Liang Zheng

Liang Zheng

Auto-generated profile, based on publicly available information

Liang Zheng

Australian National University

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

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

Representative Publications

View All Publications
30 May 2017 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
LZLiang Zheng
Liang Zheng
YYYi Yang
Yi Yang
QTQi Tian
Qi Tian
In the early days, content-based image retrieval (CBIR) was studied with global features. Since 2003, image retrieval based on local descriptors (de facto SIFT) has been extensively studied for over a decade due to the advantage of SIFT in dealing with image transformations. Recently, image representations based on the convolutional neural network (CNN) have attracted increasing interest in the community and demonstrated impressive performance. Given this time of rapid evolution, this article provides a comprehensive survey of instance retrieval over the last decade. Two broad categories, SIFT-based and CNN-based methods, are presented. For the former, according to the codebook size, we organize the literature into using large/medium-sized/small codebooks. For the latter, we discuss three lines of methods, i.e., using pre-trained or fine-tuned CNN models, and hybrid methods. The first two perform a single-pass of an image to the network, while the last category employs a patch-based feature extraction scheme. This survey presents milestones in modern instance retrieval, reviews a broad selection of previous works in different categories, and provides insights on the connection between SIFT and CNN-based methods. After analyzing and comparing retrieval performance of different categories on several datasets, we discuss promising directions towards generic and specialized instance retrieval.

18 April 2019 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
LZLiang Zheng
Liang Zheng
YHYujia Huang
Yujia Huang
HLHuchuan Lu
Huchuan Lu
YYYi Yang
Yi Yang
Pedestrian misalignment, which mainly arises from detector errors and pose variations, is a critical problem for a robust person re-identification (re-ID) system. With poor alignment, the feature learning and matching process might be largely compromised. To address this problem, this paper introduces the pose invariant embedding (PIE) as a pedestrian descriptor. First, in order to align pedestrians to a standard pose, the PoseBox structure is introduced, which is generated through pose estimation followed by affine transformations. Second, to reduce the impact of pose estimation errors and information loss during PoseBox construction, we design a PoseBox fusion (PBF) CNN architecture that takes the original image, the PoseBox, and the pose estimation confidence as input. The proposed PIE descriptor is thus defined as the fully connected layer of the PBF network for the retrieval task. Experiments are conducted on the Market-1501, CUHK03-NP, and DukeMTMC-reID datasets. We show that PoseBox alone yields decent re-ID accuracy, and that when integrated in the PBF network, the learned PIE descriptor produces competitive performance compared with the state-of-the-art approaches.

4 October 2018 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
Zhedong ZhengZhedong Zheng
Zhedong Zheng
LZLiang Zheng
Liang Zheng
YYYi Yang
Yi Yang
Person re-identification (re-ID) is mostly viewed as an image retrieval problem. This task aims to search a query person in a large image pool. In practice, person re-ID usually adopts automatic detectors to obtain cropped pedestrian images. However, this process suffers from two types of detector errors: excessive background and part missing. Both errors deteriorate the quality of pedestrian alignment and may compromise pedestrian matching due to the position and scale variances. To address the misalignment problem, we propose that alignment be learned from an identification procedure. We introduce the pedestrian alignment network (PAN) which allows discriminative embedding learning pedestrian alignment without extra annotations. We observe that when the convolutional neural network (CNN) learns to discriminate between different identities, the learned feature maps usually exhibit strong activations on the human body rather than the background. The proposed network thus takes advantage of this attention mechanism to adaptively locate and align pedestrians within a bounding box. Visual examples show that pedestrians are better aligned with PAN. Experiments on three large-scale re-ID datasets confirm that PAN improves the discriminative ability of the feature embeddings and yields competitive accuracy with the state-of-the-art methods.

8 October 2018 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
Zhun ZhongZhun Zhong
Zhun Zhong
LZLiang Zheng
Liang Zheng
Zhedong ZhengZhedong Zheng
Zhedong Zheng
SLShaozi Li
Shaozi Li
YYYi Yang
Yi Yang
Person re-identification (re-ID) is cross-camera retrieval task that suffers from image style variations caused by different cameras. The art implicitly addresses this problem by learning a camera-invariant descriptor subspace. In this paper, we explicitly consider this challenge by introducing camera style (CamStyle). CamStyle can serve as a data augmentation approach that reduces the risk of deep network over-fitting and that smooths the camera style disparities. Specifically, with a style transfer model, labeled training images can be style-transferred to each camera, and, along with the original training samples, form the augmented training set. This method, while increasing data diversity against over-fitting, also incurs a considerable level of noise. In the effort to alleviate the impact of noise, the label smooth regularization (LSR) is adopted. The vanilla version of our method (without LSR) performs reasonably well on few-camera systems in which over-fitting often occurs. With LSR, we demonstrate consistent improvement in all systems regardless of the extent of over-fitting. We also report competitive accuracy compared with the state of the art on Market-1501 and DukeMTMC-reID. Importantly, CamStyle can be employed to the challenging problems of one view learning and unsupervised domain adaptation in person re-identification, both of which have critical research and application significance. The former only has labeled data in one camera view and the latter only has labeled data in the source domain. Experiment results show that CamStyle significantly improves the performance of baseline in the two problems. Specially, for unsupervised domain adaptation, CamStyle achieves state-of-the-art accuracy based on a baseline deep re-ID model on Market-1501 and DukeMTMC-reID. Our code is available at: https://github.com/zhunzhong07/CamStyle

28 February 2020 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
Zhun ZhongZhun Zhong
Zhun Zhong
LZLiang Zheng
Liang Zheng
ZLZhiming Luo
Zhiming Luo
SLShaozi Li
Shaozi Li
YYYi Yang
Yi Yang
This work considers the problem of unsupervised domain adaptation in person re-identification (re-ID), which aims to transfer knowledge from the source domain to the target domain. Existing methods are primary to reduce the inter-domain shift between the domains, which however usually overlook the relations among target samples. This paper investigates into the intra-domain variations of the target domain and proposes a novel adaptation framework w.r.t three types of underlying invariance, i.e., Exemplar-Invariance, Camera-Invariance, and Neighborhood-Invariance. Specifically, an exemplar memory is introduced to store features of samples, which can effectively and efficiently enforce the invariance constraints over the global dataset. We further present the Graph-based Positive Prediction (GPP) method to explore reliable neighbors for the target domain, which is built upon the memory and is trained on the source samples. Experiments demonstrate that 1) the three invariance properties are complementary and indispensable for effective domain adaptation, 2) the memory plays a key role in implementing invariance learning and improves the performance with limited extra computation cost, 3) GPP can facilitate the invariance learning and thus significantly improves the results, and 4) our approach produces new state-of-the-art adaptation accuracy on three re-ID large-scale benchmarks.

7 June 2018 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
XDXuanyi Dong
Xuanyi Dong
LZLiang Zheng
Liang Zheng
FMFan Ma
Fan Ma
YYYi Yang
Yi Yang
DMDeyu Meng
Deyu Meng
In this paper, we study object detection using a large pool of unlabeled images and only a few labeled images per category, named “few-example object detection”. The key challenge consists in generating trustworthy training samples as many as possible from the pool. Using few training examples as seeds, our method iterates between model training and high-confidence sample selection. In training, easy samples are generated first and, then the poorly initialized model undergoes improvement. As the model becomes more discriminative, challenging but reliable samples are selected. After that, another round of model improvement takes place. To further improve the precision and recall of the generated training samples, we embed multiple detection models in our framework, which has proven to outperform the single model baseline and the model ensemble method. Experiments on PASCAL VOC'07, MS COCO'14, and ILSVRC'13 indicate that by using as few as three or four samples selected for each category, our method produces very competitive results when compared to the state-of-the-art weakly-supervised approaches using a large number of image-level labels.