205 citations · 1.4k across the 102 of their papers we have counts for
28 papers · 1 filter
Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE
Qihuang Zhong, Liang Ding, Yibing Zhan +11
This technical report briefly describes our JDExplore d-team's Vega v2 submission on the SuperGLUE leaderboard. SuperGLUE is more challenging than the widely used general language…
Improving Training and Inference of Face Recognition Models via Random Temperature Scaling
Lei Shang, Mouxiao Huang, Wu Shi +6
Data uncertainty is commonly observed in the images for face recognition (FR). However, deep learning algorithms often make predictions with high confidence even for uncertain or i…
ResFormer: Scaling ViTs with Multi-Resolution Training
Rui Tian, Zuxuan Wu, Qi Dai +3
Vision Transformers (ViTs) have achieved overwhelming success, yet they suffer from vulnerable resolution scalability, i.e., the performance drops drastically when presented with i…
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information
Weijie Su, Xizhou Zhu, Chenxin Tao +7
To effectively exploit the potential of large-scale models, various pre-training strategies supported by massive data from different sources are proposed, including supervised pre-…
BEVFormer v2: Adapting Modern Image Backbones to Bird's-Eye-View Recognition via Perspective Supervision
Chenyu Yang, Yuntao Chen, Hao Tian +9
We present a novel bird's-eye-view (BEV) detector with perspective supervision, which converges faster and better suits modern image backbones. Existing state-of-the-art BEV detect…
Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks
Hao Li, Jinguo Zhu, Xiaohu Jiang +8
Despite the remarkable success of foundation models, their task-specific fine-tuning paradigm makes them inconsistent with the goal of general perception modeling. The key to elimi…
UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer
Kunchang Li, Yali Wang, Yinan He +4
Learning discriminative spatiotemporal representation is the key problem of video understanding. Recently, Vision Transformers (ViTs) have shown their power in learning long-term v…
Demystify Transformers & Convolutions in Modern Image Deep Networks
Xiaowei Hu, Min Shi, Weiyun Wang +9
Vision transformers have gained popularity recently, leading to the development of new vision backbones with improved features and consistent performance gains. However, these adva…
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Wenhai Wang, Jifeng Dai, Zhe Chen +9
Compared to the great progress of large-scale vision transformers (ViTs) in recent years, large-scale models based on convolutional neural networks (CNNs) are still in an early sta…
Wider and Higher: Intensive Integration and Global Foreground Perception for Image Matting
Yu Qiao, Ziqi Wei, Yuhao Liu +4
This paper reviews recent deep-learning-based matting research and conceives our wider and higher motivation for image matting. Many approaches achieve alpha mattes with complex en…
Hierarchical and Progressive Image Matting
Yu Qiao, Yuhao Liu, Ziqi Wei +4
Most matting researches resort to advanced semantics to achieve high-quality alpha mattes, and direct low-level features combination is usually explored to complement alpha details…
Efficient Image Super-Resolution using Vast-Receptive-Field Attention
Lin Zhou, Haoming Cai, Jinjin Gu +5
The attention mechanism plays a pivotal role in designing advanced super-resolution (SR) networks. In this work, we design an efficient SR network by improving the attention mechan…
Low-Resolution Action Recognition for Tiny Actions Challenge
Boyu Chen, Yu Qiao, Yali Wang
Tiny Actions Challenge focuses on understanding human activities in real-world surveillance. Basically, there are two main difficulties for activity recognition in this scenario. F…
Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe
Hongyang Li, Chonghao Sima, Jifeng Dai +19
Learning powerful representations in bird's-eye-view (BEV) for perception tasks is trending and drawing extensive attention both from industry and academia. Conventional approaches…
Frozen CLIP Models are Efficient Video Learners
Ziyi Lin, Shijie Geng, Renrui Zhang +6
Video recognition has been dominated by the end-to-end learning paradigm -- first initializing a video recognition model with weights of a pretrained image model and then conductin…
Vision-Centric BEV Perception: A Survey
Yuexin Ma, Tai Wang, Xuyang Bai +7
In recent years, vision-centric Bird's Eye View (BEV) perception has garnered significant interest from both industry and academia due to its inherent advantages, such as providing…
GenText: Unsupervised Artistic Text Generation via Decoupled Font and Texture Manipulation
Qirui Huang, Bin Fu, Aozhong Zhang +1
Automatic artistic text generation is an emerging topic which receives increasing attention due to its wide applications. The artistic text can be divided into three components, co…
HQANN: Efficient and Robust Similarity Search for Hybrid Queries with Structured and Unstructured Constraints
Wei Wu, Junlin He, Yu Qiao +3
The in-memory approximate nearest neighbor search (ANNS) algorithms have achieved great success for fast high-recall query processing, but are extremely inefficient when handling h…
CP3: Unifying Point Cloud Completion by Pretrain-Prompt-Predict Paradigm
Mingye Xu, Yali Wang, Yihao Liu +2
Point cloud completion aims to predict complete shape from its partial observation. Current approaches mainly consist of generation and refinement stages in a coarse-to-fine style.…
Siamese Image Modeling for Self-Supervised Vision Representation Learning
Chenxin Tao, Xizhou Zhu, Weijie Su +6
Self-supervised learning (SSL) has delivered superior performance on a variety of downstream vision tasks. Two main-stream SSL frameworks have been proposed, i.e., Instance Discrim…
Blueprint Separable Residual Network for Efficient Image Super-Resolution
Zheyuan Li, Yingqi Liu, Xiangyu Chen +4
Recent advances in single image super-resolution (SISR) have achieved extraordinary performance, but the computational cost is too heavy to apply in edge devices. To alleviate this…
Cross Domain Object Detection by Target-Perceived Dual Branch Distillation
Mengzhe He, Yali Wang, Jiaxi Wu +6
Cross domain object detection is a realistic and challenging task in the wild. It suffers from performance degradation due to large shift of data distributions and lack of instance…
Vision Transformer Adapter for Dense Predictions
Zhe Chen, Yuchen Duan, Wenhai Wang +4
This work investigates a simple yet powerful dense prediction task adapter for Vision Transformer (ViT). Unlike recently advanced variants that incorporate vision-specific inductiv…
Evaluating the Generalization Ability of Super-Resolution Networks
Yihao Liu, Hengyuan Zhao, Jinjin Gu +2
Performance and generalization ability are two important aspects to evaluate the deep learning models. However, research on the generalization ability of Super-Resolution (SR) netw…