arXiv subjects

Yanning Zhang

Publications and source records attributed to Yanning Zhang.

At least 181 records · Page 10Linked to original sources

arXiv2021

Pluggable Weakly-Supervised Cross-View Learning for Accurate Vehicle Re-Identification

Learning cross-view consistent feature representation is the key for accurate vehicle Re-identification (ReID), since the visual appearance of vehicles changes significantly under different viewpoints. To this end, most existing approaches resort to the supervised cross-view learning using extensive extra viewpoints annotations, which however, is difficult to deploy in real applications due to the expensive labelling cost and the continous viewpoint variation that makes it hard to define discrete viewpoint labels. In this study, we present a pluggable Weakly-supervised Cross-View Learning (WCVL) module for vehicle ReID. Through hallucinating the cross-view samples as the hardest positive counterparts in feature domain, we can learn the consistent feature representation via minimizing the cross-view feature distance based on vehicle IDs only without using any viewpoint annotation. More importantly, the proposed method can be seamlessly plugged into most existing vehicle ReID baselines for cross-view learning without re-training the baselines. To demonstrate its efficacy, we plug the proposed method into a bunch of off-the-shelf baselines and obtain significant performance improvement on four public benchmark datasets, i.e., VeRi-776, VehicleID, VRIC and VRAI.

cs.CV↗

arXiv2021

Learning Depth via Leveraging Semantics: Self-supervised Monocular Depth Estimation with Both Implicit and Explicit Semantic Guidance

Self-supervised depth estimation has made a great success in learning depth from unlabeled image sequences. While the mappings between image and pixel-wise depth are well-studied in current methods, the correlation between image, depth and scene semantics, however, is less considered. This hinders the network to better understand the real geometry of the scene, since the contextual clues, contribute not only the latent representations of scene depth, but also the straight constraints for depth map. In this paper, we leverage the two benefits by proposing the implicit and explicit semantic guidance for accurate self-supervised depth estimation. We propose a Semantic-aware Spatial Feature Alignment (SSFA) scheme to effectively align implicit semantic features with depth features for scene-aware depth estimation. We also propose a semantic-guided ranking loss to explicitly constrain the estimated depth maps to be consistent with real scene contextual properties. Both semantic label noise and prediction uncertainty is considered to yield reliable depth supervisions. Extensive experimental results show that our method produces high quality depth maps which are consistently superior either on complex scenes or diverse semantic categories, and outperforms the state-of-the-art methods by a significant margin.

cs.CV↗

arXiv2021

Non-uniform Motion Deblurring with Blurry Component Divided Guidance

Blind image deblurring is a fundamental and challenging computer vision problem, which aims to recover both the blur kernel and the latent sharp image from only a blurry observation. Despite the superiority of deep learning methods in image deblurring have displayed, there still exists major challenge with various non-uniform motion blur. Previous methods simply take all the image features as the input to the decoder, which handles different degrees (e.g. large blur, small blur) simultaneously, leading to challenges for sharp image generation. To tackle the above problems, we present a deep two-branch network to deal with blurry images via a component divided module, which divides an image into two components based on the representation of blurry degree. Specifically, two component attentive blocks are employed to learn attention maps to exploit useful deblurring feature representations on both large and small blurry regions. Then, the blur-aware features are fed into two-branch reconstruction decoders respectively. In addition, a new feature fusion mechanism, orientation-based feature fusion, is proposed to merge sharp features of the two branches. Both qualitative and quantitative experimental results show that our method performs favorably against the state-of-the-art approaches.

cs.CV↗

arXiv2020

Semantic-Guided Representation Enhancement for Self-supervised Monocular Trained Depth Estimation

Self-supervised depth estimation has shown its great effectiveness in producing high quality depth maps given only image sequences as input. However, its performance usually drops when estimating on border areas or objects with thin structures due to the limited depth representation ability. In this paper, we address this problem by proposing a semantic-guided depth representation enhancement method, which promotes both local and global depth feature representations by leveraging rich contextual information. In stead of a single depth network as used in conventional paradigms, we propose an extra semantic segmentation branch to offer extra contextual features for depth estimation. Based on this framework, we enhance the local feature representation by sampling and feeding the point-based features that locate on the semantic edges to an individual Semantic-guided Edge Enhancement module (SEEM), which is specifically designed for promoting depth estimation on the challenging semantic borders. Then, we improve the global feature representation by proposing a semantic-guided multi-level attention mechanism, which enhances the semantic and depth features by exploring pixel-wise correlations in the multi-level depth decoding scheme. Extensive experiments validate the distinct superiority of our method in capturing highly accurate depth on the challenging image areas such as semantic category borders and thin objects. Both quantitative and qualitative experiments on KITTI show that our method outperforms the state-of-the-art methods.

cs.CV↗

arXiv2020

Meta-Generating Deep Attentive Metric for Few-shot Classification

Learning to generate a task-aware base learner proves a promising direction to deal with few-shot learning (FSL) problem. Existing methods mainly focus on generating an embedding model utilized with a fixed metric (eg, cosine distance) for nearest neighbour classification or directly generating a linear classier. However, due to the limited discriminative capacity of such a simple metric or classifier, these methods fail to generalize to challenging cases appropriately. To mitigate this problem, we present a novel deep metric meta-generation method that turns to an orthogonal direction, ie, learning to adaptively generate a specific metric for a new FSL task based on the task description (eg, a few labelled samples). In this study, we structure the metric using a three-layer deep attentive network that is flexible enough to produce a discriminative metric for each task. Moreover, different from existing methods that utilize an uni-modal weight distribution conditioned on labelled samples for network generation, the proposed meta-learner establishes a multi-modal weight distribution conditioned on cross-class sample pairs using a tailored variational autoencoder, which can separately capture the specific inter-class discrepancy statistics for each class and jointly embed the statistics for all classes into metric generation. By doing this, the generated metric can be appropriately adapted to a new FSL task with pleasing generalization performance. To demonstrate this, we test the proposed method on four benchmark FSL datasets and gain surprisingly obvious performance improvement over state-of-the-art competitors, especially in the challenging cases, eg, improve the accuracy from 26.14% to 46.69% in the 20-way 1-shot task on miniImageNet, while improve the accuracy from 45.2% to 68.72% in the 5-way 1-shot task on FC100. Code is available: https://github.com/NWPUZhoufei/DAM.

cs.CV↗

arXiv2020

Unsupervised Alternating Optimization for Blind Hyperspectral Imagery Super-resolution

Despite the great success of deep model on Hyperspectral imagery (HSI) super-resolution(SR) for simulated data, most of them function unsatisfactory when applied to the real data, especially for unsupervised HSI SR methods. One of the main reason comes from the fact that the predefined degeneration models (e.g. blur in spatial domain) utilized by most HSI SR methods often exist great discrepancy with the real one, which results in these deep models overfit and ultimately degrade their performance on real data. To well mitigate such a problem, we explore the unsupervised blind HSI SR method. Specifically, we investigate how to effectively obtain the degeneration models in spatial and spectral domain, respectively, and makes them can well compatible with the fusion based SR reconstruction model. To this end, we first propose an alternating optimization based deep framework to estimate the degeneration models and reconstruct the latent image, with which the degeneration models estimation and HSI reconstruction can mutually promotes each other. Then, a meta-learning based mechanism is further proposed to pre-train the network, which can effectively improve the speed and generalization ability adapting to different complex degeneration. Experiments on three benchmark HSI SR datasets report an excellent superiority of the proposed method on handling blind HSI fusion problem over other competing methods.

eess.IV↗

arXiv2020

On Efficient and Robust Metrics for RANSAC Hypotheses and 3D Rigid Registration

This paper focuses on developing efficient and robust evaluation metrics for RANSAC hypotheses to achieve accurate 3D rigid registration. Estimating six-degree-of-freedom (6-DoF) pose from feature correspondences remains a popular approach to 3D rigid registration, where random sample consensus (RANSAC) is a de-facto choice to this problem. However, existing metrics for RANSAC hypotheses are either time-consuming or sensitive to common nuisances, parameter variations, and different application scenarios, resulting in performance deterioration in overall registration accuracy and speed. We alleviate this problem by first analyzing the contributions of inliers and outliers, and then proposing several efficient and robust metrics with different designing motivations for RANSAC hypotheses. Comparative experiments on four standard datasets with different nuisances and application scenarios verify that the proposed metrics can significantly improve the registration performance and are more robust than several state-of-the-art competitors, making them good gifts to practical applications. This work also draws an interesting conclusion, i.e., not all inliers are equal while all outliers should be equal, which may shed new light on this research problem.

cs.CV↗

arXiv2020

Where to Look and How to Describe: Fashion Image Retrieval with an Attentional Heterogeneous Bilinear Network

Fashion products typically feature in compositions of a variety of styles at different clothing parts. In order to distinguish images of different fashion products, we need to extract both appearance (i.e., "how to describe") and localization (i.e.,"where to look") information, and their interactions. To this end, we propose a biologically inspired framework for image-based fashion product retrieval, which mimics the hypothesized twostream visual processing system of human brain. The proposed attentional heterogeneous bilinear network (AHBN) consists of two branches: a deep CNN branch to extract fine-grained appearance attributes and a fully convolutional branch to extract landmark localization information. A joint channel-wise attention mechanism is further applied to the extracted heterogeneous features to focus on important channels, followed by a compact bilinear pooling layer to model the interaction of the two streams. Our proposed framework achieves satisfactory performance on three image-based fashion product retrieval benchmarks.

cs.CV↗

arXiv2020

Few-shot Action Recognition with Implicit Temporal Alignment and Pair Similarity Optimization

Few-shot learning aims to recognize instances from novel classes with few labeled samples, which has great value in research and application. Although there has been a lot of work in this area recently, most of the existing work is based on image classification tasks. Video-based few-shot action recognition has not been explored well and remains challenging: 1) the differences of implementation details among different papers make a fair comparison difficult; 2) the wide variations and misalignment of temporal sequences make the video-level similarity comparison difficult; 3) the scarcity of labeled data makes the optimization difficult. To solve these problems, this paper presents 1) a specific setting to evaluate the performance of few-shot action recognition algorithms; 2) an implicit sequence-alignment algorithm for better video-level similarity comparison; 3) an advanced loss for few-shot learning to optimize pair similarity with limited data. Specifically, we propose a novel few-shot action recognition framework that uses long short-term memory following 3D convolutional layers for sequence modeling and alignment. Circle loss is introduced to maximize the within-class similarity and minimize the between-class similarity flexibly towards a more definite convergence target. Instead of using random or ambiguous experimental settings, we set a concrete criterion analogous to the standard image-based few-shot learning setting for few-shot action recognition evaluation. Extensive experiments on two datasets demonstrate the effectiveness of our proposed method.

cs.CV↗

arXiv2020

AE-Netv2: Optimization of Image Fusion Efficiency and Network Architecture

Existing image fusion methods pay few research attention to image fusion efficiency and network architecture. However, the efficiency and accuracy of image fusion has an important impact in practical applications. To solve this problem, we propose an \textit{efficient autonomous evolution image fusion method, dubed by AE-Netv2}. Different from other image fusion methods based on deep learning, AE-Netv2 is inspired by human brain cognitive mechanism. Firstly, we discuss the influence of different network architecture on image fusion quality and fusion efficiency, which provides a reference for the design of image fusion architecture. Secondly, we explore the influence of pooling layer on image fusion task and propose an image fusion method with pooling layer. Finally, we explore the commonness and characteristics of different image fusion tasks, which provides a research basis for further research on the continuous learning characteristics of human brain in the field of image fusion. Comprehensive experiments demonstrate the superiority of AE-Netv2 compared with state-of-the-art methods in different fusion tasks at a real time speed of 100+ FPS on GTX 2070. Among all tested methods based on deep learning, AE-Netv2 has the faster speed, the smaller model size and the better robustness.

cs.CV↗

arXiv2020

3D Correspondence Grouping with Compatibility Features

We present a simple yet effective method for 3D correspondence grouping. The objective is to accurately classify initial correspondences obtained by matching local geometric descriptors into inliers and outliers. Although the spatial distribution of correspondences is irregular, inliers are expected to be geometrically compatible with each other. Based on such observation, we propose a novel representation for 3D correspondences, dubbed compatibility feature (CF), to describe the consistencies within inliers and inconsistencies within outliers. CF consists of top-ranked compatibility scores of a candidate to other correspondences, which purely relies on robust and rotation-invariant geometric constraints. We then formulate the grouping problem as a classification problem for CF features, which is accomplished via a simple multilayer perceptron (MLP) network. Comparisons with nine state-of-the-art methods on four benchmarks demonstrate that: 1) CF is distinctive, robust, and rotation-invariant; 2) our CF-based method achieves the best overall performance and holds good generalization ability.

cs.CV↗

arXiv2020

AE-Net: Autonomous Evolution Image Fusion Method Inspired by Human Cognitive Mechanism

In order to solve the robustness and generality problems of the image fusion task,inspired by the human brain cognitive mechanism, we propose a robust and general image fusion method with autonomous evolution ability, and is therefore denoted with AE-Net. Through the collaborative optimization of multiple image fusion methods to simulate the cognitive process of human brain, unsupervised learning image fusion task can be transformed into semi-supervised image fusion task or supervised image fusion task, thus promoting the evolutionary ability of network model weight. Firstly, the relationship between human brain cognitive mechanism and image fusion task is analyzed and a physical model is established to simulate human brain cognitive mechanism. Secondly, we analyze existing image fusion methods and image fusion loss functions, select the image fusion method with complementary features to construct the algorithm module, establish the multi-loss joint evaluation function to obtain the optimal solution of algorithm module. The optimal solution of each image is used to guide the weight training of network model. Our image fusion method can effectively unify the cross-modal image fusion task and the same modal image fusion task, and effectively overcome the difference of data distribution between different datasets. Finally, extensive numerical results verify the effectiveness and superiority of our method on a variety of image fusion datasets, including multi-focus dataset, infrared and visi-ble dataset, medical image dataset and multi-exposure dataset. Comprehensive experiments demonstrate the superiority of our image fusion method in robustness and generality. In addition, experimental results also demonstate the effectiveness of human brain cognitive mechanism to improve the robustness and generality of image fusion.

cs.CV↗

arXiv2020

IllumiNet: Transferring Illumination from Planar Surfaces to Virtual Objects in Augmented Reality

This paper presents an illumination estimation method for virtual objects in real environment by learning. While previous works tackled this problem by reconstructing high dynamic range (HDR) environment maps or the corresponding spherical harmonics, we do not seek to recover the lighting environment of the entire scene. Given a single RGB image, our method directly infers the relit virtual object by transferring the illumination features extracted from planar surfaces in the scene to the desired geometries. Compared to previous works, our approach is more robust as it works in both indoor and outdoor environments with spatially-varying illumination. Experiments and evaluation results show that our approach outperforms the state-of-the-art quantitatively and qualitatively, achieving realistic augmented experience.

cs.CV↗

arXiv2020

Non-linear and Selective Fusion of Cross-Modal Images

The human visual perception system has strong robustness in image fusion. This robustness is based on human visual perception system's characteristics of feature selection and non-linear fusion of different features. In order to simulate the human visual perception mechanism in image fusion tasks, we propose a multi-source image fusion framework that combines illuminance factors and attention mechanisms. The framework effectively combines traditional image features and modern deep learning features. First, we perform multi-scale decomposition of multi-source images. Then, the visual saliency map and the deep feature map are combined with the illuminance fusion factor to perform high-low frequency nonlinear fusion. Secondly, the characteristics of high and low frequency fusion are selected through the channel attention network to obtain the final fusion map. By simulating the nonlinear characteristics and selection characteristics of the human visual perception system in image fusion, the fused image is more in line with the human visual perception mechanism. Finally, we validate our fusion framework on public datasets of infrared and visible images, medical images and multi-focus images. The experimental results demonstrate the superiority of our fusion framework over state-of-arts in visual quality, objective fusion metrics and robustness.

cs.CV↗

arXiv2020

A Cross-Modal Image Fusion Method Guided by Human Visual Characteristics

The characteristics of feature selection, nonlinear combination and multi-task auxiliary learning mechanism of the human visual perception system play an important role in real-world scenarios, but the research of image fusion theory based on the characteristics of human visual perception is less. Inspired by the characteristics of human visual perception, we propose a robust multi-task auxiliary learning optimization image fusion theory. Firstly, we combine channel attention model with nonlinear convolutional neural network to select features and fuse nonlinear features. Then, we analyze the impact of the existing image fusion loss on the image fusion quality, and establish the multi-loss function model of unsupervised learning network. Secondly, aiming at the multi-task auxiliary learning mechanism of human visual perception system, we study the influence of multi-task auxiliary learning mechanism on image fusion task on the basis of single task multi-loss network model. By simulating the three characteristics of human visual perception system, the fused image is more consistent with the mechanism of human brain image fusion. Finally, in order to verify the superiority of our algorithm, we carried out experiments on the combined vision system image data set, and extended our algorithm to the infrared and visible image and the multi-focus image public data set for experimental verification. The experimental results demonstrate the superiority of our fusion theory over state-of-arts in generality and robustness.

cs.CV↗

arXiv2020

A Robust Attentional Framework for License Plate Recognition in the Wild

Recognizing car license plates in natural scene images is an important yet still challenging task in realistic applications. Many existing approaches perform well for license plates collected under constrained conditions, eg, shooting in frontal and horizontal view-angles and under good lighting conditions. However, their performance drops significantly in an unconstrained environment that features rotation, distortion, occlusion, blurring, shading or extreme dark or bright conditions. In this work, we propose a robust framework for license plate recognition in the wild. It is composed of a tailored CycleGAN model for license plate image generation and an elaborate designed image-to-sequence network for plate recognition. On one hand, the CycleGAN based plate generation engine alleviates the exhausting human annotation work. Massive amount of training data can be obtained with a more balanced character distribution and various shooting conditions, which helps to boost the recognition accuracy to a large extent. On the other hand, the 2D attentional based license plate recognizer with an Xception-based CNN encoder is capable of recognizing license plates with different patterns under various scenarios accurately and robustly. Without using any heuristics rule or post-processing, our method achieves the state-of-the-art performance on four public datasets, which demonstrates the generality and robustness of our framework. Moreover, we released a new license plate dataset, named "CLPD", with 1200 images from all 31 provinces in mainland China. The dataset can be available from: https://github.com/wangpengnorman/CLPD_dataset.

cs.CV↗

arXiv2020

Attention-based network for low-light image enhancement

The captured images under low light conditions often suffer insufficient brightness and notorious noise. Hence, low-light image enhancement is a key challenging task in computer vision. A variety of methods have been proposed for this task, but these methods often failed in an extreme low-light environment and amplified the underlying noise in the input image. To address such a difficult problem, this paper presents a novel attention-based neural network to generate high-quality enhanced low-light images from the raw sensor data. Specifically, we first employ attention strategy (i.e. channel attention and spatial attention modules) to suppress undesired chromatic aberration and noise. The channel attention module guides the network to refine redundant colour features. The spatial attention module focuses on denoising by taking advantage of the non-local correlation in the image. Furthermore, we propose a new pooling layer, called inverted shuffle layer, which adaptively selects useful information from previous features. Extensive experiments demonstrate the superiority of the proposed network in terms of suppressing the chromatic aberration and noise artifacts in enhancement, especially when the low-light image has severe noise.

eess.IV↗

arXiv2020

Person Re-identification in Aerial Imagery

Nowadays, with the rapid development of consumer Unmanned Aerial Vehicles (UAVs), visual surveillance by utilizing the UAV platform has been very attractive. Most of the research works for UAV captured visual data are mainly focused on the tasks of object detection and tracking. However, limited attention has been paid to the task of person Re-identification (ReID) which has been widely studied in ordinary surveillance cameras with fixed emplacements. In this paper, to facilitate the research of person ReID in aerial imagery, we collect a large scale airborne person ReID dataset named as Person ReID for Aerial Imagery (PRAI-1581), which consists of 39,461 images of 1581 person identities. The images of the dataset are shot by two DJI consumer UAVs flying at an altitude ranging from 20 to 60 meters above the ground, which covers most of the real UAV surveillance scenarios. In addition, we propose to utilize subspace pooling of convolution feature maps to represent the input person images. Our method can learn a discriminative and compact feature representation for ReID in aerial imagery and can be trained in an end-to-end fashion efficiently. We conduct extensive experiments on the proposed dataset and the experimental results demonstrate that re-identify persons in aerial imagery is a challenging problem, where our method performs favorably against state of the arts. Our dataset can be accessed via \url{https://github.com/stormyoung/PRAI-1581}.

cs.CV↗