arXiv subjects

Qian He

Publications and source records attributed to Qian He.

At least 73 records · Page 4Linked to original sources

arXiv2023

DreamTuner: Single Image is Enough for Subject-Driven Generation

Diffusion-based models have demonstrated impressive capabilities for text-to-image generation and are expected for personalized applications of subject-driven generation, which require the generation of customized concepts with one or a few reference images. However, existing methods based on fine-tuning fail to balance the trade-off between subject learning and the maintenance of the generation capabilities of pretrained models. Moreover, other methods that utilize additional image encoders tend to lose important details of the subject due to encoding compression. To address these challenges, we propose DreamTurner, a novel method that injects reference information from coarse to fine to achieve subject-driven image generation more effectively. DreamTurner introduces a subject-encoder for coarse subject identity preservation, where the compressed general subject features are introduced through an attention layer before visual-text cross-attention. We then modify the self-attention layers within pretrained text-to-image models to self-subject-attention layers to refine the details of the target subject. The generated image queries detailed features from both the reference image and itself in self-subject-attention. It is worth emphasizing that self-subject-attention is an effective, elegant, and training-free method for maintaining the detailed features of customized subjects and can serve as a plug-and-play solution during inference. Finally, with additional subject-driven fine-tuning, DreamTurner achieves remarkable performance in subject-driven image generation, which can be controlled by a text or other conditions such as pose. For further details, please visit the project page at https://dreamtuner-diffusion.github.io/.

cs.CV↗

arXiv2023

DPCIPI: A pre-trained deep learning model for predicting cross-immunity between drifted strains of Influenza A/H3N2

Predicting cross-immunity between viral strains is vital for public health surveillance and vaccine development. Traditional neural network methods, such as BiLSTM, could be ineffective due to the lack of lab data for model training and the overshadowing of crucial features within sequence concatenation. The current work proposes a less data-consuming model incorporating a pre-trained gene sequence model and a mutual information inference operator. Our methodology utilizes gene alignment and deduplication algorithms to preprocess gene sequences, enhancing the model's capacity to discern and focus on distinctions among input gene pairs. The model, i.e., DNA Pretrained Cross-Immunity Protection Inference model (DPCIPI), outperforms state-of-the-art (SOTA) models in predicting hemagglutination inhibition titer from influenza viral gene sequences only. Improvement in binary cross-immunity prediction is 1.58% in F1, 2.34% in precision, 1.57% in recall, and 1.57% in Accuracy. For multilevel cross-immunity improvements, the improvement is 2.12% in F1, 3.50% in precision, 2.19% in recall, and 2.19% in Accuracy. Our study highlights the potential of pre-trained gene models in revolutionizing gene sequence-related prediction tasks. With more gene sequence data being harnessed and larger models trained, we foresee a significant impact of pre-trained models on clinical and public health applications.

cs.CE↗

arXiv2023

UGC: Unified GAN Compression for Efficient Image-to-Image Translation

Recent years have witnessed the prevailing progress of Generative Adversarial Networks (GANs) in image-to-image translation. However, the success of these GAN models hinges on ponderous computational costs and labor-expensive training data. Current efficient GAN learning techniques often fall into two orthogonal aspects: i) model slimming via reduced calculation costs; ii)data/label-efficient learning with fewer training data/labels. To combine the best of both worlds, we propose a new learning paradigm, Unified GAN Compression (UGC), with a unified optimization objective to seamlessly prompt the synergy of model-efficient and label-efficient learning. UGC sets up semi-supervised-driven network architecture search and adaptive online semi-supervised distillation stages sequentially, which formulates a heterogeneous mutual learning scheme to obtain an architecture-flexible, label-efficient, and performance-excellent model.

cs.CV↗

arXiv2023

Quantum storage of entangled photons at telecom wavelengths in a crystal

The quantum internet -- in synergy with the internet that we use today -- promises an enabling platform for next-generation information processing, including exponentially speed-up distributed computation, secure communication, and high-precision metrology. The key ingredients for realizing such a global network are the distribution and storage of quantum entanglement. As ground-based quantum networks are likely to be based on existing fiber networks, telecom-wavelength entangled photons and corresponding quantum memories are of central interest. Recently, $\rm^{167}Er^{3+}$ ions have been identified as a promising candidate for an efficient, broadband quantum memory at telecom wavelength. However, to date, no storage of entangled photons, the crucial step of quantum memory using these promising ions, $\rm^{167}Er^{3+}$, has been reported. Here, we demonstrate the storage and recall of the entangled state of two telecom photons generated from an integrated photonic chip based on a silicon nitride micro-ring resonator. Combining the natural narrow linewidth of the entangled photons and long storage time of $\rm^{167}Er^{3+}$ ions, we achieve storage time of 1.936 $μ$s, more than 387 times longer than in previous works. Successful storage of entanglement in the crystal is certified by a violation of an entanglement witness with more than 23 standard deviations (-0.234 $\pm$ 0.010) at 1.936 $μ$s storage time. These results pave the way for realizing quantum networks based on solid-state devices.

quant-ph↗

arXiv2023

GaFET: Learning Geometry-aware Facial Expression Translation from In-The-Wild Images

While current face animation methods can manipulate expressions individually, they suffer from several limitations. The expressions manipulated by some motion-based facial reenactment models are crude. Other ideas modeled with facial action units cannot generalize to arbitrary expressions not covered by annotations. In this paper, we introduce a novel Geometry-aware Facial Expression Translation (GaFET) framework, which is based on parametric 3D facial representations and can stably decoupled expression. Among them, a Multi-level Feature Aligned Transformer is proposed to complement non-geometric facial detail features while addressing the alignment challenge of spatial features. Further, we design a De-expression model based on StyleGAN, in order to reduce the learning difficulty of GaFET in unpaired "in-the-wild" images. Extensive qualitative and quantitative experiments demonstrate that we achieve higher-quality and more accurate facial expression transfer results compared to state-of-the-art methods, and demonstrate applicability of various poses and complex textures. Besides, videos or annotated training data are omitted, making our method easier to use and generalize.

cs.CV↗

arXiv2023

DreamIdentity: Improved Editability for Efficient Face-identity Preserved Image Generation

While large-scale pre-trained text-to-image models can synthesize diverse and high-quality human-centric images, an intractable problem is how to preserve the face identity for conditioned face images. Existing methods either require time-consuming optimization for each face-identity or learning an efficient encoder at the cost of harming the editability of models. In this work, we present an optimization-free method for each face identity, meanwhile keeping the editability for text-to-image models. Specifically, we propose a novel face-identity encoder to learn an accurate representation of human faces, which applies multi-scale face features followed by a multi-embedding projector to directly generate the pseudo words in the text embedding space. Besides, we propose self-augmented editability learning to enhance the editability of models, which is achieved by constructing paired generated face and edited face images using celebrity names, aiming at transferring mature ability of off-the-shelf text-to-image models in celebrity faces to unseen faces. Extensive experiments show that our methods can generate identity-preserved images under different scenes at a much faster speed.

cs.CV↗

arXiv2023

Semantic 3D-aware Portrait Synthesis and Manipulation Based on Compositional Neural Radiance Field

Recently 3D-aware GAN methods with neural radiance field have developed rapidly. However, current methods model the whole image as an overall neural radiance field, which limits the partial semantic editability of synthetic results. Since NeRF renders an image pixel by pixel, it is possible to split NeRF in the spatial dimension. We propose a Compositional Neural Radiance Field (CNeRF) for semantic 3D-aware portrait synthesis and manipulation. CNeRF divides the image by semantic regions and learns an independent neural radiance field for each region, and finally fuses them and renders the complete image. Thus we can manipulate the synthesized semantic regions independently, while fixing the other parts unchanged. Furthermore, CNeRF is also designed to decouple shape and texture within each semantic region. Compared to state-of-the-art 3D-aware GAN methods, our approach enables fine-grained semantic region manipulation, while maintaining high-quality 3D-consistent synthesis. The ablation studies show the effectiveness of the structure and loss function used by our method. In addition real image inversion and cartoon portrait 3D editing experiments demonstrate the application potential of our method.

cs.CV↗

arXiv2023

Design Booster: A Text-Guided Diffusion Model for Image Translation with Spatial Layout Preservation

Diffusion models are able to generate photorealistic images in arbitrary scenes. However, when applying diffusion models to image translation, there exists a trade-off between maintaining spatial structure and high-quality content. Besides, existing methods are mainly based on test-time optimization or fine-tuning model for each input image, which are extremely time-consuming for practical applications. To address these issues, we propose a new approach for flexible image translation by learning a layout-aware image condition together with a text condition. Specifically, our method co-encodes images and text into a new domain during the training phase. In the inference stage, we can choose images/text or both as the conditions for each time step, which gives users more flexible control over layout and content. Experimental comparisons of our method with state-of-the-art methods demonstrate our model performs best in both style image translation and semantic image translation and took the shortest time.

cs.CV↗

arXiv2023

ReGANIE: Rectifying GAN Inversion Errors for Accurate Real Image Editing

The StyleGAN family succeed in high-fidelity image generation and allow for flexible and plausible editing of generated images by manipulating the semantic-rich latent style space.However, projecting a real image into its latent space encounters an inherent trade-off between inversion quality and editability. Existing encoder-based or optimization-based StyleGAN inversion methods attempt to mitigate the trade-off but see limited performance. To fundamentally resolve this problem, we propose a novel two-phase framework by designating two separate networks to tackle editing and reconstruction respectively, instead of balancing the two. Specifically, in Phase I, a W-space-oriented StyleGAN inversion network is trained and used to perform image inversion and editing, which assures the editability but sacrifices reconstruction quality. In Phase II, a carefully designed rectifying network is utilized to rectify the inversion errors and perform ideal reconstruction. Experimental results show that our approach yields near-perfect reconstructions without sacrificing the editability, thus allowing accurate manipulation of real images. Further, we evaluate the performance of our rectifying network, and see great generalizability towards unseen manipulation types and out-of-domain images.

cs.CV↗

arXiv2023

HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection

The High-Resolution Transformer (HRFormer) can maintain high-resolution representation and share global receptive fields. It is friendly towards salient object detection (SOD) in which the input and output have the same resolution. However, two critical problems need to be solved for two-modality SOD. One problem is two-modality fusion. The other problem is the HRFormer output's fusion. To address the first problem, a supplementary modality is injected into the primary modality by using global optimization and an attention mechanism to select and purify the modality at the input level. To solve the second problem, a dual-direction short connection fusion module is used to optimize the output features of HRFormer, thereby enhancing the detailed representation of objects at the output level. The proposed model, named HRTransNet, first introduces an auxiliary stream for feature extraction of supplementary modality. Then, features are injected into the primary modality at the beginning of each multi-resolution branch. Next, HRFormer is applied to achieve forwarding propagation. Finally, all the output features with different resolutions are aggregated by intra-feature and inter-feature interactive transformers. Application of the proposed model results in impressive improvement for driving two-modality SOD tasks, e.g., RGB-D, RGB-T, and light field SOD.https://github.com/liuzywen/HRTransNet

cs.CV↗

arXiv2022

High fusion computers: The IoTs, edges, data centers, and humans-in-the-loop as a computer

Emerging and future applications rely heavily upon systems consisting of Internet of Things (IoT), edges, data centers, and humans-in-the-loop. Significantly different from warehouse-scale computers that serve independent concurrent user requests, this new class of computer systems directly interacts with the physical world, considering humans an essential part and performing safety-critical and mission-critical operations; their computations have intertwined dependencies between not only adjacent execution loops but also actions or decisions triggered by IoTs, edge, datacenters, or humans-in-the-loop; the systems must first satisfy the accuracy metric in predicting, interpreting, or taking action before meeting the performance goal under different cases. This article argues we need a paradigm shift to reconstruct the IoTs, edges, data centers, and humans-in-the-loop as a computer rather than a distributed system. We coin a new term, high fusion computers (HFCs), to describe this class of systems. The fusion in the term has two implications: fusing IoTs, edges, data centers, and humans-in-the-loop as a computer, fusing the physical and digital worlds through HFC systems. HFC is a pivotal case of the open-source computer systems initiative. We laid out the challenges, plan, and call for uniting our community's wisdom and actions to address the HFC challenges. Everything, including the source code, will be publicly available from the project homepage: https://www.computercouncil.org/HFC/.

cs.DC↗

arXiv2022

Mutual Information-guided Knowledge Transfer for Novel Class Discovery

We tackle the novel class discovery problem, aiming to discover novel classes in unlabeled data based on labeled data from seen classes. The main challenge is to transfer knowledge contained in the seen classes to unseen ones. Previous methods mostly transfer knowledge through sharing representation space or joint label space. However, they tend to neglect the class relation between seen and unseen categories, and thus the learned representations are less effective for clustering unseen classes. In this paper, we propose a principle and general method to transfer semantic knowledge between seen and unseen classes. Our insight is to utilize mutual information to measure the relation between seen classes and unseen classes in a restricted label space and maximizing mutual information promotes transferring semantic knowledge. To validate the effectiveness and generalization of our method, we conduct extensive experiments both on novel class discovery and general novel class discovery settings. Our results show that the proposed method outperforms previous SOTA by a significant margin on several benchmarks.

cs.CV↗

arXiv2022

An Integrated Constrained Gradient Descent (iCGD) Protocol to Correct Scan-Positional Errors for Electron Ptychography with High Accuracy and Precision

Correcting scan-positional errors is critical in achieving electron ptychography with both high resolution and high precision. This is a demanding and challenging task due to the sheer number of parameters that need to be optimized. For atomic-resolution ptychographic reconstructions, we found classical refining methods for scan positions not satisfactory due to the inherent entanglement between the object and scan positions, which can produce systematic errors in the results. Here, we propose a new protocol consisting of a series of constrained gradient descent (CGD) methods to achieve better recovery of scan positions. The central idea of these CGD methods is to utilize a priori knowledge about the nature of STEM experiments and add necessary constraints to isolate different types of scan positional errors during the iterative reconstruction process. Each constraint will be introduced with the help of simulated 4D-STEM datasets with known positional errors. Then the integrated constrained gradient decent (iCGD) protocol will be demonstrated using an experimental 4D-STEM dataset of the 1H-MoS2 monolayer. We will show that the iCGD protocol can effectively address the errors of scan positions across the spectrum and help to achieve electron ptychography with high accuracy and precision.

cond-mat.other↗

arXiv2022

DyStyle: Dynamic Neural Network for Multi-Attribute-Conditioned Style Editing

The semantic controllability of StyleGAN is enhanced by unremitting research. Although the existing weak supervision methods work well in manipulating the style codes along one attribute, the accuracy of manipulating multiple attributes is neglected. Multi-attribute representations are prone to entanglement in the StyleGAN latent space, while sequential editing leads to error accumulation. To address these limitations, we design a Dynamic Style Manipulation Network (DyStyle) whose structure and parameters vary by input samples, to perform nonlinear and adaptive manipulation of latent codes for flexible and precise attribute control. In order to efficient and stable optimization of the DyStyle network, we propose a Dynamic Multi-Attribute Contrastive Learning (DmaCL) method: including dynamic multi-attribute contrastor and dynamic multi-attribute contrastive loss, which simultaneously disentangle a variety of attributes from the generative image and latent space of model. As a result, our approach demonstrates fine-grained disentangled edits along multiple numeric and binary attributes. Qualitative and quantitative comparisons with existing style manipulation methods verify the superiority of our method in terms of the multi-attribute control accuracy and identity preservation without compromising photorealism.

cs.CV↗

arXiv2022

Caught in the Crossfire: Fears of Chinese-American Scientists

The US leadership in science and technology has greatly benefitted from immigrants from other countries, most notably from China in the recent decades. However, feeling the pressure of potential federal investigation since the 2018 launch of the China Initiative under the Trump administration, Chinese-origin scientists in the US now face higher incentives to leave the US and lower incentives to apply for federal grants. Analyzing data pertaining to institutional affiliations of more than 2.3 million scientific papers, we find a steady increase in the return migration of Chinese-origin scientists from the US back to China. We also conducted a survey of Chinese-origin scientists employed by US universities in tenure or tenure-track positions (n=1300), with results revealing general feelings of fear and anxiety that lead them to consider leaving the US and/or stop applying for federal grants.

physics.soc-ph↗

arXiv2022

Part-aware Prototypical Graph Network for One-shot Skeleton-based Action Recognition

In this paper, we study the problem of one-shot skeleton-based action recognition, which poses unique challenges in learning transferable representation from base classes to novel classes, particularly for fine-grained actions. Existing meta-learning frameworks typically rely on the body-level representations in spatial dimension, which limits the generalisation to capture subtle visual differences in the fine-grained label space. To overcome the above limitation, we propose a part-aware prototypical representation for one-shot skeleton-based action recognition. Our method captures skeleton motion patterns at two distinctive spatial levels, one for global contexts among all body joints, referred to as body level, and the other attends to local spatial regions of body parts, referred to as the part level. We also devise a class-agnostic attention mechanism to highlight important parts for each action class. Specifically, we develop a part-aware prototypical graph network consisting of three modules: a cascaded embedding module for our dual-level modelling, an attention-based part fusion module to fuse parts and generate part-aware prototypes, and a matching module to perform classification with the part-aware representations. We demonstrate the effectiveness of our method on two public skeleton-based action recognition datasets: NTU RGB+D 120 and NW-UCLA.

cs.CV↗

arXiv2022

Current and perspective sensing methods for monkeypox virus: a reemerging zoonosis in its infancy

Objectives The review is dedicated to evaluate the current monkeypox virus (MPXV) detection methods, discuss their pros and cons, and provide recommended solutions to the problems. Methods The literature for this review is identified through searches in PubMed, Web of Science, Google Scholar, ResearchGate, and Science Direct advanced search for articles published in English without any start date until June, 2022, by use of the terms "monkeypox virus" or "poxvirus" along with "diagnosis"; "PCR"; "real-time PCR"; "LAMP"; "RPA"; "immunoassay"; "reemergence"; "biothreat"; "endemic", and "multi-country outbreak" and also, by tracking citations of the relevant papers. The most relevant articles are included in the review. Results Our literature review shows that PCR is the gold standard method for MPXV detection. In addition, loop-mediated isothermal amplification (LAMP) and recombinase polymerase amplification (RPA) have been reported as alternatives to PCR. Immunodiagnostics, whole particle detection, and image-based detection are the non-nucleic acid-based MPXV detection modalities. Conclusions PCR is easy to leverage and adapt for a quick response to an outbreak, but the PCR-based MPXV detection approaches may not be suitable for marginalized settings. Limited progress has been made towards innovations in MPXV diagnostics, providing room for the development of novel detection techniques for this virus.

q-bio.QM↗

arXiv2022

XMP-Font: Self-Supervised Cross-Modality Pre-training for Few-Shot Font Generation

Generating a new font library is a very labor-intensive and time-consuming job for glyph-rich scripts. Few-shot font generation is thus required, as it requires only a few glyph references without fine-tuning during test. Existing methods follow the style-content disentanglement paradigm and expect novel fonts to be produced by combining the style codes of the reference glyphs and the content representations of the source. However, these few-shot font generation methods either fail to capture content-independent style representations, or employ localized component-wise style representations, which is insufficient to model many Chinese font styles that involve hyper-component features such as inter-component spacing and "connected-stroke". To resolve these drawbacks and make the style representations more reliable, we propose a self-supervised cross-modality pre-training strategy and a cross-modality transformer-based encoder that is conditioned jointly on the glyph image and the corresponding stroke labels. The cross-modality encoder is pre-trained in a self-supervised manner to allow effective capture of cross- and intra-modality correlations, which facilitates the content-style disentanglement and modeling style representations of all scales (stroke-level, component-level and character-level). The pre-trained encoder is then applied to the downstream font generation task without fine-tuning. Experimental comparisons of our method with state-of-the-art methods demonstrate our method successfully transfers styles of all scales. In addition, it only requires one reference glyph and achieves the lowest rate of bad cases in the few-shot font generation task 28% lower than the second best

cs.CV↗