arXiv subjects

Zhipeng Huang

Publications and source records attributed to Zhipeng Huang.

46 records · Page 3Linked to original sources

arXiv2022

Lifelong Unsupervised Domain Adaptive Person Re-identification with Coordinated Anti-forgetting and Adaptation

Unsupervised domain adaptive person re-identification (ReID) has been extensively investigated to mitigate the adverse effects of domain gaps. Those works assume the target domain data can be accessible all at once. However, for the real-world streaming data, this hinders the timely adaptation to changing data statistics and sufficient exploitation of increasing samples. In this paper, to address more practical scenarios, we propose a new task, Lifelong Unsupervised Domain Adaptive (LUDA) person ReID. This is challenging because it requires the model to continuously adapt to unlabeled data in the target environments while alleviating catastrophic forgetting for such a fine-grained person retrieval task. We design an effective scheme for this task, dubbed CLUDA-ReID, where the anti-forgetting is harmoniously coordinated with the adaptation. Specifically, a meta-based Coordinated Data Replay strategy is proposed to replay old data and update the network with a coordinated optimization direction for both adaptation and memorization. Moreover, we propose Relational Consistency Learning for old knowledge distillation/inheritance in line with the objective of retrieval-based tasks. We set up two evaluation settings to simulate the practical application scenarios. Extensive experiments demonstrate the effectiveness of our CLUDA-ReID for both scenarios with stationary target streams and scenarios with dynamic target streams.

cs.CV↗

arXiv2022

Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identification

Generalizable person re-identification aims to learn a model with only several labeled source domains that can perform well on unseen domains. Without access to the unseen domain, the feature statistics of the batch normalization (BN) layer learned from a limited number of source domains is doubtlessly biased for unseen domain. This would mislead the feature representation learning for unseen domain and deteriorate the generalizaiton ability of the model. In this paper, we propose a novel Debiased Batch Normalization via Gaussian Process approach (GDNorm) for generalizable person re-identification, which models the feature statistic estimation from BN layers as a dynamically self-refining Gaussian process to alleviate the bias to unseen domain for improving the generalization. Specifically, we establish a lightweight model with multiple set of domain-specific BN layers to capture the discriminability of individual source domain, and learn the corresponding parameters of the domain-specific BN layers. These parameters of different source domains are employed to deduce a Gaussian process. We randomly sample several paths from this Gaussian process served as the BN estimations of potential new domains outside of existing source domains, which can further optimize these learned parameters from source domains, and estimate more accurate Gaussian process by them in return, tending to real data distribution. Even without a large number of source domains, GDNorm can still provide debiased BN estimation by using the mean path of the Gaussian process, while maintaining low computational cost during testing. Extensive experiments demonstrate that our GDNorm effectively improves the generalization ability of the model on unseen domain.

cs.CV↗

arXiv2022

Modality-Adaptive Mixup and Invariant Decomposition for RGB-Infrared Person Re-Identification

RGB-infrared person re-identification is an emerging cross-modality re-identification task, which is very challenging due to significant modality discrepancy between RGB and infrared images. In this work, we propose a novel modality-adaptive mixup and invariant decomposition (MID) approach for RGB-infrared person re-identification towards learning modality-invariant and discriminative representations. MID designs a modality-adaptive mixup scheme to generate suitable mixed modality images between RGB and infrared images for mitigating the inherent modality discrepancy at the pixel-level. It formulates modality mixup procedure as Markov decision process, where an actor-critic agent learns dynamical and local linear interpolation policy between different regions of cross-modality images under a deep reinforcement learning framework. Such policy guarantees modality-invariance in a more continuous latent space and avoids manifold intrusion by the corrupted mixed modality samples. Moreover, to further counter modality discrepancy and enforce invariant visual semantics at the feature-level, MID employs modality-adaptive convolution decomposition to disassemble a regular convolution layer into modality-specific basis layers and a modality-shared coefficient layer. Extensive experimental results on two challenging benchmarks demonstrate superior performance of MID over state-of-the-art methods.

cs.CV↗

arXiv2021

Adaptive Domain-Specific Normalization for Generalizable Person Re-Identification

Although existing person re-identification (Re-ID) methods have shown impressive accuracy, most of them usually suffer from poor generalization on unseen target domain. Thus, generalizable person Re-ID has recently drawn increasing attention, which trains a model on source domains that generalizes well on unseen target domain without model updating. In this work, we propose a novel adaptive domain-specific normalization approach (AdsNorm) for generalizable person Re-ID. It describes unseen target domain as a combination of the known source ones, and explicitly learns domain-specific representation with target distribution to improve the model's generalization by a meta-learning pipeline. Specifically, AdsNorm utilizes batch normalization layers to collect individual source domains' characteristics, and maps source domains into a shared latent space by using these characteristics, where the domain relevance is measured by a distance function of different domain-specific normalization statistics and features. At the testing stage, AdsNorm projects images from unseen target domain into the same latent space, and adaptively integrates the domain-specific features carrying the source distributions by domain relevance for learning more generalizable aggregated representation on unseen target domain. Considering that target domain is unavailable during training, a meta-learning algorithm combined with a customized relation loss is proposed to optimize an effective and efficient ensemble model. Extensive experiments demonstrate that AdsNorm outperforms the state-of-the-art methods. The code is available at: https://github.com/hzphzp/AdsNorm.

cs.CV↗

arXiv2020

Quantum droplets in two-dimensional optical lattices

We study the stability of zero-vorticity and vortex lattice quantum droplets (LQDs), which are described by a two-dimensional (2D) Gross-Pitaevskii (GP) equation with a periodic potential and Lee-Huang-Yang (LHY) term. The LQDs are divided in two types: onsite-centered and offsitecentered LQDs, the centers of which are located at the minimum and the maximum of the potential, respectively. The stability areas of these two types of LQDs with different number of sites for zerovorticity and vorticity with S = 1 are given. We found that the u-N relationship of the stable LQDs with a fixed number of sites can violate the Vakhitov-Kolokolov (VK) criterion, which is a necessary stability condition for nonlinear modes with an attractive interaction. Moreover, the u-N relationship shows that two types of vortex LQDs with the same number of sites are degenerated, while the zero-vorticity LQDs are not degenerated. It is worth mentioning that the offsite-centered LQDs with zero-vorticity and vortex LQDs with S = 1 are heterogeneous.

nlin.PS↗

arXiv2018

Laser-induced acoustic desorption of thermally stable and unstable biomolecules

We evaluated the effect of the laser-induced acoustic desorption (LIAD) process on thermally stable and unstable biomolecules. We found that the thermally labile glycine molecule fragmented following desorption via LIAD, due to the production of hot molecules from the LIAD process. We furthermore observed a rise in translational temperature with increasing desorption laser intensity, while the forward velocity was invariant with respect to the desorption laser intensity for both glycine and adenine molecules. The forward kinetic energy was in the range of the surface stress energy, which supports the previously proposed stress-induced desorption model for the laser-induced acoustic desorption process.

physics.chem-ph↗

arXiv2018

Joint Embedding of Meta-Path and Meta-Graph for Heterogeneous Information Networks

Meta-graph is currently the most powerful tool for similarity search on heterogeneous information networks,where a meta-graph is a composition of meta-paths that captures the complex structural information. However, current relevance computing based on meta-graph only considers the complex structural information, but ignores its embedded meta-paths information. To address this problem, we proposeMEta-GrAph-based network embedding models, called MEGA and MEGA++, respectively. The MEGA model uses normalized relevance or similarity measures that are derived from a meta-graph and its embedded meta-paths between nodes simultaneously, and then leverages tensor decomposition method to perform node embedding. The MEGA++ further facilitates the use of coupled tensor-matrix decomposition method to obtain a joint embedding for nodes, which simultaneously considers the hidden relations of all meta information of a meta-graph.Extensive experiments on two real datasets demonstrate thatMEGA and MEGA++ are more effective than state-of-the-art approaches.

cs.SI↗

arXiv2018

Development and characterization of a laser-induced acoustic desorption source

A laser-induced acoustic desorption source, developed for use at central facilities, such as free-electron lasers, is presented. It features prolonged measurement times and a fixed interaction point. A novel sample deposition method using aerosol spraying provides a uniform sample coverage and hence stable signal intensity. Utilizing strong-field ionization as a universal detection scheme, the produced molecular plume is characterized in terms of number density, spatial extend, fragmentation, temporal distribution, translational velocity, and translational temperature. The effect of desorption laser intensity on these plume properties is evaluated. While translational velocity is invariant for different desorption laser intensities, pointing to a non-thermal desorption mechanism, the translational temperature increases significantly and higher fragmentation is observed with increased desorption laser fluence.

physics.chem-ph↗

arXiv2017

T-Crowd: Effective Crowdsourcing for Tabular Data

Crowdsourcing employs human workers to solve computer-hard problems, such as data cleaning, entity resolution, and sentiment analysis. When crowdsourcing tabular data, e.g., the attribute values of an entity set, a worker's answers on the different attributes (e.g., the nationality and age of a celebrity star) are often treated independently. This assumption is not always true and can lead to suboptimal crowdsourcing performance. In this paper, we present the T-Crowd system, which takes into consideration the intricate relationships among tasks, in order to converge faster to their true values. Particularly, T-Crowd integrates each worker's answers on different attributes to effectively learn his/her trustworthiness and the true data values. The attribute relationship information is also used to guide task allocation to workers. Finally, T-Crowd seamlessly supports categorical and continuous attributes, which are the two main datatypes found in typical databases. Our extensive experiments on real and synthetic datasets show that T-Crowd outperforms state-of-the-art methods in terms of truth inference and reducing the cost of crowdsourcing.

cs.DB↗

arXiv2017

Heterogeneous Information Network Embedding for Meta Path based Proximity

A network embedding is a representation of a large graph in a low-dimensional space, where vertices are modeled as vectors. The objective of a good embedding is to preserve the proximity between vertices in the original graph. This way, typical search and mining methods can be applied in the embedded space with the help of off-the-shelf multidimensional indexing approaches. Existing network embedding techniques focus on homogeneous networks, where all vertices are considered to belong to a single class.

cs.AI↗