arXiv subjects

Lei Qi

Publications and source records attributed to Lei Qi.

115 records · Page 7Linked to original sources

arXiv2020

Progressive Cross-camera Soft-label Learning for Semi-supervised Person Re-identification

In this paper, we focus on the semi-supervised person re-identification (Re-ID) case, which only has the intra-camera (within-camera) labels but not inter-camera (cross-camera) labels. In real-world applications, these intra-camera labels can be readily captured by tracking algorithms or few manual annotations, when compared with cross-camera labels. In this case, it is very difficult to explore the relationships between cross-camera persons in the training stage due to the lack of cross-camera label information. To deal with this issue, we propose a novel Progressive Cross-camera Soft-label Learning (PCSL) framework for the semi-supervised person Re-ID task, which can generate cross-camera soft-labels and utilize them to optimize the network. Concretely, we calculate an affinity matrix based on person-level features and adapt them to produce the similarities between cross-camera persons (i.e., cross-camera soft-labels). To exploit these soft-labels to train the network, we investigate the weighted cross-entropy loss and the weighted triplet loss from the classification and discrimination perspectives, respectively. Particularly, the proposed framework alternately generates progressive cross-camera soft-labels and gradually improves feature representations in the whole learning course. Extensive experiments on five large-scale benchmark datasets show that PCSL significantly outperforms the state-of-the-art unsupervised methods that employ labeled source domains or the images generated by the GAN-based models. Furthermore, the proposed method even has a competitive performance with respect to deep supervised Re-ID methods.

cs.CV↗

arXiv2019

Differentiable Meta-learning Model for Few-shot Semantic Segmentation

To address the annotation scarcity issue in some cases of semantic segmentation, there have been a few attempts to develop the segmentation model in the few-shot learning paradigm. However, most existing methods only focus on the traditional 1-way segmentation setting (i.e., one image only contains a single object). This is far away from practical semantic segmentation tasks where the K-way setting (K>1) is usually required by performing the accurate multi-object segmentation. To deal with this issue, we formulate the few-shot semantic segmentation task as a learning-based pixel classification problem and propose a novel framework called MetaSegNet based on meta-learning. In MetaSegNet, an architecture of embedding module consisting of the global and local feature branches is developed to extract the appropriate meta-knowledge for the few-shot segmentation. Moreover, we incorporate a linear model into MetaSegNet as a base learner to directly predict the label of each pixel for the multi-object segmentation. Furthermore, our MetaSegNet can be trained by the episodic training mechanism in an end-to-end manner from scratch. Experiments on two popular semantic segmentation datasets, i.e., PASCAL VOC and COCO, reveal the effectiveness of the proposed MetaSegNet in the K-way few-shot semantic segmentation task.

cs.CV↗

arXiv2019

A Novel Unsupervised Camera-aware Domain Adaptation Framework for Person Re-identification

Unsupervised cross-domain person re-identification (Re-ID) faces two key issues. One is the data distribution discrepancy between source and target domains, and the other is the lack of labelling information in target domain. They are addressed in this paper from the perspective of representation learning. For the first issue, we highlight the presence of camera-level sub-domains as a unique characteristic of person Re-ID, and develop camera-aware domain adaptation to reduce the discrepancy not only between source and target domains but also across these sub-domains. For the second issue, we exploit the temporal continuity in each camera of target domain to create discriminative information. This is implemented by dynamically generating online triplets within each batch, in order to maximally take advantage of the steadily improved feature representation in training process. Together, the above two methods give rise to a novel unsupervised deep domain adaptation framework for person Re-ID. Experiments and ablation studies on benchmark datasets demonstrate its superiority and interesting properties.

cs.CV↗

arXiv2019

A Novel Bi-hemispheric Discrepancy Model for EEG Emotion Recognition

The neuroscience study has revealed the discrepancy of emotion expression between left and right hemispheres of human brain. Inspired by this study, in this paper, we propose a novel bi-hemispheric discrepancy model (BiHDM) to learn the asymmetric differences between two hemispheres for electroencephalograph (EEG) emotion recognition. Concretely, we first employ four directed recurrent neural networks (RNNs) based on two spatial orientations to traverse electrode signals on two separate brain regions, which enables the model to obtain the deep representations of all the EEG electrodes' signals while keeping the intrinsic spatial dependence. Then we design a pairwise subnetwork to capture the discrepancy information between two hemispheres and extract higher-level features for final classification. Besides, in order to reduce the domain shift between training and testing data, we use a domain discriminator that adversarially induces the overall feature learning module to generate emotion-related but domain-invariant feature, which can further promote EEG emotion recognition. We conduct experiments on three public EEG emotional datasets, and the experiments show that the new state-of-the-art results can be achieved.

q-bio.NC↗

arXiv2019

MaskReID: A Mask Based Deep Ranking Neural Network for Person Re-identification

Person retrieval faces many challenges including cluttered background, appearance variations (e.g., illumination, pose, occlusion) among different camera views and the similarity among different person's images. To address these issues, we put forward a novel mask based deep ranking neural network with a skipped fusing layer. Firstly, to alleviate the problem of cluttered background, masked images with only the foreground regions are incorporated as input in the proposed neural network. Secondly, to reduce the impact of the appearance variations, the multi-layer fusion scheme is developed to obtain more discriminative fine-grained information. Lastly, considering person retrieval is a special image retrieval task, we propose a novel ranking loss to optimize the whole network. The proposed ranking loss can further mitigate the interference problem of similar negative samples when producing ranking results. The extensive experiments validate the superiority of the proposed method compared with the state-of-the-art methods on many benchmark datasets.

cs.CV↗

arXiv2018

Asymmetric viscothermal acoustic propagation and implication on flow measurement

In the application of high frequency acoustic flow measurement, viscothermal dissipation and asymmetric acoustic modes cannot be overlooked. Present paper mathematically formulates asymmetric linear disturbance dynamics in terms of velocity and temperature disturbances based on the conservations of mass, momentum and energy. An iterative calculation procedure, which is similar to Galerkin method, is presented. Numerical analysis of asymmetric acoustic features (phase velocity and attenuation coefficient) are comprehensively given under the effects of viscothermal dissipation and shear flow convection. In the end, flow measurement performance of asymmetric acoustic modes is literally discussed. Numerical study shows that viscothermal dissipation affects the cut-on frequency of acoustic modes and couples nonlinearly with shear convection when the flow Mach number is large. These parameters impose significant influences on measurement performance. Each acoustic mode has inherent measurement derivation which can be theoretically used to compensate the acoustic flow measurement error. Apparent prediction error may occur if the viscothermal dissipation is taken out of consideration

physics.flu-dyn↗

arXiv2010

Non-Gaussian Quasi Maximum Likelihood Estimation of GARCH Models

The non-Gaussian quasi maximum likelihood estimator is frequently used in GARCH models with intension to improve the efficiency of the GARCH parameters. However, unless the quasi-likelihood happens to be the true one, non-Gaussian QMLE methods suffers inconsistency even if shape parameters in the quasi-likelihood are estimated. To correct this bias, we identify an unknown scale parameter that is critical to the consistent estimation of non-Gaussian QMLE, and propose a two-step non-Gaussian QMLE (2SNG-QMLE) for estimation of the scale parameter and GARCH parameters. This novel approach is consistent and asymptotically normal. Moreover, it has higher efficiency than the Gaussian QMLE, particularly when the innovation error has heavy tails. Two extensions are proposed to further improve the efficiency of 2SNG-QMLE. The impact of relative heaviness of tails of the innovation and quasi-likelihood distributions on the asymptotic efficiency has been thoroughly investigated. Monte Carlo simulations and an empirical study confirm the advantages of the proposed approach.

stat.ME↗