Xiaogang Wang

Xiaogang Wang

Auto-generated profile, based on publicly available information

Xiaogang Wang

Southwest University

Research Focus & Metrics

Academic Career Length

24Years (2003-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 October 2019 in International Journal of Computer Vision
Verified
Journal Article
Open access
PDF file
LLLi Liu
Li Liu
WOWanli Ouyang
Wanli Ouyang
XWXiaogang Wang
Xiaogang Wang
PFPaul Fieguth
Paul Fieguth
JCJie Chen
Jie Chen
MPMatti Pietikäinen
Matti Pietikäinen
Object detection, one of the most fundamental and challenging problems in computer vision, seeks to locate object instances from a large number of predefined categories in natural images. Deep learning techniques have emerged as a powerful strategy for learning feature representations directly from data and have led to remarkable breakthroughs in the field of generic object detection. Given this period of rapid evolution, the goal of this paper is to provide a comprehensive survey of the recent achievements in this field brought about by deep learning techniques. More than 300 research contributions are included in this survey, covering many aspects of generic object detection: detection frameworks, object feature representation, object proposal generation, context modeling, training strategies, and evaluation metrics. We finish the survey by identifying promising directions for future research.

28 February 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
SSShaoshuai Shi
Shaoshuai Shi
ZWZhe Wang
Zhe Wang
JSJianping Shi
Jianping Shi
XWXiaogang Wang
Xiaogang Wang
HLHongsheng Li
Hongsheng Li
3D object detection from LiDAR point cloud is a challenging problem in 3D scene understanding and has many practical applications. In this paper, we extend our preliminary work PointRCNN to a novel and strong point-cloud-based 3D object detection framework, the part-aware and aggregation neural network (Part- $A^2$ net). The whole framework consists of the part-aware stage and the part-aggregation stage. Firstly, the part-aware stage for the first time fully utilizes free-of-charge part supervisions derived from 3D ground-truth boxes to simultaneously predict high quality 3D proposals and accurate intra-object part locations. The predicted intra-object part locations within the same proposals are grouped by our new-designed RoI-aware point cloud pooling module, which results in an effective representation to encode the geometry-specific features of each 3D proposal. Then the part-aggregation stage learns to re-score the box and refine the box location by exploring the spatial relationship of the pooled intra-object part locations. Extensive experiments are conducted to demonstrate the performance improvements from each component of our proposed framework. Our Part- $A^2$ net outperforms all existing 3D detection methods and achieves new state-of-the-art on KITTI 3D object detection dataset by utilizing only the LiDAR point cloud data.

12 September 2008 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
XWXiaogang Wang
Xiaogang Wang
XTXiaoou Tang
Xiaoou Tang
In this paper, we propose a novel face photo-sketch synthesis and recognition method using a multiscale Markov Random Fields (MRF) model. Our system has three components: 1) given a face photo, synthesizing a sketch drawing; 2) given a face sketch drawing, synthesizing a photo; and 3) searching for face photos in the database based on a query sketch drawn by an artist. It has useful applications for both digital entertainment and law enforcement. We assume that faces to be studied are in a frontal pose, with normal lighting and neutral expression, and have no occlusions. To synthesize sketch/photo images, the face region is divided into overlapping patches for learning. The size of the patches decides the scale of local face structures to be learned. From a training set which contains photo-sketch pairs, the joint photo-sketch model is learned at multiple scales using a multiscale MRF model. By transforming a face photo to a sketch (or transforming a sketch to a photo), the difference between photos and sketches is significantly reduced, thus allowing effective matching between the two in face sketch recognition. After the photo-sketch transformation, in principle, most of the proposed face photo recognition approaches can be applied to face sketch recognition in a straightforward way. Extensive experiments are conducted on a face sketch database including 606 faces, which can be downloaded from our Web site (http://mmlab.ie.cuhk.edu.hk/facesketch.html).

27 April 2023 in International Journal of Computer Vision
Verified
Journal Article
Closed access
PDF file
JMJIAGENG MAO
JIAGENG MAO
SSShaoshuai Shi
Shaoshuai Shi
XWXiaogang Wang
Xiaogang Wang
HLHongsheng Li
Hongsheng Li

17 July 2019 in Proceedings of the AAAI Conference on Artificial Intelligence
Verified
Journal Article
Open access
PDF file
BLBuyu Li
Buyu Li
YLYu Liu
Yu Liu
XWXiaogang Wang
Xiaogang Wang
Despite the great success of two-stage detectors, single-stage detector is still a more elegant and efficient way, yet suffers from the two well-known disharmonies during training, i.e. the huge difference in quantity between positive and negative examples as well as between easy and hard examples. In this work, we first point out that the essential effect of the two disharmonies can be summarized in term of the gradient. Further, we propose a novel gradient harmonizing mechanism (GHM) to be a hedging for the disharmonies. The philosophy behind GHM can be easily embedded into both classification loss function like cross-entropy (CE) and regression loss function like smooth-L1 (SL1) loss. To this end, two novel loss functions called GHM-C and GHM-R are designed to balancing the gradient flow for anchor classification and bounding box refinement, respectively. Ablation study on MS COCO demonstrates that without laborious hyper-parameter tuning, both GHM-C and GHM-R can bring substantial improvement for single-stage detector. Without any whistles and bells, the proposed model achieves 41.6 mAP on COCO testdev set which surpass the state-of-the-art method, Focal Loss (FL) + SL1, by 0.8. The code1 is released to facilitate future research.

18 March 2021 in arXiv
Verified
Preprint
Open access
PDF file
XZXizhou Zhu
Xizhou Zhu
WSWeijie Su
Weijie Su
LLLewei Lu
Lewei Lu
BLBin Li
Bin Li
XWXiaogang Wang
Xiaogang Wang
JDJifeng Dai
Jifeng Dai
DETR has been recently proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance. However, it suffers from slow convergence and limited feature spatial resolution, due to the limitation of Transformer attention modules in processing image feature maps. To mitigate these issues, we proposed Deformable DETR, whose attention modules only attend to a small set of key sampling points around a reference. Deformable DETR can achieve better performance than DETR (especially on small objects) with 10 times less training epochs. Extensive experiments on the COCO benchmark demonstrate the effectiveness of our approach. Code is released at https://github.com/fundamentalvision/Deformable-DETR.