arXiv subjects

Yuhao Chen

Publications and source records attributed to Yuhao Chen.

At least 109 records · Page 6Linked to original sources

arXiv2024

Evidence for Plasmoid-mediated Magnetic Reconnection during a Small-scale Flare in the Partially Ionized Low Solar Atmosphere

Magnetic reconnection plays a crucial role in the energy release process for different kinds of solar eruptions and activities. The rapid solar eruption requires a fast reconnection model. Plasmoid instability in the reconnecting current sheets is one of the most acceptable fast reconnection mechanisms for explaining the explosive events in the magnetohydrodynamics (MHD) scale, which is also a potential bridge between the macroscopic MHD reconnection process and microscale dissipations. Plenty of high resolution observations indicate that the plasmoid-like structures exist in the high temperature solar corona, but such evidences are very rare in the lower solar atmosphere with partially ionized plasmas. Utilizing joint observations from the Goode Solar Telescope (GST) and the Solar Dynamics Observatory (SDO), we discovered a small-scale eruptive phenomenon in NOAA AR 13085, characterized by clear reconnection cusp structures, supported by Nonlinear Force-Free Field (NLFFF) extrapolation results. The plasmoid-like structures with a size about 150 km were observed to be ejected downward from the current sheet at a maximum velocity of 24 km$\cdot$s$^{-1}$ in the H$α$ line wing images, followed by enhanced emissions at around the post flare loop region in multiple wave lengths. Our 2.5D high-resolution MHD simulations further reproduced such a phenomenon and revealed reconnection fine structures. These results provide comprehensive evidences for the plasmoid mediated reconnection in partially ionized plasmas, and suggest an unified reconnection model for solar flares with different length scales from the lower chromosphere to corona.

astro-ph.SR↗

arXiv2024

Robust Analysis of Multi-Task Learning Efficiency: New Benchmarks on Light-Weighed Backbones and Effective Measurement of Multi-Task Learning Challenges by Feature Disentanglement

One of the main motivations of MTL is to develop neural networks capable of inferring multiple tasks simultaneously. While countless methods have been proposed in the past decade investigating robust model architectures and efficient training algorithms, there is still lack of understanding of these methods when applied on smaller feature extraction backbones, the generalizability of the commonly used fast approximation technique of replacing parameter-level gradients with feature level gradients, and lack of comprehensive understanding of MTL challenges and how one can efficiently and effectively identify the challenges. In this paper, we focus on the aforementioned efficiency aspects of existing MTL methods. We first carry out large-scale experiments of the methods with smaller backbones and on a the MetaGraspNet dataset as a new test ground. We also compare the existing methods with and without using the fast gradient surrogate and empirically study the generalizability of this technique. Lastly, we propose Feature Disentanglement measure as a novel and efficient identifier of the challenges in MTL, and propose Ranking Similarity score as an evaluation metric for different identifiers to prove the faithfulness of our method.

cs.CV↗

arXiv2024

AnimateZoo: Zero-shot Video Generation of Cross-Species Animation via Subject Alignment

Recent video editing advancements rely on accurate pose sequences to animate subjects. However, these efforts are not suitable for cross-species animation due to pose misalignment between species (for example, the poses of a cat differs greatly from that of a pig due to differences in body structure). In this paper, we present AnimateZoo, a zero-shot diffusion-based video generator to address this challenging cross-species animation issue, aiming to accurately produce animal animations while preserving the background. The key technique used in our AnimateZoo is subject alignment, which includes two steps. First, we improve appearance feature extraction by integrating a Laplacian detail booster and a prompt-tuning identity extractor. These components are specifically designed to capture essential appearance information, including identity and fine details. Second, we align shape features and address conflicts from differing subjects by introducing a scale-information remover. This ensures accurate cross-species animation. Moreover, we introduce two high-quality animal video datasets featuring a wide variety of species. Trained on these extensive datasets, our model is capable of generating videos characterized by accurate movements, consistent appearance, and high-fidelity frames, without the need for the pre-inference fine-tuning that prior arts required. Extensive experiments showcase the outstanding performance of our method in cross-species action following tasks, demonstrating exceptional shape adaptation capability. The project page is available at https://justinxu0.github.io/AnimateZoo/.

cs.CV↗

arXiv2024

Domain-Guided Masked Autoencoders for Unique Player Identification

Unique player identification is a fundamental module in vision-driven sports analytics. Identifying players from broadcast videos can aid with various downstream tasks such as player assessment, in-game analysis, and broadcast production. However, automatic detection of jersey numbers using deep features is challenging primarily due to: a) motion blur, b) low resolution video feed, and c) occlusions. With their recent success in various vision tasks, masked autoencoders (MAEs) have emerged as a superior alternative to conventional feature extractors. However, most MAEs simply zero-out image patches either randomly or focus on where to mask rather than how to mask. Motivated by human vision, we devise a novel domain-guided masking policy for MAEs termed d-MAE to facilitate robust feature extraction in the presence of motion blur for player identification. We further introduce a new spatio-temporal network leveraging our novel d-MAE for unique player identification. We conduct experiments on three large-scale sports datasets, including a curated baseball dataset, the SoccerNet dataset, and an in-house ice hockey dataset. We preprocess the datasets using an upgraded keyframe identification (KfID) module by focusing on frames containing jersey numbers. Additionally, we propose a keyframe-fusion technique to augment keyframes, preserving spatial and temporal context. Our spatio-temporal network showcases significant improvements, surpassing the current state-of-the-art by 8.58%, 4.29%, and 1.20% in the test set accuracies, respectively. Rigorous ablations highlight the effectiveness of our domain-guided masking approach and the refined KfID module, resulting in performance enhancements of 1.48% and 1.84% respectively, compared to original architectures.

cs.CV↗

arXiv2024

Distribution and Depth-Aware Transformers for 3D Human Mesh Recovery

Precise Human Mesh Recovery (HMR) with in-the-wild data is a formidable challenge and is often hindered by depth ambiguities and reduced precision. Existing works resort to either pose priors or multi-modal data such as multi-view or point cloud information, though their methods often overlook the valuable scene-depth information inherently present in a single image. Moreover, achieving robust HMR for out-of-distribution (OOD) data is exceedingly challenging due to inherent variations in pose, shape and depth. Consequently, understanding the underlying distribution becomes a vital subproblem in modeling human forms. Motivated by the need for unambiguous and robust human modeling, we introduce Distribution and depth-aware human mesh recovery (D2A-HMR), an end-to-end transformer architecture meticulously designed to minimize the disparity between distributions and incorporate scene-depth leveraging prior depth information. Our approach demonstrates superior performance in handling OOD data in certain scenarios while consistently achieving competitive results against state-of-the-art HMR methods on controlled datasets.

cs.CV↗

arXiv2024

Light Bridges and Solar Active Region Evolution Processes

The formation mechanism of light bridges (LBs) is strongly related to the dynamic evolution of solar active regions (ARs). To study the relationship between LB formation and AR evolution phases, we employ 109 LB samples from 69 ARs in 2014 using observational data from the Helioseismic and Magnetic Imager on board the Solar Dynamics Observatory (HMI/SDO). LBs are well matched with the weak field lanes (WFLs), except that aligned on the polarity inversion line of δ sunspots. For penumbral intrusion (type-A) and umbral-dot emergence (type-C) LBs, the WFLs represent the splitting of magnetic flux systems. The sunspots tend to decay and split into several parts after type-A and type-C LBs formed. For sunspot/umbra merging (type-B) LBs, the WFLs declining are caused by collisions of flux systems. The sunspots merge and keep stable after type-B LBs formed. We conclude that type-B LBs are formed by collisions of flux systems, while type-A and type-C LBs are generated by splits. The time differences (δT) between LBs appearing and ARs peaking have average value of 1.06, -1.60, 1.82 for type-A, B, C LBs, with the standard deviation of 3.27, 2.17, 1.89, respectively. A positive value of δT means that the LB appear after AR peaking, whereas a minus δT before the peak. Type-A LBs trend to form in the decaying phase or around the peak time. Type-B LBs are more likely to be formed in the developing phase. Type-C LBs mostly take shape in the decaying phase of ARs.

astro-ph.SR↗

arXiv2024

Assessing the Impact of Prompting Methods on ChatGPT's Mathematical Capabilities

This study critically evaluates the efficacy of prompting methods in enhancing the mathematical reasoning capability of large language models (LLMs). The investigation uses three prescriptive prompting methods - simple, persona, and conversational prompting - known for their effectiveness in enhancing the linguistic tasks of LLMs. We conduct this analysis on OpenAI's LLM chatbot, ChatGPT-3.5, on extensive problem sets from the MATH, GSM8K, and MMLU datasets, encompassing a broad spectrum of mathematical challenges. A grading script adapted to each dataset is used to determine the effectiveness of these prompting interventions in enhancing the model's mathematical analysis power. Contrary to expectations, our empirical analysis reveals that none of the investigated methods consistently improves over ChatGPT-3.5's baseline performance, with some causing significant degradation. Our findings suggest that prompting strategies do not necessarily generalize to new domains, in this study failing to enhance mathematical performance.

cs.AI↗

arXiv2023

Excitation of quasi-periodic fast-propagating waves in the early stage of the solar eruption

We propose a mechanism for the excitation of large-scale quasi-periodic fast-propagating magnetoacoustic (QFP) waves observed on both sides of the coronal mass ejection (CME). Through a series of numerical experiments, we successfully simulated the quasi-static evolution of the equilibrium locations of the magnetic flux rope in response to the change of the background magnetic field, as well as the consequent loss of the equilibrium that eventually gives rise to the eruption. During the eruption, we identified QFP waves propagating radially outwards the flux rope, and tracing their origin reveals that they result from the disturbance within the flux rope. Acting as an imperfect waveguide, the flux rope allows the internal disturbance to escape to the outside successively via its surface, invoking the observed QFP waves. Furthermore, we synthesized the images of QFP waves on the basis of the data given by our simulations, and found the consistence with observations. This indicates that the leakage of the disturbance outside the flux rope could be a reasonable mechanism of QFP waves.

astro-ph.SR↗

arXiv2023

NAS-NeRF: Generative Neural Architecture Search for Neural Radiance Fields

Neural radiance fields (NeRFs) enable high-quality novel view synthesis, but their high computational complexity limits deployability. While existing neural-based solutions strive for efficiency, they use one-size-fits-all architectures regardless of scene complexity. The same architecture may be unnecessarily large for simple scenes but insufficient for complex ones. Thus, there is a need to dynamically optimize the neural network component of NeRFs to achieve a balance between computational complexity and specific targets for synthesis quality. We introduce NAS-NeRF, a generative neural architecture search strategy that generates compact, scene-specialized NeRF architectures by balancing architecture complexity and target synthesis quality metrics. Our method incorporates constraints on target metrics and budgets to guide the search towards architectures tailored for each scene. Experiments on the Blender synthetic dataset show the proposed NAS-NeRF can generate architectures up to 5.74$\times$ smaller, with 4.19$\times$ fewer FLOPs, and 1.93$\times$ faster on a GPU than baseline NeRFs, without suffering a drop in SSIM. Furthermore, we illustrate that NAS-NeRF can also achieve architectures up to 23$\times$ smaller, with 22$\times$ fewer FLOPs, and 4.7$\times$ faster than baseline NeRFs with only a 5.3% average SSIM drop. Our source code is also made publicly available at https://saeejithnair.github.io/NAS-NeRF.

cs.CV↗

arXiv2023

NutritionVerse-Synth: An Open Access Synthetically Generated 2D Food Scene Dataset for Dietary Intake Estimation

Manually tracking nutritional intake via food diaries is error-prone and burdensome. Automated computer vision techniques show promise for dietary monitoring but require large and diverse food image datasets. To address this need, we introduce NutritionVerse-Synth (NV-Synth), a large-scale synthetic food image dataset. NV-Synth contains 84,984 photorealistic meal images rendered from 7,082 dynamically plated 3D scenes. Each scene is captured from 12 viewpoints and includes perfect ground truth annotations such as RGB, depth, semantic, instance, and amodal segmentation masks, bounding boxes, and detailed nutritional information per food item. We demonstrate the diversity of NV-Synth across foods, compositions, viewpoints, and lighting. As the largest open-source synthetic food dataset, NV-Synth highlights the value of physics-based simulations for enabling scalable and controllable generation of diverse photorealistic meal images to overcome data limitations and drive advancements in automated dietary assessment using computer vision. In addition to the dataset, the source code for our data generation framework is also made publicly available at https://saeejithnair.github.io/nvsynth.

cs.CV↗

arXiv2023

FoodFusion: A Latent Diffusion Model for Realistic Food Image Generation

Current state-of-the-art image generation models such as Latent Diffusion Models (LDMs) have demonstrated the capacity to produce visually striking food-related images. However, these generated images often exhibit an artistic or surreal quality that diverges from the authenticity of real-world food representations. This inadequacy renders them impractical for applications requiring realistic food imagery, such as training models for image-based dietary assessment. To address these limitations, we introduce FoodFusion, a Latent Diffusion model engineered specifically for the faithful synthesis of realistic food images from textual descriptions. The development of the FoodFusion model involves harnessing an extensive array of open-source food datasets, resulting in over 300,000 curated image-caption pairs. Additionally, we propose and employ two distinct data cleaning methodologies to ensure that the resulting image-text pairs maintain both realism and accuracy. The FoodFusion model, thus trained, demonstrates a remarkable ability to generate food images that exhibit a significant improvement in terms of both realism and diversity over the publicly available image generation models. We openly share the dataset and fine-tuned models to support advancements in this critical field of food image synthesis at https://bit.ly/genai4good.

cs.CV↗

arXiv2023

Cancer-Net PCa-Gen: Synthesis of Realistic Prostate Diffusion Weighted Imaging Data via Anatomic-Conditional Controlled Latent Diffusion

In Canada, prostate cancer is the most common form of cancer in men and accounted for 20% of new cancer cases for this demographic in 2022. Due to recent successes in leveraging machine learning for clinical decision support, there has been significant interest in the development of deep neural networks for prostate cancer diagnosis, prognosis, and treatment planning using diffusion weighted imaging (DWI) data. A major challenge hindering widespread adoption in clinical use is poor generalization of such networks due to scarcity of large-scale, diverse, balanced prostate imaging datasets for training such networks. In this study, we explore the efficacy of latent diffusion for generating realistic prostate DWI data through the introduction of an anatomic-conditional controlled latent diffusion strategy. To the best of the authors' knowledge, this is the first study to leverage conditioning for synthesis of prostate cancer imaging. Experimental results show that the proposed strategy, which we call Cancer-Net PCa-Gen, enhances synthesis of diverse prostate images through controllable tumour locations and better anatomical and textural fidelity. These crucial features make it well-suited for augmenting real patient data, enabling neural networks to be trained on a more diverse and comprehensive data distribution. The Cancer-Net PCa-Gen framework and sample images have been made publicly available at https://www.kaggle.com/datasets/deetsadi/cancer-net-pca-gen-dataset as a part of a global open-source initiative dedicated to accelerating advancement in machine learning to aid clinicians in the fight against cancer.

eess.IV↗

arXiv2023

Confidant: Customizing Transformer-based LLMs via Collaborative Edge Training

Transformer-based large language models (LLMs) have demonstrated impressive capabilities in a variety of natural language processing (NLP) tasks. Nonetheless, it is challenging to deploy and fine-tune LLMs on mobile edge devices with limited computing, memory, and energy budgets. In this paper, we propose Confidant, a multi-backend collaborative training framework for customizing state-of-the-art LLMs on commodity mobile devices like smartphones. Confidant partitions an LLM into several sub-models so that each fits into a mobile device's memory. A pipeline parallel training mechanism is further developed to ensure fast and efficient distributed training. In addition, we propose a novel backend scheduler to allocate different attention heads to heterogeneous compute hardware, including mobile CPU and GPUs, to maximize the compute resource utilization on each edge device. Our preliminary experimental results show that Confidant achieves at most 45.3% memory reduction and 8.03x inference speedup in practical settings.

cs.LG↗

arXiv2023

NutritionVerse-Real: An Open Access Manually Collected 2D Food Scene Dataset for Dietary Intake Estimation

Dietary intake estimation plays a crucial role in understanding the nutritional habits of individuals and populations, aiding in the prevention and management of diet-related health issues. Accurate estimation requires comprehensive datasets of food scenes, including images, segmentation masks, and accompanying dietary intake metadata. In this paper, we introduce NutritionVerse-Real, an open access manually collected 2D food scene dataset for dietary intake estimation with 889 images of 251 distinct dishes and 45 unique food types. The NutritionVerse-Real dataset was created by manually collecting images of food scenes in real life, measuring the weight of every ingredient and computing the associated dietary content of each dish using the ingredient weights and nutritional information from the food packaging or the Canada Nutrient File. Segmentation masks were then generated through human labelling of the images. We provide further analysis on the data diversity to highlight potential biases when using this data to develop models for dietary intake estimation. NutritionVerse-Real is publicly available at https://www.kaggle.com/datasets/nutritionverse/nutritionverse-real as part of an open initiative to accelerate machine learning for dietary sensing.

cs.CV↗

arXiv2023

AccEPT: An Acceleration Scheme for Speeding Up Edge Pipeline-parallel Training

It is usually infeasible to fit and train an entire large deep neural network (DNN) model using a single edge device due to the limited resources. To facilitate intelligent applications across edge devices, researchers have proposed partitioning a large model into several sub-models, and deploying each of them to a different edge device to collaboratively train a DNN model. However, the communication overhead caused by the large amount of data transmitted from one device to another during training, as well as the sub-optimal partition point due to the inaccurate latency prediction of computation at each edge device can significantly slow down training. In this paper, we propose AccEPT, an acceleration scheme for accelerating the edge collaborative pipeline-parallel training. In particular, we propose a light-weight adaptive latency predictor to accurately estimate the computation latency of each layer at different devices, which also adapts to unseen devices through continuous learning. Therefore, the proposed latency predictor leads to better model partitioning which balances the computation loads across participating devices. Moreover, we propose a bit-level computation-efficient data compression scheme to compress the data to be transmitted between devices during training. Our numerical results demonstrate that our proposed acceleration approach is able to significantly speed up edge pipeline parallel training up to 3 times faster in the considered experimental settings.

cs.LG↗

arXiv2023

Jersey Number Recognition using Keyframe Identification from Low-Resolution Broadcast Videos

Player identification is a crucial component in vision-driven soccer analytics, enabling various downstream tasks such as player assessment, in-game analysis, and broadcast production. However, automatically detecting jersey numbers from player tracklets in videos presents challenges due to motion blur, low resolution, distortions, and occlusions. Existing methods, utilizing Spatial Transformer Networks, CNNs, and Vision Transformers, have shown success in image data but struggle with real-world video data, where jersey numbers are not visible in most of the frames. Hence, identifying frames that contain the jersey number is a key sub-problem to tackle. To address these issues, we propose a robust keyframe identification module that extracts frames containing essential high-level information about the jersey number. A spatio-temporal network is then employed to model spatial and temporal context and predict the probabilities of jersey numbers in the video. Additionally, we adopt a multi-task loss function to predict the probability distribution of each digit separately. Extensive evaluations on the SoccerNet dataset demonstrate that incorporating our proposed keyframe identification module results in a significant 37.81% and 37.70% increase in the accuracies of 2 different test sets with domain gaps. These results highlight the effectiveness and importance of our approach in tackling the challenges of automatic jersey number detection in sports videos.

cs.CV↗

arXiv2023

Can the Parker Solar Probe Detect a CME-flare Current Sheet?

A current sheet (CS) is the central structure in the disrupting magnetic configuration during solar eruptions. More than 90\% of the free magnetic energy (the difference between the energy in the non-potential magnetic field and that in the potential one) stored in the coronal magnetic field beforehand is converted into heating and kinetic energy of the plasma, as well as accelerating charged particles, by magnetic reconnection occurring in the CS. However, the detailed physical properties and fine structures of the CS are still unknown since there is no relevant information obtained via in situ detections. The Parker Solar Probe (PSP) may provide us such information should it traverse a CS in the eruption. The perihelion of PSP's final orbit is located at about 10 solar radii from the center of the Sun, so it can observe the CS at a very close distance, or even traverses the CS, which provides us a unique opportunity to look into fine properties and structures of the CS, helping reveal the detailed physics of large-scale reconnection that was impossible before. We evaluate the probability that PSP can traverse a CS, and examine the orbit of a PSP-like spacecraft that has the highest probability to traverse a CS.

astro-ph.SR↗

arXiv2023

Rink-Agnostic Hockey Rink Registration

Hockey rink registration is a useful tool for aiding and automating sports analysis. When combined with player tracking, it can provide location information of players on the rink by estimating a homography matrix that can warp broadcast video frames onto an overhead template of the rink, or vice versa. However, most existing techniques require accurate ground truth information, which can take many hours to annotate, and only work on the trained rink types. In this paper, we propose a generalized rink registration pipeline that, once trained, can be applied to both seen and unseen rink types with only an overhead rink template and the video frame as inputs. Our pipeline uses domain adaptation techniques, semi-supervised learning, and synthetic data during training to achieve this ability and overcome the lack of non-NHL training data. The proposed method is evaluated on both NHL (source) and non-NHL (target) rink data and the results demonstrate that our approach can generalize to non-NHL rinks, while maintaining competitive performance on NHL rinks.

cs.CV↗