arXiv subjects

Yu Cao

Publications and source records attributed to Yu Cao.

At least 73 records · Page 4Linked to original sources

arXiv2025

Environmental Factors Can Have Opposite Biodiversity Influences on the Community Temporal Stability In Aquatic Ecosystems

1. An understanding of how biodiversity confers ecosystem stability is crucial in managing ecosystems under major environmental changes. Multiple biodiversity drivers can stabilize ecosystem functions over time. However, we know little about how local environmental conditions can influence these biodiversity drivers, and consequently how they indirectly shape the ecological stability of ecosystems. 2. We hypothesized that environmental factors can have opposite influences (i.e., not necessarily either positive or negative) on the temporal stability of communities in different environmental ranges depending on the biodiversity drivers involved. We tested this novel hypothesis by using data from a 4-year-long field study of submerged macrophyte across a water depth gradient in 8 heterogeneous bays of Erhai lake (with total sample size of 30,071 quadrats), a large lentic system in China. 3. Results indicate that a unimodal pattern of stability in temporal biomass measurements occurred along the water-depth gradient, and that multiple biodiversity drivers (the asynchrony in species dynamics, and the stability of dominant species) generally increased the temporal stability of aquatic primary producers. However, the effect of water depth either increased or decreased the stability of biomass according to the environmental conditions associated with sites along the water depth gradient. 4. Synthesis. These results reveal the influence of local environmental conditions on the biodiversity drivers of stability may help predict the functional consequences of biodiversity change across different scenarios of environmental change.

q-bio.PE↗

arXiv2024

Hand1000: Generating Realistic Hands from Text with Only 1,000 Images

Text-to-image generation models have achieved remarkable advancements in recent years, aiming to produce realistic images from textual descriptions. However, these models often struggle with generating anatomically accurate representations of human hands. The resulting images frequently exhibit issues such as incorrect numbers of fingers, unnatural twisting or interlacing of fingers, or blurred and indistinct hands. These issues stem from the inherent complexity of hand structures and the difficulty in aligning textual descriptions with precise visual depictions of hands. To address these challenges, we propose a novel approach named Hand1000 that enables the generation of realistic hand images with target gesture using only 1,000 training samples. The training of Hand1000 is divided into three stages with the first stage aiming to enhance the model's understanding of hand anatomy by using a pre-trained hand gesture recognition model to extract gesture representation. The second stage further optimizes text embedding by incorporating the extracted hand gesture representation, to improve alignment between the textual descriptions and the generated hand images. The third stage utilizes the optimized embedding to fine-tune the Stable Diffusion model to generate realistic hand images. In addition, we construct the first publicly available dataset specifically designed for text-to-hand image generation. Based on the existing hand gesture recognition dataset, we adopt advanced image captioning models and LLaMA3 to generate high-quality textual descriptions enriched with detailed gesture information. Extensive experiments demonstrate that Hand1000 significantly outperforms existing models in producing anatomically correct hand images while faithfully representing other details in the text, such as faces, clothing, and colors.

cs.CV↗

arXiv2024

Knowledge-Based Deep Learning for Time-Efficient Inverse Dynamics

Accurate understanding of muscle activation and muscle forces plays an essential role in neuro-rehabilitation and musculoskeletal disorder treatments. Computational musculoskeletal modeling has been widely used as a powerful non-invasive tool to estimate them through inverse dynamics using static optimization, but the inherent computational complexity results in time-consuming analysis. In this paper, we propose a knowledge-based deep learning framework for time-efficient inverse dynamic analysis, which can predict muscle activation and muscle forces from joint kinematic data directly while not requiring any label information during model training. The Bidirectional Gated Recurrent Unit (BiGRU) neural network is selected as the backbone of our model due to its proficient handling of time-series data. Prior physical knowledge from forward dynamics and pre-selected inverse dynamics based physiological criteria are integrated into the loss function to guide the training of neural networks. Experimental validations on two datasets, including one benchmark upper limb movement dataset and one self-collected lower limb movement dataset from six healthy subjects, are performed. The experimental results have shown that the selected BiGRU architecture outperforms other neural network models when trained using our specifically designed loss function, which illustrates the effectiveness and robustness of the proposed framework.

eess.SP↗

arXiv2024

Enhancing Zero-Shot Facial Expression Recognition by LLM Knowledge Transfer

Current facial expression recognition (FER) models are often designed in a supervised learning manner and thus are constrained by the lack of large-scale facial expression images with high-quality annotations. Consequently, these models often fail to generalize well, performing poorly on unseen images in inference. Vision-language-based zero-shot models demonstrate a promising potential for addressing such challenges. However, these models lack task-specific knowledge and therefore are not optimized for the nuances of recognizing facial expressions. To bridge this gap, this work proposes a novel method, Exp-CLIP, to enhance zero-shot FER by transferring the task knowledge from large language models (LLMs). Specifically, based on the pre-trained vision-language encoders, we incorporate a projection head designed to map the initial joint vision-language space into a space that captures representations of facial actions. To train this projection head for subsequent zero-shot predictions, we propose to align the projected visual representations with task-specific semantic meanings derived from the LLM encoder, and the text instruction-based strategy is employed to customize the LLM knowledge. Given unlabelled facial data and efficient training of the projection head, Exp-CLIP achieves superior zero-shot results to the CLIP models and several other large vision-language models (LVLMs) on seven in-the-wild FER datasets. The code and pre-trained models are available at https://github.com/zengqunzhao/Exp-CLIP.

cs.CV↗

arXiv2024

Context-Aware Token Selection and Packing for Enhanced Vision Transformer

In recent years, the long-range attention mechanism of vision transformers has driven significant performance breakthroughs across various computer vision tasks. However, the traditional self-attention mechanism, which processes both informative and non-informative tokens, suffers from inefficiency and inaccuracies. While sparse attention mechanisms have been introduced to mitigate these issues by pruning tokens involved in attention, they often lack context-awareness and intelligence. These mechanisms frequently apply a uniform token selection strategy across different inputs for batch training or optimize efficiency only for the inference stage. To overcome these challenges, we propose a novel algorithm: Select and Pack Attention (SPA). SPA dynamically selects informative tokens using a low-cost gating layer supervised by selection labels and packs these tokens into new batches, enabling a variable number of tokens to be used in parallelized GPU batch training and inference. Extensive experiments across diverse datasets and computer vision tasks demonstrate that SPA delivers superior performance and efficiency, including a 0.6 mAP improvement in object detection and a 16.4% reduction in computational costs.

cs.CV↗

arXiv2024

Visualizing Energy Transfer Between Redox-Active Colloids

Redox-based electrical conduction in nonconjugated polymers has been explored less than a decade, yet is already showing promise as a new concept for electrical energy transport. Here using monolayers and sub-monolayers of touching micron-sized redox active colloids (RAC) containing high densities of ethyl-viologen (EV) side groups, intercolloid redox-based electron transport was directly observed via fluorescence microscopy. This observation was enabled by the discovery that these RAC exhibit a highly non-linear electrofluorochromism which can be quantitatively coupled to the colloid redox state. By evaluating the quasi-Fickian nature of the charge transfer (CT) kinetics, the apparent CT diffusion coefficient DCT was extracted. Along with addressing more fundamental questions regarding energy transport in colloidal materials, this first real-time real-space imaging of energy transport within monolayers of redox-active colloids may provide insights into energy transfer in flow batteries, and enable design of new forms of conductive polymers for applications including organic electronics.

cond-mat.soft↗

arXiv2024

PAPL-SLAM: Principal Axis-Anchored Monocular Point-Line SLAM

In point-line SLAM systems, the utilization of line structural information and the optimization of lines are two significant problems. The former is usually addressed through structural regularities, while the latter typically involves using minimal parameter representations of lines in optimization. However, separating these two steps leads to the loss of constraint information to each other. We anchor lines with similar directions to a principal axis and optimize them with $n+2$ parameters for $n$ lines, solving both problems together. Our method considers scene structural information, which can be easily extended to different world hypotheses while significantly reducing the number of line parameters to be optimized, enabling rapid and accurate mapping and tracking. To further enhance the system's robustness and avoid mismatch, we have modeled the line-axis probabilistic data association and provided the algorithm for axis creation, updating, and optimization. Additionally, considering that most real-world scenes conform to the Atlanta World hypothesis, we provide a structural line detection strategy based on vertical priors and vanishing points. Experimental results and ablation studies on various indoor and outdoor datasets demonstrate the effectiveness of our system.

cs.RO↗

arXiv2024

Computer-aided Colorization State-of-the-science: A Survey

This paper reviews published research in the field of computer-aided colorization technology. We argue that the colorization task originates from computer graphics, prospers by introducing computer vision, and tends to the fusion of vision and graphics, so we put forward our taxonomy and organize the whole paper chronologically. We extend the existing reconstruction-based colorization evaluation techniques, considering that aesthetic assessment of colored images should be introduced to ensure that colorization satisfies human visual-related requirements and emotions more closely. We perform the colorization aesthetic assessment on seven representative unconditional colorization models and discuss the difference between our assessment and the existing reconstruction-based metrics. Finally, this paper identifies unresolved issues and proposes fruitful areas for future research and development. Access to the project associated with this survey can be obtained at https://github.com/DanielCho-HK/Colorization.

cs.CV↗

arXiv2024

Critical link identification of power system vulnerability based on modified graph attention network

With the expansion of the power grid and the increase of the proportion of new energy sources, the uncertainty and random factors of the power grid increase, endangering the safe operation of the system. It is particularly important to find out the critical links of vulnerability in the power grid to ensure the reliability of the power grid operation. Aiming at the problem that the identification speed of the traditional critical link of vulnerability identification methods is slow and difficult to meet the actual operation requirements of the power grid, the improved graph attention network (IGAT) based identification method of the critical link is proposed. First, the evaluation index set is established by combining the complex network theory and the actual operation data of power grid. Secondly, IGAT is used to dig out the mapping relationship between various indicators and critical links of vulnerability during the operation of the power grid, establish the identification model of critical links of vulnerability, and optimize the original graph attention network considering the training accuracy and efficiency. Thirdly, the original data set is obtained through simulation, and the identification model is trained, verified and tested. Finally, the model is applied to the improved IEEE 30-node system and the actual power grid, and the results show that the proposed method is feasible, and the accuracy and speed are better than that of traditional methods. It has certain engineering utilization value.

eess.SY↗

arXiv2024

Diversifying the Mixture-of-Experts Representation for Language Models with Orthogonal Optimizer

The Mixture of Experts (MoE) has emerged as a highly successful technique in deep learning, based on the principle of divide-and-conquer to maximize model capacity without significant additional computational cost. Even in the era of large-scale language models (LLMs), MoE continues to play a crucial role, as some researchers have indicated that GPT-4 adopts the MoE structure to ensure diverse inference results. However, MoE is susceptible to performance degeneracy, particularly evident in the issues of imbalance and homogeneous representation among experts. While previous studies have extensively addressed the problem of imbalance, the challenge of homogeneous representation remains unresolved. In this study, we shed light on the homogeneous representation problem, wherein experts in the MoE fail to specialize and lack diversity, leading to frustratingly high similarities in their representations (up to 99\% in a well-performed MoE model). This problem restricts the expressive power of the MoE and, we argue, contradicts its original intention. To tackle this issue, we propose a straightforward yet highly effective solution: OMoE, an orthogonal expert optimizer. Additionally, we introduce an alternating training strategy that encourages each expert to update in a direction orthogonal to the subspace spanned by other experts. Our algorithm facilitates MoE training in two key ways: firstly, it explicitly enhances representation diversity, and secondly, it implicitly fosters interaction between experts during orthogonal weights computation. Through extensive experiments, we demonstrate that our proposed optimization algorithm significantly improves the performance of fine-tuning the MoE model on the GLUE benchmark, SuperGLUE benchmark, question-answering task, and name entity recognition tasks.

cs.CL↗

arXiv2024

Selective-injection GaN Heterojunction Bipolar Transistors with 275 kA/cm$^2$ Current Density

We design and demonstrate selective injection GaN heterojunction bipolar transistors that utilize a patterned base for selective injection of electrons from the emitter. The design maneuvers minority carrier injection through a thin p-GaN base region, while the majority carrier holes for base current are injected from thick p-GaN regions adjacent to the thin p-GaN base. The design is realized using a regrowth emitter approach with SiO$_2$ as a spacer between the emitter layer and the thick p-GaN base contact regions. The fabricated device demonstrated state-of-art output current density (I$_{C, max}$) ~275 kA/cm$^2$ with a current gain ($β$) of 9, and 17 for the planar HBT design (I$_{C, max}$ =150 kA/cm$^2$). The reported results highlight the potential of the selective injection design to overcome the persistent GaN HBT design tradeoff between base resistance and current gain, paving the way for next-generation radio frequency and mm-Wave applications.

physics.app-ph↗

arXiv2024

Adaptify: A Refined Adaptation Scheme for Frame Classification in Atrophic Gastritis Videos

Atrophic gastritis is a significant risk factor for developing gastric cancer. The incorporation of machine learning algorithms can efficiently elevate the possibility of accurately detecting atrophic gastritis. Nevertheless, when the trained model is applied in real-life circumstances, its output is often not consistently reliable. In this paper, we propose Adaptify, an adaptation scheme in which the model assimilates knowledge from its own classification decisions. Our proposed approach includes keeping the primary model constant, while simultaneously running and updating the auxiliary model. By integrating the knowledge gleaned by the auxiliary model into the primary model and merging their outputs, we have observed a notable improvement in output stability and consistency compared to relying solely on either the main model or the auxiliary model.

cs.CV↗

arXiv2024

Meta-Task Prompting Elicits Embeddings from Large Language Models

We introduce a new unsupervised text embedding method, Meta-Task Prompting with Explicit One-Word Limitation (MetaEOL), for generating high-quality sentence embeddings from Large Language Models (LLMs) without the need for model fine-tuning. Leveraging meta-task prompting, MetaEOL guides LLMs to produce embeddings through a series of carefully designed prompts that address multiple representational aspects. Our comprehensive experiments demonstrate that embeddings averaged from various meta-tasks are versatile embeddings that yield competitive performance on Semantic Textual Similarity (STS) benchmarks and excel in downstream tasks, surpassing contrastive-trained models. Our findings suggest a new scaling law, offering a versatile and resource-efficient approach for embedding generation across diverse scenarios.

cs.CL↗

arXiv2024

Few-Shot Image Generation by Conditional Relaxing Diffusion Inversion

In the field of Few-Shot Image Generation (FSIG) using Deep Generative Models (DGMs), accurately estimating the distribution of target domain with minimal samples poses a significant challenge. This requires a method that can both capture the broad diversity and the true characteristics of the target domain distribution. We present Conditional Relaxing Diffusion Inversion (CRDI), an innovative `training-free' approach designed to enhance distribution diversity in synthetic image generation. Distinct from conventional methods, CRDI does not rely on fine-tuning based on only a few samples. Instead, it focuses on reconstructing each target image instance and expanding diversity through few-shot learning. The approach initiates by identifying a Sample-wise Guidance Embedding (SGE) for the diffusion model, which serves a purpose analogous to the explicit latent codes in certain Generative Adversarial Network (GAN) models. Subsequently, the method involves a scheduler that progressively introduces perturbations to the SGE, thereby augmenting diversity. Comprehensive experiments demonstrates that our method surpasses GAN-based reconstruction techniques and equals state-of-the-art (SOTA) FSIG methods in performance. Additionally, it effectively mitigates overfitting and catastrophic forgetting, common drawbacks of fine-tuning approaches.

cs.CV↗

arXiv2024

Periodic domain inversion in single crystal barium titanate-on-insulator thin film

We report experimentally achieving first-ever electric field periodic poling of single crystal barium titanate (BTO, or BaTiO3) thin film on insulator. Owing to the outstanding optical nonlinearities of BTO, this result is a key step towards achieving quasi-phase-matching in BTO. We first grow the BTO thin film on a dysprosium scandate substrate using pulsed laser deposition with a thin layer of strontium ruthenate later serving as the bottom electrode for poling. We present characterization of the BTO thin film using x-ray diffraction and piezo-response force microscopy to clearly demonstrate single crystal, single domain growth of the film which enables the desired periodic poling. To investigate the poling quality, we apply both non-destructive piezo force response microscopy and destructive etching-assisted scanning electron microscopy and we show that high quality, uniform and intransient poling with 50 % duty cycle and periods ranging from 2 μm to 10 μm is achieved. The successful realization of periodic poling in BTO thin film unlocks the potential for highly efficient nonlinear processes under quasi-phase-matching that seemed far-fetched with prior polycrystalline BTO thin films which predominantly relied on efficiency-limited random or non-phase matching conditions and is a key step towards integration of BTO photonic devices.

physics.optics↗

arXiv2024

CRNet: A Detail-Preserving Network for Unified Image Restoration and Enhancement Task

In real-world scenarios, images captured often suffer from blurring, noise, and other forms of image degradation, and due to sensor limitations, people usually can only obtain low dynamic range images. To achieve high-quality images, researchers have attempted various image restoration and enhancement operations on photographs, including denoising, deblurring, and high dynamic range imaging. However, merely performing a single type of image enhancement still cannot yield satisfactory images. In this paper, to deal with the challenge above, we propose the Composite Refinement Network (CRNet) to address this issue using multiple exposure images. By fully integrating information-rich multiple exposure inputs, CRNet can perform unified image restoration and enhancement. To improve the quality of image details, CRNet explicitly separates and strengthens high and low-frequency information through pooling layers, using specially designed Multi-Branch Blocks for effective fusion of these frequencies. To increase the receptive field and fully integrate input features, CRNet employs the High-Frequency Enhancement Module, which includes large kernel convolutions and an inverted bottleneck ConvFFN. Our model secured third place in the first track of the Bracketing Image Restoration and Enhancement Challenge, surpassing previous SOTA models in both testing metrics and visual quality.

cs.CV↗

arXiv2024

Corpus-Steered Query Expansion with Large Language Models

Recent studies demonstrate that query expansions generated by large language models (LLMs) can considerably enhance information retrieval systems by generating hypothetical documents that answer the queries as expansions. However, challenges arise from misalignments between the expansions and the retrieval corpus, resulting in issues like hallucinations and outdated information due to the limited intrinsic knowledge of LLMs. Inspired by Pseudo Relevance Feedback (PRF), we introduce Corpus-Steered Query Expansion (CSQE) to promote the incorporation of knowledge embedded within the corpus. CSQE utilizes the relevance assessing capability of LLMs to systematically identify pivotal sentences in the initially-retrieved documents. These corpus-originated texts are subsequently used to expand the query together with LLM-knowledge empowered expansions, improving the relevance prediction between the query and the target documents. Extensive experiments reveal that CSQE exhibits strong performance without necessitating any training, especially with queries for which LLMs lack knowledge.

cs.IR↗

arXiv2023

Transformer-based Selective Super-Resolution for Efficient Image Refinement

Conventional super-resolution methods suffer from two drawbacks: substantial computational cost in upscaling an entire large image, and the introduction of extraneous or potentially detrimental information for downstream computer vision tasks during the refinement of the background. To solve these issues, we propose a novel transformer-based algorithm, Selective Super-Resolution (SSR), which partitions images into non-overlapping tiles, selects tiles of interest at various scales with a pyramid architecture, and exclusively reconstructs these selected tiles with deep features. Experimental results on three datasets demonstrate the efficiency and robust performance of our approach for super-resolution. Compared to the state-of-the-art methods, the FID score is reduced from 26.78 to 10.41 with 40% reduction in computation cost for the BDD100K dataset. The source code is available at https://github.com/destiny301/SSR.

cs.CV↗