arXiv subjects

Shengcai Liao

Publications and source records attributed to Shengcai Liao.

53 records · Page 3Linked to original sources

arXiv2020

Generalizable Pedestrian Detection: The Elephant In The Room

Pedestrian detection is used in many vision based applications ranging from video surveillance to autonomous driving. Despite achieving high performance, it is still largely unknown how well existing detectors generalize to unseen data. This is important because a practical detector should be ready to use in various scenarios in applications. To this end, we conduct a comprehensive study in this paper, using a general principle of direct cross-dataset evaluation. Through this study, we find that existing state-of-the-art pedestrian detectors, though perform quite well when trained and tested on the same dataset, generalize poorly in cross dataset evaluation. We demonstrate that there are two reasons for this trend. Firstly, their designs (e.g. anchor settings) may be biased towards popular benchmarks in the traditional single-dataset training and test pipeline, but as a result largely limit their generalization capability. Secondly, the training source is generally not dense in pedestrians and diverse in scenarios. Under direct cross-dataset evaluation, surprisingly, we find that a general purpose object detector, without pedestrian-tailored adaptation in design, generalizes much better compared to existing state-of-the-art pedestrian detectors. Furthermore, we illustrate that diverse and dense datasets, collected by crawling the web, serve to be an efficient source of pre-training for pedestrian detection. Accordingly, we propose a progressive training pipeline and find that it works well for autonomous-driving oriented pedestrian detection. Consequently, the study conducted in this paper suggests that more emphasis should be put on cross-dataset evaluation for the future design of generalizable pedestrian detectors. Code and models can be accessed at https://github.com/hasanirtiza/Pedestron.

cs.CV↗

arXiv2020

Surpassing Real-World Source Training Data: Random 3D Characters for Generalizable Person Re-Identification

Person re-identification has seen significant advancement in recent years. However, the ability of learned models to generalize to unknown target domains still remains limited. One possible reason for this is the lack of large-scale and diverse source training data, since manually labeling such a dataset is very expensive and privacy sensitive. To address this, we propose to automatically synthesize a large-scale person re-identification dataset following a set-up similar to real surveillance but with virtual environments, and then use the synthesized person images to train a generalizable person re-identification model. Specifically, we design a method to generate a large number of random UV texture maps and use them to create different 3D clothing models. Then, an automatic code is developed to randomly generate various different 3D characters with diverse clothes, races and attributes. Next, we simulate a number of different virtual environments using Unity3D, with customized camera networks similar to real surveillance systems, and import multiple 3D characters at the same time, with various movements and interactions along different paths through the camera networks. As a result, we obtain a virtual dataset, called RandPerson, with 1,801,816 person images of 8,000 identities. By training person re-identification models on these synthesized person images, we demonstrate, for the first time, that models trained on virtual data can generalize well to unseen target images, surpassing the models trained on various real-world datasets, including CUHK03, Market-1501, DukeMTMC-reID, and almost MSMT17. The RandPerson dataset is available at https://github.com/VideoObjectSearch/RandPerson.

cs.CV↗

arXiv2020

Interpretable and Generalizable Person Re-Identification with Query-Adaptive Convolution and Temporal Lifting

For person re-identification, existing deep networks often focus on representation learning. However, without transfer learning, the learned model is fixed as is, which is not adaptable for handling various unseen scenarios. In this paper, beyond representation learning, we consider how to formulate person image matching directly in deep feature maps. We treat image matching as finding local correspondences in feature maps, and construct query-adaptive convolution kernels on the fly to achieve local matching. In this way, the matching process and results are interpretable, and this explicit matching is more generalizable than representation features to unseen scenarios, such as unknown misalignments, pose or viewpoint changes. To facilitate end-to-end training of this architecture, we further build a class memory module to cache feature maps of the most recent samples of each class, so as to compute image matching losses for metric learning. Through direct cross-dataset evaluation, the proposed Query-Adaptive Convolution (QAConv) method gains large improvements over popular learning methods (about 10%+ mAP), and achieves comparable results to many transfer learning methods. Besides, a model-free temporal cooccurrence based score weighting method called TLift is proposed, which improves the performance to a further extent, achieving state-of-the-art results in cross-dataset person re-identification. Code is available at https://github.com/ShengcaiLiao/QAConv.

cs.CV↗

arXiv2019

Pixel-aware Deep Function-mixture Network for Spectral Super-Resolution

Spectral super-resolution (SSR) aims at generating a hyperspectral image (HSI) from a given RGB image. Recently, a promising direction for SSR is to learn a complicated mapping function from the RGB image to the HSI counterpart using a deep convolutional neural network. This essentially involves mapping the RGB context within a size-specific receptive field centered at each pixel to its spectrum in the HSI. The focus thereon is to appropriately determine the receptive field size and establish the mapping function from RGB context to the corresponding spectrum. Due to their differences in category or spatial position, pixels in HSIs often require different-sized receptive fields and distinct mapping functions. However, few efforts have been invested to explicitly exploit this prior. To address this problem, we propose a pixel-aware deep function-mixture network for SSR, which is composed of a new class of modules, termed function-mixture (FM) blocks. Each FM block is equipped with some basis functions, i.e., parallel subnets of different-sized receptive fields. Besides, it incorporates an extra subnet as a mixing function to generate pixel-wise weights, and then linearly mixes the outputs of all basis functions with those generated weights. This enables us to pixel-wisely determine the receptive field size and the mapping function. Moreover, we stack several such FM blocks to further increase the flexibility of the network in learning the pixel-wise mapping. To encourage feature reuse, intermediate features generated by the FM blocks are fused in late stage, which proves to be effective for boosting the SSR performance. Experimental results on three benchmark HSI datasets demonstrate the superiority of the proposed method.

cs.CV↗

arXiv2018

Vehicle Re-identification Using Quadruple Directional Deep Learning Features

In order to resist the adverse effect of viewpoint variations for improving vehicle re-identification performance, we design quadruple directional deep learning networks to extract quadruple directional deep learning features (QD-DLF) of vehicle images. The quadruple directional deep learning networks are with similar overall architecture, including the same basic deep learning architecture but different directional feature pooling layers. Specifically, the same basic deep learning architecture is a shortly and densely connected convolutional neural network to extract basic feature maps of an input square vehicle image in the first stage. Then, the quadruple directional deep learning networks utilize different directional pooling layers, i.e., horizontal average pooling (HAP) layer, vertical average pooling (VAP) layer, diagonal average pooling (DAP) layer and anti-diagonal average pooling (AAP) layer, to compress the basic feature maps into horizontal, vertical, diagonal and anti-diagonal directional feature maps, respectively. Finally, these directional feature maps are spatially normalized and concatenated together as a quadruple directional deep learning feature for vehicle re-identification. Extensive experiments on both VeRi and VehicleID databases show that the proposed QD-DLF approach outperforms multiple state-of-the-art vehicle re-identification methods.

cs.CV↗

arXiv2017

Deep Person Re-Identification with Improved Embedding and Efficient Training

Person re-identification task has been greatly boosted by deep convolutional neural networks (CNNs) in recent years. The core of which is to enlarge the inter-class distinction as well as reduce the intra-class variance. However, to achieve this, existing deep models prefer to adopt image pairs or triplets to form verification loss, which is inefficient and unstable since the number of training pairs or triplets grows rapidly as the number of training data grows. Moreover, their performance is limited since they ignore the fact that different dimension of embedding may play different importance. In this paper, we propose to employ identification loss with center loss to train a deep model for person re-identification. The training process is efficient since it does not require image pairs or triplets for training while the inter-class distinction and intra-class variance are well handled. To boost the performance, a new feature reweighting (FRW) layer is designed to explicitly emphasize the importance of each embedding dimension, thus leading to an improved embedding. Experiments on several benchmark datasets have shown the superiority of our method over the state-of-the-art alternatives on both accuracy and speed.

cs.CV↗

arXiv2017

Learning Efficient Image Representation for Person Re-Identification

Color names based image representation is successfully used in person re-identification, due to the advantages of being compact, intuitively understandable as well as being robust to photometric variance. However, there exists the diversity between underlying distribution of color names' RGB values and that of image pixels' RGB values, which may lead to inaccuracy when directly comparing them in Euclidean space. In this paper, we propose a new method named soft Gaussian mapping (SGM) to address this problem. We model the discrepancies between color names and pixels using a Gaussian and utilize the inverse of covariance matrix to bridge the gap between them. Based on SGM, an image could be converted to several soft Gaussian maps. In each soft Gaussian map, we further seek to establish stable and robust descriptors within a local region through a max pooling operation. Then, a robust image representation based on color names is obtained by concatenating the statistical descriptors in each stripe. When labeled data are available, one discriminative subspace projection matrix is learned to build efficient representations of an image via cross-view coupling learning. Experiments on the public datasets - VIPeR, PRID450S and CUHK03, demonstrate the effectiveness of our method.

cs.CV↗

arXiv2017

Deep Hybrid Similarity Learning for Person Re-identification

Person Re-IDentification (Re-ID) aims to match person images captured from two non-overlapping cameras. In this paper, a deep hybrid similarity learning (DHSL) method for person Re-ID based on a convolution neural network (CNN) is proposed. In our approach, a CNN learning feature pair for the input image pair is simultaneously extracted. Then, both the element-wise absolute difference and multiplication of the CNN learning feature pair are calculated. Finally, a hybrid similarity function is designed to measure the similarity between the feature pair, which is realized by learning a group of weight coefficients to project the element-wise absolute difference and multiplication into a similarity score. Consequently, the proposed DHSL method is able to reasonably assign parameters of feature learning and metric learning in a CNN so that the performance of person Re-ID is improved. Experiments on three challenging person Re-ID databases, QMUL GRID, VIPeR and CUHK03, illustrate that the proposed DHSL method is superior to multiple state-of-the-art person Re-ID methods.

cs.CV↗

arXiv2016

Embedding Deep Metric for Person Re-identication A Study Against Large Variations

Person re-identification is challenging due to the large variations of pose, illumination, occlusion and camera view. Owing to these variations, the pedestrian data is distributed as highly-curved manifolds in the feature space, despite the current convolutional neural networks (CNN)'s capability of feature extraction. However, the distribution is unknown, so it is difficult to use the geodesic distance when comparing two samples. In practice, the current deep embedding methods use the Euclidean distance for the training and test. On the other hand, the manifold learning methods suggest to use the Euclidean distance in the local range, combining with the graphical relationship between samples, for approximating the geodesic distance. From this point of view, selecting suitable positive i.e. intra-class) training samples within a local range is critical for training the CNN embedding, especially when the data has large intra-class variations. In this paper, we propose a novel moderate positive sample mining method to train robust CNN for person re-identification, dealing with the problem of large variation. In addition, we improve the learning by a metric weight constraint, so that the learned metric has a better generalization ability. Experiments show that these two strategies are effective in learning robust deep metrics for person re-identification, and accordingly our deep model significantly outperforms the state-of-the-art methods on several benchmarks of person re-identification. Therefore, the study presented in this paper may be useful in inspiring new designs of deep models for person re-identification.

cs.CV↗

arXiv2016

Learning Discriminative Features with Class Encoder

Deep neural networks usually benefit from unsupervised pre-training, e.g. auto-encoders. However, the classifier further needs supervised fine-tuning methods for good discrimination. Besides, due to the limits of full-connection, the application of auto-encoders is usually limited to small, well aligned images. In this paper, we incorporate the supervised information to propose a novel formulation, namely class-encoder, whose training objective is to reconstruct a sample from another one of which the labels are identical. Class-encoder aims to minimize the intra-class variations in the feature space, and to learn a good discriminative manifolds on a class scale. We impose the class-encoder as a constraint into the softmax for better supervised training, and extend the reconstruction on feature-level to tackle the parameter size issue and translation issue. The experiments show that the class-encoder helps to improve the performance on benchmarks of classification and face recognition. This could also be a promising direction for fast training of face recognition models.

cs.CV↗

arXiv2015

Cross-Modal Similarity Learning : A Low Rank Bilinear Formulation

The cross-media retrieval problem has received much attention in recent years due to the rapid increasing of multimedia data on the Internet. A new approach to the problem has been raised which intends to match features of different modalities directly. In this research, there are two critical issues: how to get rid of the heterogeneity between different modalities and how to match the cross-modal features of different dimensions. Recently metric learning methods show a good capability in learning a distance metric to explore the relationship between data points. However, the traditional metric learning algorithms only focus on single-modal features, which suffer difficulties in addressing the cross-modal features of different dimensions. In this paper, we propose a cross-modal similarity learning algorithm for the cross-modal feature matching. The proposed method takes a bilinear formulation, and with the nuclear-norm penalization, it achieves low-rank representation. Accordingly, the accelerated proximal gradient algorithm is successfully imported to find the optimal solution with a fast convergence rate O(1/t^2). Experiments on three well known image-text cross-media retrieval databases show that the proposed method achieves the best performance compared to the state-of-the-art algorithms.

cs.MM↗

arXiv2015

Constrained Deep Metric Learning for Person Re-identification

Person re-identification aims to re-identify the probe image from a given set of images under different camera views. It is challenging due to large variations of pose, illumination, occlusion and camera view. Since the convolutional neural networks (CNN) have excellent capability of feature extraction, certain deep learning methods have been recently applied in person re-identification. However, in person re-identification, the deep networks often suffer from the over-fitting problem. In this paper, we propose a novel CNN-based method to learn a discriminative metric with good robustness to the over-fitting problem in person re-identification. Firstly, a novel deep architecture is built where the Mahalanobis metric is learned with a weight constraint. This weight constraint is used to regularize the learning, so that the learned metric has a better generalization ability. Secondly, we find that the selection of intra-class sample pairs is crucial for learning but has received little attention. To cope with the large intra-class variations in pedestrian images, we propose a novel training strategy named moderate positive mining to prevent the training process from over-fitting to the extreme samples in intra-class pairs. Experiments show that our approach significantly outperforms state-of-the-art methods on several benchmarks of person re-identification.

cs.CV↗

arXiv2015

A Fast and Accurate Unconstrained Face Detector

We propose a method to address challenges in unconstrained face detection, such as arbitrary pose variations and occlusions. First, a new image feature called Normalized Pixel Difference (NPD) is proposed. NPD feature is computed as the difference to sum ratio between two pixel values, inspired by the Weber Fraction in experimental psychology. The new feature is scale invariant, bounded, and is able to reconstruct the original image. Second, we propose a deep quadratic tree to learn the optimal subset of NPD features and their combinations, so that complex face manifolds can be partitioned by the learned rules. This way, only a single soft-cascade classifier is needed to handle unconstrained face detection. Furthermore, we show that the NPD features can be efficiently obtained from a look up table, and the detection template can be easily scaled, making the proposed face detector very fast. Experimental results on three public face datasets (FDDB, GENKI, and CMU-MIT) show that the proposed method achieves state-of-the-art performance in detecting unconstrained faces with arbitrary pose variations and occlusions in cluttered scenes.

cs.CV↗

arXiv2015

Person Re-identification by Local Maximal Occurrence Representation and Metric Learning

Person re-identification is an important technique towards automatic search of a person's presence in a surveillance video. Two fundamental problems are critical for person re-identification, feature representation and metric learning. An effective feature representation should be robust to illumination and viewpoint changes, and a discriminant metric should be learned to match various person images. In this paper, we propose an effective feature representation called Local Maximal Occurrence (LOMO), and a subspace and metric learning method called Cross-view Quadratic Discriminant Analysis (XQDA). The LOMO feature analyzes the horizontal occurrence of local features, and maximizes the occurrence to make a stable representation against viewpoint changes. Besides, to handle illumination variations, we apply the Retinex transform and a scale invariant texture operator. To learn a discriminant metric, we propose to learn a discriminant low dimensional subspace by cross-view quadratic discriminant analysis, and simultaneously, a QDA metric is learned on the derived subspace. We also present a practical computation method for XQDA, as well as its regularization. Experiments on four challenging person re-identification databases, VIPeR, QMUL GRID, CUHK Campus, and CUHK03, show that the proposed method improves the state-of-the-art rank-1 identification rates by 2.2%, 4.88%, 28.91%, and 31.55% on the four databases, respectively.

cs.CV↗

arXiv2014

Learning Face Representation from Scratch

Pushing by big data and deep convolutional neural network (CNN), the performance of face recognition is becoming comparable to human. Using private large scale training datasets, several groups achieve very high performance on LFW, i.e., 97% to 99%. While there are many open source implementations of CNN, none of large scale face dataset is publicly available. The current situation in the field of face recognition is that data is more important than algorithm. To solve this problem, this paper proposes a semi-automatical way to collect face images from Internet and builds a large scale dataset containing about 10,000 subjects and 500,000 images, called CASIAWebFace. Based on the database, we use a 11-layer CNN to learn discriminative representation and obtain state-of-theart accuracy on LFW and YTF. The publication of CASIAWebFace will attract more research groups entering this field and accelerate the development of face recognition in the wild.

cs.CV↗

arXiv2014

Open-set Person Re-identification

Person re-identification is becoming a hot research for developing both machine learning algorithms and video surveillance applications. The task of person re-identification is to determine which person in a gallery has the same identity to a probe image. This task basically assumes that the subject of the probe image belongs to the gallery, that is, the gallery contains this person. However, in practical applications such as searching a suspect in a video, this assumption is usually not true. In this paper, we consider the open-set person re-identification problem, which includes two sub-tasks, detection and identification. The detection sub-task is to determine the presence of the probe subject in the gallery, and the identification sub-task is to determine which person in the gallery has the same identity as the accepted probe. We present a database collected from a video surveillance setting of 6 cameras, with 200 persons and 7,413 images segmented. Based on this database, we develop a benchmark protocol for evaluating the performance under the open-set person re-identification scenario. Several popular metric learning algorithms for person re-identification have been evaluated as baselines. From the baseline performance, we observe that the open-set person re-identification problem is still largely unresolved, thus further attention and effort is needed.

cs.CV↗

arXiv2014

Shared Representation Learning for Heterogeneous Face Recognition

After intensive research, heterogenous face recognition is still a challenging problem. The main difficulties are owing to the complex relationship between heterogenous face image spaces. The heterogeneity is always tightly coupled with other variations, which makes the relationship of heterogenous face images highly nonlinear. Many excellent methods have been proposed to model the nonlinear relationship, but they apt to overfit to the training set, due to limited samples. Inspired by the unsupervised algorithms in deep learning, this paper proposes an novel framework for heterogeneous face recognition. We first extract Gabor features at some localized facial points, and then use Restricted Boltzmann Machines (RBMs) to learn a shared representation locally to remove the heterogeneity around each facial point. Finally, the shared representations of local RBMs are connected together and processed by PCA. Two problems (Sketch-Photo and NIR-VIS) and three databases are selected to evaluate the proposed method. For Sketch-Photo problem, we obtain perfect results on the CUFS database. For NIR-VIS problem, we produce new state-of-the-art performance on the CASIA HFB and NIR-VIS 2.0 databases.

cs.CV↗