arXiv subjects

Jian Hu

Publications and source records attributed to Jian Hu.

At least 55 records · Page 3Linked to original sources

arXiv2024

Design and Visual Servoing Control of a Hybrid Dual-Segment Flexible Neurosurgical Robot for Intraventricular Biopsy

Traditional rigid endoscopes have challenges in flexibly treating tumors located deep in the brain, and low operability and fixed viewing angles limit its development. This study introduces a novel dual-segment flexible robotic endoscope MicroNeuro, designed to perform biopsies with dexterous surgical manipulation deep in the brain. Taking into account the uncertainty of the control model, an image-based visual servoing with online robot Jacobian estimation has been implemented to enhance motion accuracy. Furthermore, the application of model predictive control with constraints significantly bolsters the flexible robot's ability to adaptively track mobile objects and resist external interference. Experimental results underscore that the proposed control system enhances motion stability and precision. Phantom testing substantiates its considerable potential for deployment in neurosurgery.

cs.RO↗

arXiv2023

Relax Image-Specific Prompt Requirement in SAM: A Single Generic Prompt for Segmenting Camouflaged Objects

Camouflaged object detection (COD) approaches heavily rely on pixel-level annotated datasets. Weakly-supervised COD (WSCOD) approaches use sparse annotations like scribbles or points to reduce annotation effort, but this can lead to decreased accuracy. The Segment Anything Model (SAM) shows remarkable segmentation ability with sparse prompts like points. However, manual prompt is not always feasible, as it may not be accessible in real-world application. Additionally, it only provides localization information instead of semantic one, which can intrinsically cause ambiguity in interpreting the targets. In this work, we aim to eliminate the need for manual prompt. The key idea is to employ Cross-modal Chains of Thought Prompting (CCTP) to reason visual prompts using the semantic information given by a generic text prompt. To that end, we introduce a test-time adaptation per-instance mechanism called Generalizable SAM (GenSAM) to automatically enerate and optimize visual prompts the generic task prompt for WSCOD. In particular, CCTP maps a single generic text prompt onto image-specific consensus foreground and background heatmaps using vision-language models, acquiring reliable visual prompts. Moreover, to test-time adapt the visual prompts, we further propose Progressive Mask Generation (PMG) to iteratively reweight the input image, guiding the model to focus on the targets in a coarse-to-fine manner. Crucially, all network parameters are fixed, avoiding the need for additional training. Experiments demonstrate the superiority of GenSAM. Experiments on three benchmarks demonstrate that GenSAM outperforms point supervision approaches and achieves comparable results to scribble supervision ones, solely relying on general task descriptions as prompts. our codes is in: https://lwpyh.github.io/GenSAM/.

cs.CV↗

arXiv2023

Aligning Language Models with Offline Learning from Human Feedback

Learning from human preferences is crucial for language models (LMs) to effectively cater to human needs and societal values. Previous research has made notable progress by leveraging human feedback to follow instructions. However, these approaches rely primarily on online learning techniques like Proximal Policy Optimization (PPO), which have been proven unstable and challenging to tune for language models. Moreover, PPO requires complex distributed system implementation, hindering the efficiency of large-scale distributed training. In this study, we propose an offline learning from human feedback framework to align LMs without interacting with environments. Specifically, we explore filtering alignment (FA), reward-weighted regression (RWR), and conditional alignment (CA) to align language models to human preferences. By employing a loss function similar to supervised fine-tuning, our methods ensure more stable model training than PPO with a simple machine learning system~(MLSys) and much fewer (around 9\%) computing resources. Experimental results demonstrate that conditional alignment outperforms other offline alignment methods and is comparable to PPO.

cs.CL↗

arXiv2023

Calibrating the effective magnitudes of type Ia supernovae with a model-independent method

This research explores the correlation between the absolute magnitude and the redshift of Type Ia supernovae (SNe Ia) with a model-independent approach. The Pantheon sample of SNe Ia and strong gravitational lensing systems (SGLS) are used. With the cosmic distance-duality relation (CDDR), the evolution parameter of the magnitude, the light curve parameters of SNe Ia, and the parameters of the SGLS geometric model are constrained simultaneously. Considering the consistency of the redshifts, we selected a subsample of SNe Ia in which the redshift of each SNe Ia is close to the corresponding redshift of the SGLS sample. Two parametric models are used to describe this evolution, which can be written as $δ_M=\varepsilon z$ and $δ_M=\varepsilon\log(1+z)$, respectively. Our analysis reveals that $\varepsilon=-0.036^{+0.357}_{-0.339}$ in the first parametric model and $\varepsilon=-0.014^{+0.588}_{-0.630}$ in the second model, indicating that no significant evolution ($\varepsilon=0$) is supported at the 1$σ$ confidence level in this study. These results represent a significant advancement in our understanding of the intrinsic properties of SNe Ia and provide important constraints for future SNe Ia study.

astro-ph.CO↗

arXiv2023

Pixel-wise Graph Attention Networks for Person Re-identification

Graph convolutional networks (GCN) is widely used to handle irregular data since it updates node features by using the structure information of graph. With the help of iterated GCN, high-order information can be obtained to further enhance the representation of nodes. However, how to apply GCN to structured data (such as pictures) has not been deeply studied. In this paper, we explore the application of graph attention networks (GAT) in image feature extraction. First of all, we propose a novel graph generation algorithm to convert images into graphs through matrix transformation. It is one magnitude faster than the algorithm based on K Nearest Neighbors (KNN). Then, GAT is used on the generated graph to update the node features. Thus, a more robust representation is obtained. These two steps are combined into a module called pixel-wise graph attention module (PGA). Since the graph obtained by our graph generation algorithm can still be transformed into a picture after processing, PGA can be well combined with CNN. Based on these two modules, we consulted the ResNet and design a pixel-wise graph attention network (PGANet). The PGANet is applied to the task of person re-identification in the datasets Market1501, DukeMTMC-reID and Occluded-DukeMTMC (outperforms state-of-the-art by 0.8\%, 1.1\% and 11\% respectively, in mAP scores). Experiment results show that it achieves the state-of-the-art performance. \href{https://github.com/wenyu1009/PGANet}{The code is available here}.

cs.CV↗

arXiv2023

SysNoise: Exploring and Benchmarking Training-Deployment System Inconsistency

Extensive studies have shown that deep learning models are vulnerable to adversarial and natural noises, yet little is known about model robustness on noises caused by different system implementations. In this paper, we for the first time introduce SysNoise, a frequently occurred but often overlooked noise in the deep learning training-deployment cycle. In particular, SysNoise happens when the source training system switches to a disparate target system in deployments, where various tiny system mismatch adds up to a non-negligible difference. We first identify and classify SysNoise into three categories based on the inference stage; we then build a holistic benchmark to quantitatively measure the impact of SysNoise on 20+ models, comprehending image classification, object detection, instance segmentation and natural language processing tasks. Our extensive experiments revealed that SysNoise could bring certain impacts on model robustness across different tasks and common mitigations like data augmentation and adversarial training show limited effects on it. Together, our findings open a new research topic and we hope this work will raise research attention to deep learning deployment systems accounting for model performance. We have open-sourced the benchmark and framework at https://modeltc.github.io/systemnoise_web.

cs.LG↗

arXiv2023

A comparison of cosmological models with high-redshift quasars

The non-linear relationship between the monochromatic X-ray and UV luminosities in quasars offers the possibility of using high-z quasars as standard candles for cosmological testing. In this paper, we use a high-quality catalog of 1598 quasars extending to redshift 6, to compare the flat and uniformly expanding cosmological model, $R_h$ = ct and $Λ$CDM cosmological models which are the most debated. The quasar samples are mainly from the XMM-Newton and the Sloan Digital Sky Survey (SDSS). The final result is that the Akaike Information Criterion favors $Λ$CDM over $R_h$=ct with a relative probability of 86.30% versus 13.70%.

astro-ph.CO↗

arXiv2023

Rethinking the Implementation Tricks and Monotonicity Constraint in Cooperative Multi-Agent Reinforcement Learning

Many complex multi-agent systems such as robot swarms control and autonomous vehicle coordination can be modeled as Multi-Agent Reinforcement Learning (MARL) tasks. QMIX, a widely popular MARL algorithm, has been used as a baseline for the benchmark environments, e.g., Starcraft Multi-Agent Challenge (SMAC), Difficulty-Enhanced Predator-Prey (DEPP). Recent variants of QMIX target relaxing the monotonicity constraint of QMIX, allowing for performance improvement in SMAC. In this paper, we investigate the code-level optimizations of these variants and the monotonicity constraint. (1) We find that such improvements of the variants are significantly affected by various code-level optimizations. (2) The experiment results show that QMIX with normalized optimizations outperforms other works in SMAC; (3) beyond the common wisdom from these works, the monotonicity constraint can improve sample efficiency in SMAC and DEPP. We also discuss why monotonicity constraints work well in purely cooperative tasks with a theoretical analysis. We open-source the code at \url{https://github.com/hijkzzz/pymarl2}.

cs.LG↗

arXiv2023

Policy Regularization via Noisy Advantage Values for Cooperative Multi-agent Actor-Critic methods

Recent works have applied the Proximal Policy Optimization (PPO) to the multi-agent cooperative tasks, such as Independent PPO (IPPO); and vanilla Multi-agent PPO (MAPPO) which has a centralized value function. However, previous literature shows that MAPPO may not perform as well as Independent PPO (IPPO) and the Fine-tuned QMIX on Starcraft Multi-Agent Challenge (SMAC). MAPPO-Feature-Pruned (MAPPO-FP) improves the performance of MAPPO by the carefully designed agent-specific features, which may be not friendly to algorithmic utility. By contrast, we find that MAPPO may face the problem of \textit{The Policies Overfitting in Multi-agent Cooperation(POMAC)}, as they learn policies by the sampled advantage values. Then POMAC may lead to updating the multi-agent policies in a suboptimal direction and prevent the agents from exploring better trajectories. In this paper, to mitigate the multi-agent policies overfitting, we propose a novel policy regularization method, which disturbs the advantage values via random Gaussian noise. The experimental results show that our method outperforms the Fine-tuned QMIX, MAPPO-FP, and achieves SOTA on SMAC without agent-specific features. We open-source the code at \url{https://github.com/hijkzzz/noisy-mappo}.

cs.MA↗

arXiv2023

Exploring the possible evolution of the mass density power-law index of strong gravitational lenses with a model-independent method

In this work, we adopt a cosmological model-independent approach for the first time to test the question of whether the mass density power-law index($γ$) of the strong gravitational lensing system(SGLS) evolves with redshift, and the JLA SNe Ia sample and the quasar sample from Risaliti \& Lusso (2019) are used to provide the luminosity distances to be calibrated. Our work is based on the flat universe assumption and the cosmic distance duality relation. A reliable data-matching method is used to pair SGLS-SNe and SGLS-quasar. By using the maximum likelihood method to constrain the luminosity distance and $γ$ index, we obtain the likelihood function values for the evolved and non-evolved cases, and then use the Akaike weights and the BIC selection weights to compare the advantages and disadvantages of these two cases. We find that the $γ$ index is slightly more likely to be a non-evolutionary model for $γ=2$ in the case of the currently used samples with low redshift ($z_l<\sim$0.66). With Akaike weights, the relative probability is 66.3\% versus 33.7\% and 69.9\% versus 30.1\% for the SGLS+SNe Ia sample and SGLS+quasar sample, respectively, and with BIC selection weights, the relative probability is 87.4\% versus 12.6\% and 52.0\% versus 48.0\% for the two samples. In the evolving case for the relatively low redshift lens (SGLS+SNe Ia), with redshift 0.0625 to 0.659, $γ= 2.058^{+0.041}_{-0.040}-0.136^{+0.163}_{-0.165}z$. At high redshift (SGLS+quasar ), with redshift 0.0625 to 1.004, $γ= 2.051^{+0.076}_{-0.077}-0.171^{+0.214}_{-0.196}z$. Although not the more likely model, this evolved $γ$ case also fits the data well, with a negative and mild evolution for both low and high redshift samples.

astro-ph.CO↗

arXiv2022

Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modeling

Domain adaptation (DA) aims to transfer knowledge learned from a labeled source domain to an unlabeled or a less labeled but related target domain. Ideally, the source and target distributions should be aligned to each other equally to achieve unbiased knowledge transfer. However, due to the significant imbalance between the amount of annotated data in the source and target domains, usually only the target distribution is aligned to the source domain, leading to adapting unnecessary source specific knowledge to the target domain, i.e., biased domain adaptation. To resolve this problem, in this work, we delve into the transferability estimation problem in domain adaptation and propose a non-intrusive Unbiased Transferability Estimation Plug-in (UTEP) by modeling the uncertainty of a discriminator in adversarial-based DA methods to optimize unbiased transfer. We theoretically analyze the effectiveness of the proposed approach to unbiased transferability learning in DA. Furthermore, to alleviate the impact of imbalanced annotated data, we utilize the estimated uncertainty for pseudo label selection of unlabeled samples in the target domain, which helps achieve better marginal and conditional distribution alignments between domains. Extensive experimental results on a high variety of DA benchmark datasets show that the proposed approach can be readily incorporated into various adversarial-based DA methods, achieving state-of-the-art performance.

cs.CV↗

arXiv2022

Feature-Distribution Perturbation and Calibration for Generalized Person ReID

Person Re-identification (ReID) has been advanced remarkably over the last 10 years along with the rapid development of deep learning for visual recognition. However, the i.i.d. (independent and identically distributed) assumption commonly held in most deep learning models is somewhat non-applicable to ReID considering its objective to identify images of the same pedestrian across cameras at different locations often of variable and independent domain characteristics that are also subject to view-biased data distribution. In this work, we propose a Feature-Distribution Perturbation and Calibration (PECA) method to derive generic feature representations for person ReID, which is not only discriminative across cameras but also agnostic and deployable to arbitrary unseen target domains. Specifically, we perform per-domain feature-distribution perturbation to refrain the model from overfitting to the domain-biased distribution of each source (seen) domain by enforcing feature invariance to distribution shifts caused by perturbation. Furthermore, we design a global calibration mechanism to align feature distributions across all the source domains to improve the model generalization capacity by eliminating domain bias. These local perturbation and global calibration are conducted simultaneously, which share the same principle to avoid models overfitting by regularization respectively on the perturbed and the original distributions. Extensive experiments were conducted on eight person ReID datasets and the proposed PECA model outperformed the state-of-the-art competitors by significant margins.

cs.CV↗

arXiv2021

Semi-supervised t-SNE for Millimeter-wave Wireless Localization

We consider the mobile localization problem in future millimeter-wave wireless networks with distributed Base Stations (BSs) based on multi-antenna channel state information (CSI). For this problem, we propose a Semi-supervised tdistributed Stochastic Neighbor Embedding (St-SNE) algorithm to directly embed the high-dimensional CSI samples into the 2D geographical map. We evaluate the performance of St-SNE in a simulated urban outdoor millimeter-wave radio access network. Our results show that St-SNE achieves a mean localization error of 6.8 m with only 5% of labeled CSI samples in a 200*200 m^2 area with a ray-tracing channel model. St-SNE does not require accurate synchronization among multiple BSs, and is promising for future large-scale millimeter-wave localization.

cs.LG↗

arXiv2021

Scheduling of Separable Mobile Energy Storage Systems with Mobile Generators and Fuel Tankers to Boost Distribution System Resilience

Mobile energy resources (MERs) have been shown to boost DS resilience effectively in recent years. In this paper, we propose a novel idea, the separable mobile energy storage system (SMESS), as an attempt to further extend the flexibility of MER applications. "Separable" denotes that the carrier and the energy storage modules are treated as independent parts, which allows the carrier to carry multiple modules and scatter them independently throughout the DS. The constraints for scheduling SMESSs involving carriers and modules are derived based upon the interactive behavior among them and the DS. In addition, the fuel delivery issue of feeding mobile emergency generators (MEGs), which was usually bypassed in previous studies involving the scheduling of MEGs, is also considered and modeled. SMESSs, MEGs, and fuel tankers (FTs) are then jointly routed and scheduled, along with the dynamic DS reconfiguration, for DS service restoration by integrating them in a mixed-integer linear programming (MILP) model. Finally, the test is conducted on a modified IEEE 33-node test system, and results verify the effectiveness of the model in boosting DS resilience.

eess.SY↗

arXiv2021

Self-Adaptive Partial Domain Adaptation

Partial Domain adaptation (PDA) aims to solve a more practical cross-domain learning problem that assumes target label space is a subset of source label space. However, the mismatched label space causes significant negative transfer. A traditional solution is using soft weights to increase weights of source shared domain and reduce those of source outlier domain. But it still learns features of outliers and leads to negative immigration. The other mainstream idea is to distinguish source domain into shared and outlier parts by hard binary weights, while it is unavailable to correct the tangled shared and outlier classes. In this paper, we propose an end-to-end Self-Adaptive Partial Domain Adaptation(SAPDA) Network. Class weights evaluation mechanism is introduced to dynamically self-rectify the weights of shared, outlier and confused classes, thus the higher confidence samples have the more sufficient weights. Meanwhile it can eliminate the negative transfer caused by the mismatching of label space greatly. Moreover, our strategy can efficiently measure the transferability of samples in a broader sense, so that our method can achieve competitive results on unsupervised DA task likewise. A large number of experiments on multiple benchmarks have demonstrated the effectiveness of our SAPDA.

cs.CV↗

arXiv2021

Domain Adaptive YOLO for One-Stage Cross-Domain Detection

Domain shift is a major challenge for object detectors to generalize well to real world applications. Emerging techniques of domain adaptation for two-stage detectors help to tackle this problem. However, two-stage detectors are not the first choice for industrial applications due to its long time consumption. In this paper, a novel Domain Adaptive YOLO (DA-YOLO) is proposed to improve cross-domain performance for one-stage detectors. Image level features alignment is used to strictly match for local features like texture, and loosely match for global features like illumination. Multi-scale instance level features alignment is presented to reduce instance domain shift effectively , such as variations in object appearance and viewpoint. A consensus regularization to these domain classifiers is employed to help the network generate domain-invariant detections. We evaluate our proposed method on popular datasets like Cityscapes, KITTI, SIM10K and etc.. The results demonstrate significant improvement when tested under different cross-domain scenarios.

cs.CV↗

arXiv2021

QR-MIX: Distributional Value Function Factorisation for Cooperative Multi-Agent Reinforcement Learning

In Cooperative Multi-Agent Reinforcement Learning (MARL) and under the setting of Centralized Training with Decentralized Execution (CTDE), agents observe and interact with their environment locally and independently. With local observation and random sampling, the randomness in rewards and observations leads to randomness in long-term returns. Existing methods such as Value Decomposition Network (VDN) and QMIX estimate the value of long-term returns as a scalar that does not contain the information of randomness. Our proposed model QR-MIX introduces quantile regression, modeling joint state-action values as a distribution, combining QMIX with Implicit Quantile Network (IQN). However, the monotonicity in QMIX limits the expression of joint state-action value distribution and may lead to incorrect estimation results in non-monotonic cases. Therefore, we proposed a flexible loss function to approximate the monotonicity found in QMIX. Our model is not only more tolerant of the randomness of returns, but also more tolerant of the randomness of monotonic constraints. The experimental results demonstrate that QR-MIX outperforms the previous state-of-the-art method QMIX in the StarCraft Multi-Agent Challenge (SMAC) environment.

cs.LG↗

arXiv2020

Estimating dust attenuation from galactic spectra. I. methodology and tests

We develop a method to estimate the dust attenuation curve of galaxies from full spectral fitting of their optical spectra. Motivated from previous studies, we separate the small-scale features from the large-scale spectral shape, by performing a moving average method to both the observed spectrum and the simple stellar population model spectra. The intrinsic dust-free model spectrum is then derived by fitting the observed ratio of the small-scale to large-scale (S/L) components with the S/L ratios of the SSP models. The selective dust attenuation curve is then determined by comparing the observed spectrum with the dust-free model spectrum. One important advantage of this method is that the estimated dust attenuation curve is independent of the shape of theoretical dust attenuation curves. We have done a series of tests on a set of mock spectra covering wide ranges of stellar age and metallicity. We show that our method is able to recover the input dust attenuation curve accurately, although the accuracy depends slightly on signal-to-noise ratio of the spectra. We have applied our method to a number of edge-on galaxies with obvious dust lanes from the ongoing MaNGA survey, deriving their dust attenuation curves and $E(B-V)$ maps, as well as dust-free images in $g$, $r$, and $i$ bands. These galaxies show obvious dust lane features in their original images, which largely disappear after we have corrected the effect of dust attenuation. The vertical brightness profiles of these galaxies become axis-symmetric and can well be fitted by a simple model proposed for the disk vertical structure. Comparing the estimated dust attenuation curve with the three commonly-adopted model curves, we find that the Calzetti curve provides the best description of the estimated curves for the inner region of galaxies, while the Milky Way and SMC curves work better for the outer region.

astro-ph.GA↗