arXiv subjects

Jie Song

Publications and source records attributed to Jie Song.

At least 145 records · Page 8Linked to original sources

arXiv2024

USmorph: An Updated Framework of Automatic Classification of Galaxy Morphologies and Its Application to Galaxies in the COSMOS Field

Morphological classification conveys abundant information on the formation, evolution, and environment of galaxies. In this work, we refine the two-step galaxy morphological classification framework ({\tt\string USmorph}), which employs a combination of unsupervised machine learning (UML) and supervised machine learning (SML) techniques, along with a self-consistent and robust data preprocessing step. The updated method is applied to the galaxies with $I_{\rm mag}<25$ at $0.2<z<1.2$ in the COSMOS field. Based on their HST/ACS I-band images, we classify them into five distinct morphological types: spherical (SPH, 15,200), early-type disk (ETD, 17,369), late-type disk (LTD, 21,143), irregular disk (IRR, 28,965), and unclassified (UNC, 17,129). In addition, we have conducted both parametric and nonparametric morphological measurements. For galaxies with stellar masses exceeding $10^{9}M_{\sun}$, a gradual increase in effective radius from SPHs to IRRs is observed, accompanied by a decrease in the Sérsic index. Nonparametric morphologies reveal distinct distributions of galaxies across the $Gini-M_{20}$ and $C-A$ parameter spaces for different categories. Moreover, different categories exhibit significant dissimilarity in their $G_2$ and $Ψ$ distributions. We find morphology to be strongly correlated with redshift and stellar mass. The consistency of these classification results with expected correlations among multiple parameters underscores the validity and reliability of our classification method, rendering it a valuable tool for future studies.

astro-ph.GA↗

arXiv2024

Supervised learning for robust quantum control in composite-pulse systems

In this work, we develop a supervised learning model for implementing robust quantum control in composite-pulse systems, where the training parameters can be either phases, detunings, or Rabi frequencies. This model exhibits great resistance to all kinds of systematic errors, including single, multiple, and time-varying errors. We propose a modified gradient descent algorithm for adapting the training of phase parameters, and show that different sampling methods result in different robust performances. In particular, there is a trade-off between high fidelity and robustness for a given number of training parameters, and both can be simultaneously enhanced by increasing the number of training parameters (pulses). For its applications, we demonstrate that the current model can be used for achieving high-fidelity arbitrary superposition states and universal quantum gates in a robust manner. This work provides a highly efficient learning model for fault-tolerant quantum computation by training various physical parameters.

quant-ph↗

arXiv2024

SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion

A long-standing goal of 3D human reconstruction is to create lifelike and fully detailed 3D humans from single-view images. The main challenge lies in inferring unknown body shapes, appearances, and clothing details in areas not visible in the images. To address this, we propose SiTH, a novel pipeline that uniquely integrates an image-conditioned diffusion model into a 3D mesh reconstruction workflow. At the core of our method lies the decomposition of the challenging single-view reconstruction problem into generative hallucination and reconstruction subproblems. For the former, we employ a powerful generative diffusion model to hallucinate unseen back-view appearance based on the input images. For the latter, we leverage skinned body meshes as guidance to recover full-body texture meshes from the input and back-view images. SiTH requires as few as 500 3D human scans for training while maintaining its generality and robustness to diverse images. Extensive evaluations on two 3D human benchmarks, including our newly created one, highlighted our method's superior accuracy and perceptual quality in 3D textured human reconstruction. Our code and evaluation benchmark are available at https://ait.ethz.ch/sith

cs.CV↗

arXiv2024

On the Concept Trustworthiness in Concept Bottleneck Models

Concept Bottleneck Models (CBMs), which break down the reasoning process into the input-to-concept mapping and the concept-to-label prediction, have garnered significant attention due to their remarkable interpretability achieved by the interpretable concept bottleneck. However, despite the transparency of the concept-to-label prediction, the mapping from the input to the intermediate concept remains a black box, giving rise to concerns about the trustworthiness of the learned concepts (i.e., these concepts may be predicted based on spurious cues). The issue of concept untrustworthiness greatly hampers the interpretability of CBMs, thereby hindering their further advancement. To conduct a comprehensive analysis on this issue, in this study we establish a benchmark to assess the trustworthiness of concepts in CBMs. A pioneering metric, referred to as concept trustworthiness score, is proposed to gauge whether the concepts are derived from relevant regions. Additionally, an enhanced CBM is introduced, enabling concept predictions to be made specifically from distinct parts of the feature map, thereby facilitating the exploration of their related regions. Besides, we introduce three modules, namely the cross-layer alignment (CLA) module, the cross-image alignment (CIA) module, and the prediction alignment (PA) module, to further enhance the concept trustworthiness within the elaborated CBM. The experiments on five datasets across ten architectures demonstrate that without using any concept localization annotations during training, our model improves the concept trustworthiness by a large margin, meanwhile achieving superior accuracy to the state-of-the-arts. Our code is available at https://github.com/hqhQAQ/ProtoCBM.

cs.CV↗

arXiv2024

Training-Free Pretrained Model Merging

Recently, model merging techniques have surfaced as a solution to combine multiple single-talent models into a single multi-talent model. However, previous endeavors in this field have either necessitated additional training or fine-tuning processes, or require that the models possess the same pre-trained initialization. In this work, we identify a common drawback in prior works w.r.t. the inconsistency of unit similarity in the weight space and the activation space. To address this inconsistency, we propose an innovative model merging framework, coined as merging under dual-space constraints (MuDSC). Specifically, instead of solely maximizing the objective of a single space, we advocate for the exploration of permutation matrices situated in a region with a unified high similarity in the dual space, achieved through the linear combination of activation and weight similarity matrices. In order to enhance usability, we have also incorporated adaptations for group structure, including Multi-Head Attention and Group Normalization. Comprehensive experimental comparisons demonstrate that MuDSC can significantly boost the performance of merged models with various task combinations and architectures. Furthermore, the visualization of the merged model within the multi-task loss landscape reveals that MuDSC enables the merged model to reside in the overlapping segment, featuring a unified lower loss for each task. Our code is publicly available at https://github.com/zju-vipa/training_free_model_merging.

cs.CV↗

arXiv2024

Data Monetization Pathways and Complex Dynamic Game Equilibrium Analysis in the Energy Industry

As the most critical production factor in the era of the digital economy, data will have a significant impact on social production and development. Energy enterprises possess data that is interconnected with multiple industries, characterized by diverse needs, sensitivity, and long-term nature. The path to monetizing energy enterprises' data is challenging yet crucial. This paper explores the game-theoretic aspects of the data monetization process in energy enterprises by considering the relationships between enterprises and trading platforms. We construct a class of game decision models and study their equilibrium strategies. Our analysis shows that enterprises and platforms can adjust respective benefits by regulating the wholesale price of data and the intensity of data value mining to form a benign equilibrium state. Furthermore, by integrating nonlinear dynamical theory, we discuss the dynamic characteristics present in multi-period repeated game processes. We find that decision-makers should keep the adjustment parameters and initial states within reasonable ranges in multi-period dynamic decision-making to avoid market failure. Finally, based on the theoretical and numerical analysis, we provide decision insights and recommendations for enterprise decision-making to facilitate data monetization through strategic interactions with trading platforms.

cs.GT↗

arXiv2024

Pre-Trained Model Recommendation for Downstream Fine-tuning

As a fundamental problem in transfer learning, model selection aims to rank off-the-shelf pre-trained models and select the most suitable one for the new target task. Existing model selection techniques are often constrained in their scope and tend to overlook the nuanced relationships between models and tasks. In this paper, we present a pragmatic framework \textbf{Fennec}, delving into a diverse, large-scale model repository while meticulously considering the intricate connections between tasks and models. The key insight is to map all models and historical tasks into a transfer-related subspace, where the distance between model vectors and task vectors represents the magnitude of transferability. A large vision model, as a proxy, infers a new task's representation in the transfer space, thereby circumventing the computational burden of extensive forward passes. We also investigate the impact of the inherent inductive bias of models on transfer results and propose a novel method called \textbf{archi2vec} to encode the intricate structures of models. The transfer score is computed through straightforward vector arithmetic with a time complexity of $\mathcal{O}(1)$. Finally, we make a substantial contribution to the field by releasing a comprehensive benchmark. We validate the effectiveness of our framework through rigorous testing on two benchmarks. The benchmark and the code will be publicly available in the near future.

cs.CV↗

arXiv2024

ArtiGrasp: Physically Plausible Synthesis of Bi-Manual Dexterous Grasping and Articulation

We present ArtiGrasp, a novel method to synthesize bi-manual hand-object interactions that include grasping and articulation. This task is challenging due to the diversity of the global wrist motions and the precise finger control that are necessary to articulate objects. ArtiGrasp leverages reinforcement learning and physics simulations to train a policy that controls the global and local hand pose. Our framework unifies grasping and articulation within a single policy guided by a single hand pose reference. Moreover, to facilitate the training of the precise finger control required for articulation, we present a learning curriculum with increasing difficulty. It starts with single-hand manipulation of stationary objects and continues with multi-agent training including both hands and non-stationary objects. To evaluate our method, we introduce Dynamic Object Grasping and Articulation, a task that involves bringing an object into a target articulated pose. This task requires grasping, relocation, and articulation. We show our method's efficacy towards this task. We further demonstrate that our method can generate motions with noisy hand-object pose estimates from an off-the-shelf image-based regressor.

cs.RO↗

arXiv2024

SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition

Event cameras are bio-inspired sensors that respond to local changes in light intensity and feature low latency, high energy efficiency, and high dynamic range. Meanwhile, Spiking Neural Networks (SNNs) have gained significant attention due to their remarkable efficiency and fault tolerance. By synergistically harnessing the energy efficiency inherent in event cameras and the spike-based processing capabilities of SNNs, their integration could enable ultra-low-power application scenarios, such as action recognition tasks. However, existing approaches often entail converting asynchronous events into conventional frames, leading to additional data mapping efforts and a loss of sparsity, contradicting the design concept of SNNs and event cameras. To address this challenge, we propose SpikePoint, a novel end-to-end point-based SNN architecture. SpikePoint excels at processing sparse event cloud data, effectively extracting both global and local features through a singular-stage structure. Leveraging the surrogate training method, SpikePoint achieves high accuracy with few parameters and maintains low power consumption, specifically employing the identity mapping feature extractor on diverse datasets. SpikePoint achieves state-of-the-art (SOTA) performance on four event-based action recognition datasets using only 16 timesteps, surpassing other SNN methods. Moreover, it also achieves SOTA performance across all methods on three datasets, utilizing approximately 0.3\% of the parameters and 0.5\% of power consumption employed by artificial neural networks (ANNs). These results emphasize the significance of Point Cloud and pave the way for many ultra-low-power event-based data processing applications.

cs.CV↗

arXiv2024

Three-state coherent control using narrowband and passband sequences

In this work, we propose a comprehensive design for narrowband and passband composite pulse sequences by involving the dynamics of all states in the three-state system. The design is quite universal as all pulse parameters can be freely employed to modify the coefficients of error terms. Two modulation techniques, the strength and phase modulations, are used to achieve arbitrary population transfer with a desired excitation profile, while the system keeps minimal leakage to the third state. Furthermore, the current sequences are capable of tolerating inaccurate waveforms, detunings errors, and work well when rotating wave approximation is not strictly justified. Therefore, this work provides versatile adaptability for shaping various excitation profiles in both narrowband and passband sequences.

quant-ph↗

arXiv2023

Orbital angular momentum-enhanced phase estimation using non-Gaussian state with photon loss

This study investigates the use of orbital angular momentum (OAM) to enhance phase estimation in Mach-Zehnder interferometers (MZIs) by employing non-Gaussian states as input resources in the presence of noise. Our research demonstrates that non-Gaussian states, particularly the photonsubtraction-then-addition (PSA) state, exhibit the best sensitivity in the presence of symmetric noise. Additionally, higher-order of Bose operator of non-Gaussian states provide better sensitivity for symmetric noise. OAM can mitigate the deterioration of noise, making it possible to estimate small phase shifts theta close to 0. OAM enhances the resolution and sensitivity of all input states and mitigating the deterioration caused by photon loss. Additionally, OAM enhances the resolution and sensitivity of all input states, enabling the sensitivity to approach the 1/N limit even under significant photon loss (e.g.,50% symmetric photon loss). These results hold promise for enhancing the sensitivity and robustness of quantum metrology, particularly in the presence of significant photon loss.

quant-ph↗

arXiv2023

Agent-Aware Training for Agent-Agnostic Action Advising in Deep Reinforcement Learning

Action advising endeavors to leverage supplementary guidance from expert teachers to alleviate the issue of sampling inefficiency in Deep Reinforcement Learning (DRL). Previous agent-specific action advising methods are hindered by imperfections in the agent itself, while agent-agnostic approaches exhibit limited adaptability to the learning agent. In this study, we propose a novel framework called Agent-Aware trAining yet Agent-Agnostic Action Advising (A7) to strike a balance between the two. The underlying concept of A7 revolves around utilizing the similarity of state features as an indicator for soliciting advice. However, unlike prior methodologies, the measurement of state feature similarity is performed by neither the error-prone learning agent nor the agent-agnostic advisor. Instead, we employ a proxy model to extract state features that are both discriminative (adaptive to the agent) and generally applicable (robust to agent noise). Furthermore, we utilize behavior cloning to train a model for reusing advice and introduce an intrinsic reward for the advised samples to incentivize the utilization of expert guidance. Experiments are conducted on the GridWorld, LunarLander, and six prominent scenarios from Atari games. The results demonstrate that A7 significantly accelerates the learning process and surpasses existing methods (both agent-specific and agent-agnostic) by a substantial margin. Our code will be made publicly available.

cs.AI↗

arXiv2023

Load Data Valuation in Multi-Energy Systems: An End-to-End Approach

Accurate load forecasting serves as the foundation for the flexible operation of multi-energy systems (MES). Multi-energy loads are tightly coupled and exhibit significant uncertainties. Many works focus on enhancing forecasting accuracy by leveraging cross-sector information. However, data owners may not be motivated to share their data unless it leads to substantial benefits. Ensuring a reasonable data valuation can encourage them to share their data willingly. This paper presents an end-to-end framework to quantify multi-energy load data value by integrating forecasting and decision processes. To address optimization problems with integer variables, a two-stage end-to-end model solution is proposed. Moreover, a profit allocation strategy based on contribution to cost savings is investigated to encourage data sharing in MES. The experimental results demonstrate a significant decrease in operation costs, suggesting that the proposed valuation approach more effectively extracts the inherent data value than traditional methods. According to the proposed incentive mechanism, all sectors can benefit from data sharing by improving forecasting accuracy or receiving economic compensation.

eess.SY↗

arXiv2023

Lookaround Optimizer: $k$ steps around, 1 step average

Weight Average (WA) is an active research topic due to its simplicity in ensembling deep networks and the effectiveness in promoting generalization. Existing weight average approaches, however, are often carried out along only one training trajectory in a post-hoc manner (i.e., the weights are averaged after the entire training process is finished), which significantly degrades the diversity between networks and thus impairs the effectiveness. In this paper, inspired by weight average, we propose Lookaround, a straightforward yet effective SGD-based optimizer leading to flatter minima with better generalization. Specifically, Lookaround iterates two steps during the whole training period: the around step and the average step. In each iteration, 1) the around step starts from a common point and trains multiple networks simultaneously, each on transformed data by a different data augmentation, and 2) the average step averages these trained networks to get the averaged network, which serves as the starting point for the next iteration. The around step improves the functionality diversity while the average step guarantees the weight locality of these networks during the whole training, which is essential for WA to work. We theoretically explain the superiority of Lookaround by convergence analysis, and make extensive experiments to evaluate Lookaround on popular benchmarks including CIFAR and ImageNet with both CNNs and ViTs, demonstrating clear superiority over state-of-the-arts. Our code is available at https://github.com/Ardcy/Lookaround.

cs.CV↗

arXiv2023

Zeroth-Order Feedback-Based Optimization for Distributed Demand Response

Distributed demand response is a typical distributed optimization problem that requires coordination among multiple agents to satisfy demand response requirements. However, existing distributed algorithms for this problem still face challenges such as unknown system models, nonconvexity, privacy issues, etc. To address these challenges, we propose and analyze two distributed algorithms, in which the agents do not share their information and instead perform local updates using zeroth-order feedback information to estimate the gradient of the global objective function. One algorithm applies to problems with general convex and compact feasible sets but has higher oracle complexity bounded by $O(d/ε^2)$, while the other algorithm achieves lower complexity bound $O(d/ε)$ but is only applicable to problems with box constraints. We conduct empirical experiments to validate their performance.

eess.SY↗

arXiv2023

A Survey of Deep Learning for Low-Shot Object Detection

Object detection has achieved a huge breakthrough with deep neural networks and massive annotated data. However, current detection methods cannot be directly transferred to the scenario where the annotated data is scarce due to the severe overfitting problem. Although few-shot learning and zero-shot learning have been extensively explored in the field of image classification, it is indispensable to design new methods for object detection in the data-scarce scenario since object detection has an additional challenging localization task. Low-Shot Object Detection (LSOD) is an emerging research topic of detecting objects from a few or even no annotated samples, consisting of One-Shot Object Detection (OSOD), Few-Shot Object Detection (FSOD) and Zero-Shot Object Detection (ZSD). This survey provides a comprehensive review of LSOD methods. First, we propose a thorough taxonomy of LSOD methods and analyze them systematically, comprising some extensional topics of LSOD (semi-supervised LSOD, weakly-supervised LSOD, and incremental LSOD). Then, we indicate the pros and cons of current LSOD methods with a comparison of their performance. Finally, we discuss the challenges and promising directions of LSOD to provide guidance for future works.

cs.CV↗

arXiv2023

Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networks

Part-prototype networks (e.g., ProtoPNet, ProtoTree, and ProtoPool) have attracted broad research interest for their intrinsic interpretability and comparable accuracy to non-interpretable counterparts. However, recent works find that the interpretability from prototypes is fragile, due to the semantic gap between the similarities in the feature space and that in the input space. In this work, we strive to address this challenge by making the first attempt to quantitatively and objectively evaluate the interpretability of the part-prototype networks. Specifically, we propose two evaluation metrics, termed as consistency score and stability score, to evaluate the explanation consistency across images and the explanation robustness against perturbations, respectively, both of which are essential for explanations taken into practice. Furthermore, we propose an elaborated part-prototype network with a shallow-deep feature alignment (SDFA) module and a score aggregation (SA) module to improve the interpretability of prototypes. We conduct systematical evaluation experiments and provide substantial discussions to uncover the interpretability of existing part-prototype networks. Experiments on three benchmarks across nine architectures demonstrate that our model achieves significantly superior performance to the state of the art, in both the accuracy and interpretability. Our code is available at https://github.com/hqhQAQ/EvalProtoPNet.

cs.CV↗

arXiv2023

Solution to the conflict between the resolved and unresolved galaxy stellar mass estimation from the perspective of JWST

By utilizing the spatially-resolved photometry of galaxies at $0.2<z<3.0$ in the CEERS field, we estimate the resolved and unresolved stellar mass via spectral energy distribution (SED) fitting to study the discrepancy between them. We first compare $M_{\ast}$ derived from photometry with and without the JWST wavelength coverage and find that $M_{\ast}$ can be overestimated by up to 0.2 dex when lacking rest-frame NIR data. The SED fitting process tends to overestimate both stellar age and dust attenuation in the absence of rest-frame NIR data, consequently leading to a larger observed mass-to-light ratio and hence an elevated $M_{\ast}$. With the inclusion of the JWST NIR photometry, we find no significant disparity between the resolved and unresolved stellar mass estimates, providing a plausible solution to the conflict between them out to $z\sim 3$. Further investigation demonstrates that reliable $M_{\ast}$ estimates can be obtained, regardless of whether they are derived from spatially resolved or spatially unresolved photometry, so long as the reddest filter included in the SED fitting has a rest-frame wavelength larger than 10000 Å.

astro-ph.GA↗