhou, Bo Li, Lei Qiao +5
Visual Object Tracking (VOT) has synchronous needs for both robustness and accuracy. While most existing works fail to operate simultaneously on both, we investigate in this work t…
Learning Statistical Texture for Semantic Segmentation
Lanyun Zhu, Deyi Ji, Shiping Zhu +3
Existing semantic segmentation works mainly focus on learning the contextual information in high-level semantic features with CNNs. In order to maintain a precise boundary, low-lev…
Inter-class Discrepancy Alignment for Face Recognition
Jiaheng Liu, Yudong Wu, Yichao Wu +4
The field of face recognition (FR) has witnessed great progress with the surge of deep learning. Existing methods mainly focus on extracting discriminative features, and directly c…
Inception Convolution with Efficient Dilation Search
Jie Liu, Chuming Li, Feng Liang +5
As a variant of standard convolution, a dilated convolution can control effective receptive fields and handle large scale variance of objects without introducing additional computa…
DETR for Crowd Pedestrian Detection
Matthieu Lin, Chuming Li, Xingyuan Bu +5
Pedestrian detection in crowd scenes poses a challenging problem due to the heuristic defined mapping from anchors to pedestrians and the conflict between NMS and highly overlapped…
Context-Aware Graph Convolution Network for Target Re-identification
Deyi Ji, Haoran Wang, Hanzhe Hu +3
Most existing re-identification methods focus on learning robust and discriminative features with deep convolution networks. However, many of them consider content similarity separ…
PV-NAS: Practical Neural Architecture Search for Video Recognition
Zihao Wang, Chen Lin, Lu Sheng +2
Recently, deep learning has been utilized to solve video recognition problem due to its prominent representation ability. Deep neural networks for video tasks is highly customized…
Improving Auto-Augment via Augmentation-Wise Weight Sharing
Keyu Tian, Chen Lin, Ming Sun +3
The recent progress on automatically searching augmentation policies has boosted the performance substantially for various tasks. A key component of automatic augmentation search i…