arXiv subjects

Jialun Liu

Publications and source records attributed to Jialun Liu.

27 records · Page 2Linked to original sources

arXiv2024

Electric Field Driven Domain Wall Dynamics in BaTiO3 Nanoparticles

We report a detailed investigation into the response of single BaTiO3 (BTO) nanocrystals under applied electric fields (E-field) using Bragg Coherent Diffraction Imaging (BCDI). Our study reveals pronounced domain wall migration and expansion of a sample measure in situ under applied electric field. The changes are most prominent at the surface of the nanocrystal, where the lack of external strain allows greater domain wall mobility. The observed domain shifts are correlated to the strength and orientation of the applied E-field, following a side-by-side domain model from Suzana et al. Notably, we identified a critical voltage threshold at +10 V, which leads to irreversible structural changes, suggesting plastic deformation. The findings highlight how surface effects and intrinsic defects contribute to the enhanced dielectric properties of BTO at the nanoscale, in contrast to bulk materials, where strain limits domain mobility. These findings deepen our understanding of nanoscale dielectric behaviour and inform the design of advanced nanoelectronic devices.

cond-mat.mtrl-sci↗

arXiv2024

PRG: Prompt-Based Distillation Without Annotation via Proxy Relational Graph

In this paper, we propose a new distillation method for extracting knowledge from Large Foundation Models (LFM) into lightweight models, introducing a novel supervision mode that does not require manually annotated data. While LFMs exhibit exceptional zero-shot classification abilities across datasets, relying solely on LFM-generated embeddings for distillation poses two main challenges: LFM's task-irrelevant knowledge and the high density of features. The transfer of task-irrelevant knowledge could compromise the student model's discriminative capabilities, and the high density of features within target domains obstructs the extraction of discriminative knowledge essential for the task. To address this issue, we introduce the Proxy Relational Graph (PRG) method. We initially extract task-relevant knowledge from LFMs by calculating a weighted average of logits obtained through text prompt embeddings. Then we construct sample-class proxy graphs for LFM and student models, respectively, to model the correlation between samples and class proxies. Then, we achieve the distillation of selective knowledge by aligning the relational graphs produced by both the LFM and the student model. Specifically, the distillation from LFM to the student model is achieved through two types of alignment: 1) aligning the sample nodes produced by the student model with those produced by the LFM, and 2) aligning the edge relationships in the student model's graph with those in the LFM's graph. Our experimental results validate the effectiveness of PRG, demonstrating its ability to leverage the extensive knowledge base of LFMs while skillfully circumventing their inherent limitations in focused learning scenarios. Notably, in our annotation-free framework, PRG achieves an accuracy of 76.23\% (T: 77.9\%) on CIFAR-100 and 72.44\% (T: 75.3\%) on the ImageNet-1K.

cs.CV↗

arXiv2024

TexRO: Generating Delicate Textures of 3D Models by Recursive Optimization

This paper presents TexRO, a novel method for generating delicate textures of a known 3D mesh by optimizing its UV texture. The key contributions are two-fold. We propose an optimal viewpoint selection strategy, that finds the most miniature set of viewpoints covering all the faces of a mesh. Our viewpoint selection strategy guarantees the completeness of a generated result. We propose a recursive optimization pipeline that optimizes a UV texture at increasing resolutions, with an adaptive denoising method that re-uses existing textures for new texture generation. Through extensive experimentation, we demonstrate the superior performance of TexRO in terms of texture quality, detail preservation, visual consistency, and, notably runtime speed, outperforming other current methods. The broad applicability of TexRO is further confirmed through its successful use on diverse 3D models.

cs.CV↗

arXiv2024

GVA: Reconstructing Vivid 3D Gaussian Avatars from Monocular Videos

In this paper, we present a novel method that facilitates the creation of vivid 3D Gaussian avatars from monocular video inputs (GVA). Our innovation lies in addressing the intricate challenges of delivering high-fidelity human body reconstructions and aligning 3D Gaussians with human skin surfaces accurately. The key contributions of this paper are twofold. Firstly, we introduce a pose refinement technique to improve hand and foot pose accuracy by aligning normal maps and silhouettes. Precise pose is crucial for correct shape and appearance reconstruction. Secondly, we address the problems of unbalanced aggregation and initialization bias that previously diminished the quality of 3D Gaussian avatars, through a novel surface-guided re-initialization method that ensures accurate alignment of 3D Gaussian points with avatar surfaces. Experimental results demonstrate that our proposed method achieves high-fidelity and vivid 3D Gaussian avatar reconstruction. Extensive experimental analyses validate the performance qualitatively and quantitatively, demonstrating that it achieves state-of-the-art performance in photo-realistic novel view synthesis while offering fine-grained control over the human body and hand pose. Project page: https://3d-aigc.github.io/GVA/.

cs.CV↗

arXiv2023

A novel model-based parameters estimation combining local optimization and global optimization of nonlinear ship models with physical experiment dataset

Designing an autonomous precise controller for ships requires accurate and reliable ship models, including the ship dynamic model and actuator model. However, selecting a suitable model for controller design and determining its parameters pose a significant challenge, considering factors such as ship actuation, input constraints, environmental disturbances, and others. This challenge is further amplified for underactuated ships, as obtaining decoupled experiment data is not feasible, and the limited data available may not adequately represent the motion characteristics of ships. To address this issue, we propose a novel model-based parameter estimation approach, called MBPE-LOGO, for underactuated ship motion models. This method combines local optimization and global optimization methods to solve the model identification problem using a dataset generated from real experiments. The effectiveness of the identified model is verified through extensive comparisons of different trajectories and prediction steps.

math.OC↗

arXiv2021

Memory-based Jitter: Improving Visual Recognition on Long-tailed Data with Diversity In Memory

This paper considers deep visual recognition on long-tailed data. To be general, we consider two applied scenarios, \ie, deep classification and deep metric learning. Under the long-tailed data distribution, the majority classes (\ie, tail classes) only occupy relatively few samples and are prone to lack of within-class diversity. A radical solution is to augment the tail classes with higher diversity. To this end, we introduce a simple and reliable method named Memory-based Jitter (MBJ). We observe that during training, the deep model constantly changes its parameters after every iteration, yielding the phenomenon of \emph{weight jitters}. Consequentially, given a same image as the input, two historical editions of the model generate two different features in the deeply-embedded space, resulting in \emph{feature jitters}. Using a memory bank, we collect these (model or feature) jitters across multiple training iterations and get the so-called Memory-based Jitter. The accumulated jitters enhance the within-class diversity for the tail classes and consequentially improves long-tailed visual recognition. With slight modifications, MBJ is applicable for two fundamental visual recognition tasks, \emph{i.e.}, deep image classification and deep metric learning (on long-tailed data). Extensive experiments on five long-tailed classification benchmarks and two deep metric learning benchmarks demonstrate significant improvement. Moreover, the achieved performance are on par with the state of the art on both tasks.

cs.CV↗

arXiv2020

Deep Representation Learning on Long-tailed Data: A Learnable Embedding Augmentation Perspective

This paper considers learning deep features from long-tailed data. We observe that in the deep feature space, the head classes and the tail classes present different distribution patterns. The head classes have a relatively large spatial span, while the tail classes have significantly small spatial span, due to the lack of intra-class diversity. This uneven distribution between head and tail classes distorts the overall feature space, which compromises the discriminative ability of the learned features. Intuitively, we seek to expand the distribution of the tail classes by transferring from the head classes, so as to alleviate the distortion of the feature space. To this end, we propose to construct each feature into a "feature cloud". If a sample belongs to a tail class, the corresponding feature cloud will have relatively large distribution range, in compensation to its lack of diversity. It allows each tail sample to push the samples from other classes far away, recovering the intra-class diversity of tail classes. Extensive experimental evaluations on person re-identification and face recognition tasks confirm the effectiveness of our method.

cs.CV↗

arXiv2018

Identity Preserving Generative Adversarial Network for Cross-Domain Person Re-identification

Person re-identification is to retrieval pedestrian images from no-overlap camera views detected by pedestrian detectors. Most existing person re-identification (re-ID) models often fail to generalize well from the source domain where the models are trained to a new target domain without labels, because of the bias between the source and target domain. This issue significantly limits the scalability and usability of the models in the real world. Providing a labeled source training set and an unlabeled target training set, the aim of this paper is to improve the generalization ability of re-ID models to the target domain. To this end, we propose an image generative network named identity preserving generative adversarial network (IPGAN). The proposed method has two excellent properties: 1) only a single model is employed to translate the labeled images from the source domain to the target camera domains in an unsupervised manner; 2) The identity information of images from the source domain is preserved before and after translation. Furthermore, we propose IBN-reID model for the person re-identification task. It has better generalization ability than baseline models, especially in the cases without any domain adaptation. The IBN-reID model is trained on the translated images by supervised methods. Experimental results on Market-1501 and DukeMTMC-reID show that the images generated by IPGAN are more suitable for cross-domain person re-identification. Very competitive re-ID accuracy is achieved by our method.

cs.CV↗

arXiv2017

Thermal Sublimation: a Scalable and Controllable Thinning Method for the Fabrication of Few-Layer Black Phosphorus

In this work, we reported uniform layer-by-layer sublimation of black phosphorus under heating below 600 K. The uniformity and crystallinity of BP samples after thermal thinning were confirmed by Raman spectra and 2D Raman imaging. A uniform and crystalline bilayer black phosphorus flake with an area of 180 um^2 was prepared with this method. No micron scale defects were observed. The sublimation rate of BP was around 0.18 nm / min at 500 K and 1.5 nm / min at 550 K. Both room and high temperature Raman peak intensity ratio Si/A2g vs. BP thickness relations were established for in-situ thickness determination. The sublimation thinning method was shown to be a controllable and scalable approach to prepare few-layer black phosphorus.

cond-mat.mtrl-sci↗