140 citations · 919 across the 60 of their papers we have counts for
60 papers
Informative Data Mining for One-Shot Cross-Domain Semantic Segmentation
Yuxi Wang, Jian Liang, Jun Xiao +3
Contemporary domain adaptation offers a practical solution for achieving cross-domain transfer of semantic segmentation between labeled source data and unlabeled target data. These…
DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions
Haochen Wang, Junsong Fan, Yuxi Wang +3
As it is empirically observed that Vision Transformers (ViTs) are quite insensitive to the order of input tokens, the need for an appropriate self-supervised pretext task that enha…
PanoOcc: Unified Occupancy Representation for Camera-based 3D Panoptic Segmentation
Yuqi Wang, Yuntao Chen, Xingyu Liao +2
Comprehensive modeling of the surrounding 3D world is key to the success of autonomous driving. However, existing perception tasks like object detection, road structure segmentatio…
Weakly Supervised 3D Object Detection with Multi-Stage Generalization
Jiawei He, Yuqi Wang, Yuntao Chen +1
With the rapid development of large models, the need for data has become increasingly crucial. Especially in 3D object detection, costly manual annotations have hindered further ad…
Using Unreliable Pseudo-Labels for Label-Efficient Semantic Segmentation
Haochen Wang, Yuchao Wang, Yujun Shen +3
The crux of label-efficient semantic segmentation is to produce high-quality pseudo-labels to leverage a large amount of unlabeled or weakly labeled data. A common practice is to s…
Pulling Target to Source: A New Perspective on Domain Adaptive Semantic Segmentation
Haochen Wang, Yujun Shen, Jingjing Fei +4
Domain adaptive semantic segmentation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. However, existing methods primarily focus on directly l…
Hard Patches Mining for Masked Image Modeling
Haochen Wang, Kaiyou Song, Junsong Fan +3
Masked image modeling (MIM) has attracted much research attention due to its promising potential for learning scalable visual representations. In typical approaches, models usually…
A Survey of Deep Visual Cross-Domain Few-Shot Learning
Wenjian Wang, Lijuan Duan, Yuxi Wang +3
Few-Shot transfer learning has become a major focus of research as it allows recognition of new classes with limited labeled data. While it is assumed that train and test data have…
Blind Video Deflickering by Neural Filtering with a Flawed Atlas
Chenyang Lei, Xuanchi Ren, Zhaoxiang Zhang +1
Many videos contain flickering artifacts. Common causes of flicker include video processing algorithms, video generation algorithms, and capturing videos under specific situations.…
FrustumFormer: Adaptive Instance-aware Resampling for Multi-view 3D Detection
Yuqi Wang, Yuntao Chen, Zhaoxiang Zhang
The transformation of features from 2D perspective space to 3D space is essential to multi-view 3D object detection. Recent approaches mainly focus on the design of view transforma…
The catalog-to-cosmology framework for weak lensing and galaxy clustering for LSST
J. Prat, J. Zuntz, Y. Omori +20
We present TXPipe, a modular, automated and reproducible pipeline for ingesting catalog data and performing all the calculations required to obtain quality-assured two-point measur…
Extracting Semantic Knowledge from GANs with Unsupervised Learning
Jianjin Xu, Zhaoxiang Zhang, Xiaolin Hu
Recently, unsupervised learning has made impressive progress on various tasks. Despite the dominance of discriminative models, increasing attention is drawn to representations lear…
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…
4D Unsupervised Object Discovery
Yuqi Wang, Yuntao Chen, Zhaoxiang Zhang
Object discovery is a core task in computer vision. While fast progresses have been made in supervised object detection, its unsupervised counterpart remains largely unexplored. Wi…
Pro-tuning: Unified Prompt Tuning for Vision Tasks
Xing Nie, Bolin Ni, Jianlong Chang +6
In computer vision, fine-tuning is the de-facto approach to leverage pre-trained vision models to perform downstream tasks. However, deploying it in practice is quite challenging,…
MemoNav: Selecting Informative Memories for Visual Navigation
Hongxin Li, Xu Yang, Yuran Yang +2
Image-goal navigation is a challenging task, as it requires the agent to navigate to a target indicated by an image in a previously unseen scene. Current methods introduce diverse…
Densely Constrained Depth Estimator for Monocular 3D Object Detection
Yingyan Li, Yuntao Chen, Jiawei He +1
Estimating accurate 3D locations of objects from monocular images is a challenging problem because of lacking depth. Previous work shows that utilizing the object's keypoint projec…
Fully Sparse 3D Object Detection
Lue Fan, Feng Wang, Naiyan Wang +1
As the perception range of LiDAR increases, LiDAR-based 3D object detection becomes a dominant task in the long-range perception task of autonomous driving. The mainstream 3D objec…
DATA: Domain-Aware and Task-Aware Self-supervised Learning
Qing Chang, Junran Peng, Lingxie Xie +4
The paradigm of training models on massive data without label through self-supervised learning (SSL) and finetuning on many downstream tasks has become a trend recently. However, d…
Sparse Instance Activation for Real-Time Instance Segmentation
Tianheng Cheng, Xinggang Wang, Shaoyu Chen +5
In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation. Previously, most instance segmentation methods hea…
HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network
Chang Yu, Xiangyu Zhu, Xiaomei Zhang +3
Capsule networks are designed to present the objects by a set of parts and their relationships, which provide an insight into the procedure of visual perception. Although recent wo…
The Devil Is in the Details: Window-based Attention for Image Compression
Renjie Zou, Chunfeng Song, Zhaoxiang Zhang
Learned image compression methods have exhibited superior rate-distortion performance than classical image compression standards. Most existing learned image compression models are…
Emergence of Machine Language: Towards Symbolic Intelligence with Neural Networks
Yuqi Wang, Xu-Yao Zhang, Cheng-Lin Liu +1
Representation is a core issue in artificial intelligence. Humans use discrete language to communicate and learn from each other, while machines use continuous features (like vecto…
Embracing Single Stride 3D Object Detector with Sparse Transformer
Lue Fan, Ziqi Pang, Tianyuan Zhang +5
In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases. Overlooking thi…