arXiv subjects

Hao Jiang

Publications and source records attributed to Hao Jiang.

At least 235 records · Page 13Linked to original sources

arXiv2024

Holistic and Historical Instance Comparison for Cervical Cell Detection

Cytology screening from Papanicolaou (Pap) smears is a common and effective tool for the preventive clinical management of cervical cancer, where abnormal cell detection from whole slide images serves as the foundation for reporting cervical cytology. However, cervical cell detection remains challenging due to 1) hazily-defined cell types (e.g., ASC-US) with subtle morphological discrepancies caused by the dynamic cancerization process, i.e., cell class ambiguity, and 2) imbalanced class distributions of clinical data may cause missed detection, especially for minor categories, i.e., cell class imbalance. To this end, we propose a holistic and historical instance comparison approach for cervical cell detection. Specifically, we first develop a holistic instance comparison scheme enforcing both RoI-level and class-level cell discrimination. This coarse-to-fine cell comparison encourages the model to learn foreground-distinguishable and class-wise representations. To emphatically improve the distinguishability of minor classes, we then introduce a historical instance comparison scheme with a confident sample selection-based memory bank, which involves comparing current embeddings with historical embeddings for better cell instance discrimination. Extensive experiments and analysis on two large-scale cytology datasets including 42,592 and 114,513 cervical cells demonstrate the effectiveness of our method. The code is available at https://github.com/hjiangaz/HERO.

cs.CV↗

arXiv2024

GAInS: Gradient Anomaly-aware Biomedical Instance Segmentation

Instance segmentation plays a vital role in the morphological quantification of biomedical entities such as tissues and cells, enabling precise identification and delineation of different structures. Current methods often address the challenges of touching, overlapping or crossing instances through individual modeling, while neglecting the intrinsic interrelation between these conditions. In this work, we propose a Gradient Anomaly-aware Biomedical Instance Segmentation approach (GAInS), which leverages instance gradient information to perceive local gradient anomaly regions, thus modeling the spatial relationship between instances and refining local region segmentation. Specifically, GAInS is firstly built on a Gradient Anomaly Mapping Module (GAMM), which encodes the radial fields of instances through window sliding to obtain instance gradient anomaly maps. To efficiently refine boundaries and regions with gradient anomaly attention, we propose an Adaptive Local Refinement Module (ALRM) with a gradient anomaly-aware loss function. Extensive comparisons and ablation experiments in three biomedical scenarios demonstrate that our proposed GAInS outperforms other state-of-the-art (SOTA) instance segmentation methods. The code is available at https://github.com/DeepGAInS/GAInS.

cs.CV↗

arXiv2024

Federated Learning with Integrated Sensing, Communication, and Computation: Frameworks and Performance Analysis

With the emergence of integrated sensing, communication, and computation (ISCC) in the upcoming 6G era, federated learning with ISCC (FL-ISCC), integrating sample collection, local training, and parameter exchange and aggregation, has garnered increasing interest for enhancing training efficiency. Currently, FL-ISCC primarily includes two algorithms: FedAVG-ISCC and FedSGD-ISCC. However, the theoretical understanding of the performance and advantages of these algorithms remains limited. To address this gap, we investigate a general FL-ISCC framework, implementing both FedAVG-ISCC and FedSGD-ISCC. We experimentally demonstrate the substantial potential of the ISCC framework in reducing latency and energy consumption in FL. Furthermore, we provide a theoretical analysis and comparison. The results reveal that:1) Both sample collection and communication errors negatively impact algorithm performance, highlighting the need for careful design to optimize FL-ISCC applications. 2) FedAVG-ISCC performs better than FedSGD-ISCC under IID data due to its advantage with multiple local updates. 3) FedSGD-ISCC is more robust than FedAVG-ISCC under non-IID data, where the multiple local updates in FedAVG-ISCC worsen performance as non-IID data increases. FedSGD-ISCC maintains performance levels similar to IID conditions. 4) FedSGD-ISCC is more resilient to communication errors than FedAVG-ISCC, which suffers from significant performance degradation as communication errors increase.Extensive simulations confirm the effectiveness of the FL-ISCC framework and validate our theoretical analysis.

cs.LG↗

arXiv2024

Absence of itinerant ferromagnetism in a cobalt-based oxypnictide

We report a layered transition-metal-ordered oxypnictide Sr$_{2}$CrCoAsO$_{3}$. The new material was synthesized by solid-state reactions under vacuum. It has an intergrowth structure with a perovskite-like Sr$_3$Cr$_2$O$_6$ unit and ThCr$_2$Si$_2$-type SrCo$_2$As$_2$ block stacking coherently along the crystallographic $c$ axis. The measurements of electrical resistivity, magnetic susceptibility, and specific heat indicate metallic conductivity from the CoAs layers and short-range antiferromagnetic ordering in the CrO$_{2}$ planes. No itinerant-electron ferromagnetism expected in CoAs layers is observed. This result, combined with the first-principles calculations and the previous reports of other CoAs-layer-based materials, suggests that the Co$-$Co bondlength plays a crucial role in the emergence of itinerant ferromagnetism.

cond-mat.mtrl-sci↗

arXiv2024

Filter & Align: Leveraging Human Knowledge to Curate Image-Text Data

The increasing availability of image-text pairs has largely fueled the rapid advancement in vision-language foundation models. However, the vast scale of these datasets inevitably introduces significant variability in data quality, which can adversely affect the model performance. This highlights the critical role of data filtering, not only to enhance training efficiency but also to improve overall data quality. Existing methods typically rely on metrics such as CLIP Score and BLIP Score, which are derived from pre-trained models. However, these models are often trained on uncurated, noisy datasets, which can perpetuate errors and misalignments in the filtered dataset. We present a novel algorithm that incorporates human knowledge on image-text alignment to guide filtering vast corpus of web-crawled image-text datasets into a compact and high-quality form. To systemically capture human preferences on image-text alignments, we collect a diverse image-text dataset where each image is associated with multiple captions from various sources, and establish a comprehensive set of both subjective and objective criteria for critically guiding the alignment assessment from labelers. Additionally, we train a reward model on these human-preference annotations to internalize the nuanced human understanding of image-text alignment. The resulting reward model thus can act as a human-like referee to filter image-text pairs. Extensive experiments demonstrate that we can maintain, sometimes even improve, model performance while compressing the image-text datasets up to ~90%. An impressive example is that, by aggressively reducing the total training sample from 130M to only 15.5M, our BLIP-B/16 models consistently show an average improvement of 2.9% on retrieval tasks and 11.5% on captioning tasks compared to full-size-dataset counterparts.

cs.CV↗

arXiv2024

Multi-Modal Experience Inspired AI Creation

AI creation, such as poem or lyrics generation, has attracted increasing attention from both industry and academic communities, with many promising models proposed in the past few years. Existing methods usually estimate the outputs based on single and independent visual or textual information. However, in reality, humans usually make creations according to their experiences, which may involve different modalities and be sequentially correlated. To model such human capabilities, in this paper, we define and solve a novel AI creation problem based on human experiences. More specifically, we study how to generate texts based on sequential multi-modal information. Compared with the previous works, this task is much more difficult because the designed model has to well understand and adapt the semantics among different modalities and effectively convert them into the output in a sequential manner. To alleviate these difficulties, we firstly design a multi-channel sequence-to-sequence architecture equipped with a multi-modal attention network. For more effective optimization, we then propose a curriculum negative sampling strategy tailored for the sequential inputs. To benchmark this problem and demonstrate the effectiveness of our model, we manually labeled a new multi-modal experience dataset. With this dataset, we conduct extensive experiments by comparing our model with a series of representative baselines, where we can demonstrate significant improvements in our model based on both automatic and human-centered metrics. The code and data are available at: \url{https://github.com/Aman-4-Real/MMTG}.

cs.AI↗

arXiv2024

MRSE: An Efficient Multi-modality Retrieval System for Large Scale E-commerce

Providing high-quality item recall for text queries is crucial in large-scale e-commerce search systems. Current Embedding-based Retrieval Systems (ERS) embed queries and items into a shared low-dimensional space, but uni-modality ERS rely too heavily on textual features, making them unreliable in complex contexts. While multi-modality ERS incorporate various data sources, they often overlook individual preferences for different modalities, leading to suboptimal results. To address these issues, we propose MRSE, a Multi-modality Retrieval System that integrates text, item images, and user preferences through lightweight mixture-of-expert (LMoE) modules to better align features across and within modalities. MRSE also builds user profiles at a multi-modality level and introduces a novel hybrid loss function that enhances consistency and robustness using hard negative sampling. Experiments on a large-scale dataset from Shopee and online A/B testing show that MRSE achieves an 18.9% improvement in offline relevance and a 3.7% gain in online core metrics compared to Shopee's state-of-the-art uni-modality system.

cs.IR↗

arXiv2024

RePair: Automated Program Repair with Process-based Feedback

The gap between the trepidation of program reliability and the expense of repairs underscores the indispensability of Automated Program Repair (APR). APR is instrumental in transforming vulnerable programs into more robust ones, bolstering program reliability while simultaneously diminishing the financial burden of manual repairs. Commercial-scale language models (LM) have taken APR to unprecedented levels. However, the emergence reveals that for models fewer than 100B parameters, making single-step modifications may be difficult to achieve the desired effect. Moreover, humans interact with the LM through explicit prompts, which hinders the LM from receiving feedback from compiler and test cases to automatically optimize its repair policies. In this literature, we explore how small-scale LM (less than 20B) achieve excellent performance through process supervision and feedback. We start by constructing a dataset named CodeNet4Repair, replete with multiple repair records, which supervises the fine-tuning of a foundational model. Building upon the encouraging outcomes of reinforcement learning, we develop a reward model that serves as a critic, providing feedback for the fine-tuned LM's action, progressively optimizing its policy. During inference, we require the LM to generate solutions iteratively until the repair effect no longer improves or hits the maximum step limit. The results show that process-based not only outperforms larger outcome-based generation methods, but also nearly matches the performance of closed-source commercial large-scale LMs.

cs.SE↗

arXiv2024

TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and Competition

While Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA have effectively addressed GPU memory constraints during fine-tuning, their performance often falls short, especially in multidimensional task scenarios. To address this issue, one straightforward solution is to introduce task-specific LoRA modules as domain experts, leveraging the modeling of multiple experts' capabilities and thus enhancing the general capability of multi-task learning. Despite promising, these additional components often add complexity to the training and inference process, contravening the efficient characterization of PEFT designed for. Considering this, we introduce an innovative PEFT method, TeamLoRA, consisting of a collaboration and competition module for experts, and thus achieving the right balance of effectiveness and efficiency: (i) For collaboration, a novel knowledge-sharing and -organizing mechanism is devised to appropriately reduce the scale of matrix operations, thereby boosting the training and inference speed. (ii) For competition, we propose leveraging a game-theoretic interaction mechanism for experts, encouraging experts to transfer their domain-specific knowledge while facing diverse downstream tasks, and thus enhancing the performance. By doing so, TeamLoRA elegantly connects the experts as a "Team" with internal collaboration and competition, enabling a faster and more accurate PEFT paradigm for multi-task learning. To validate the superiority of TeamLoRA, we curate a comprehensive multi-task evaluation(CME) benchmark to thoroughly assess the capability of multi-task learning. Experiments conducted on our CME and other benchmarks indicate the effectiveness and efficiency of TeamLoRA. Our project is available at https://github.com/Lin-Tianwei/TeamLoRA.

cs.CL↗

arXiv2024

Near-Field Sensing: A Low-Complexity Wavenumber-Domain Method

A novel low-complexity wavenumber-domain method is proposed for near-field sensing (NISE). Specifically, the power-concentrated region of the wavenumber-domain channels is related to the target position in a non-linear manner. Based on this observation, a bi-directional convolutional neural network (BiCNN)-based approach is proposed to capture such a relationship, thereby facilitating low-complexity target localization. This method enables direct and gridless target localization using only a limited bandwidth and a single antenna array. Simulation results demonstrate that: 1) during the offline training phase, the proposed BiCNN method can learn to localize the target with fewer trainable parameters compared to the naive neural network architectures; and 2) during the online implementation phase, the BiCNN method can spend 100x less time while maintaining comparable performance to the conventional two-dimensional multiple signal classification (MUSIC) algorithms.

eess.SP↗

arXiv2024

Dynamic Neural Dowker Network: Approximating Persistent Homology in Dynamic Directed Graphs

Persistent homology, a fundamental technique within Topological Data Analysis (TDA), captures structural and shape characteristics of graphs, yet encounters computational difficulties when applied to dynamic directed graphs. This paper introduces the Dynamic Neural Dowker Network (DNDN), a novel framework specifically designed to approximate the results of dynamic Dowker filtration, aiming to capture the high-order topological features of dynamic directed graphs. Our approach creatively uses line graph transformations to produce both source and sink line graphs, highlighting the shared neighbor structures that Dowker complexes focus on. The DNDN incorporates a Source-Sink Line Graph Neural Network (SSLGNN) layer to effectively capture the neighborhood relationships among dynamic edges. Additionally, we introduce an innovative duality edge fusion mechanism, ensuring that the results for both the sink and source line graphs adhere to the duality principle intrinsic to Dowker complexes. Our approach is validated through comprehensive experiments on real-world datasets, demonstrating DNDN's capability not only to effectively approximate dynamic Dowker filtration results but also to perform exceptionally in dynamic graph classification tasks.

cs.LG↗

arXiv2024

Improving Network Interpretability via Explanation Consistency Evaluation

While deep neural networks have achieved remarkable performance, they tend to lack transparency in prediction. The pursuit of greater interpretability in neural networks often results in a degradation of their original performance. Some works strive to improve both interpretability and performance, but they primarily depend on meticulously imposed conditions. In this paper, we propose a simple yet effective framework that acquires more explainable activation heatmaps and simultaneously increase the model performance, without the need for any extra supervision. Specifically, our concise framework introduces a new metric, i.e., explanation consistency, to reweight the training samples adaptively in model learning. The explanation consistency metric is utilized to measure the similarity between the model's visual explanations of the original samples and those of semantic-preserved adversarial samples, whose background regions are perturbed by using image adversarial attack techniques. Our framework then promotes the model learning by paying closer attention to those training samples with a high difference in explanations (i.e., low explanation consistency), for which the current model cannot provide robust interpretations. Comprehensive experimental results on various benchmarks demonstrate the superiority of our framework in multiple aspects, including higher recognition accuracy, greater data debiasing capability, stronger network robustness, and more precise localization ability on both regular networks and interpretable networks. We also provide extensive ablation studies and qualitative analyses to unveil the detailed contribution of each component.

cs.CV↗

arXiv2024

BioDeepHash: Mapping Biometrics into a Stable Code

With the wide application of biometrics, more and more attention has been paid to the security of biometric templates. However most of existing biometric template protection (BTP) methods have some security problems, e.g. the problem that protected templates leak part of the original biometric data (exists in Cancelable Biometrics (CB)), the use of error-correcting codes (ECC) leads to decodable attack, statistical attack (exists in Biometric Cryptosystems (BCS)), the inability to achieve revocability (exists in methods using Neural Network (NN) to learn pre-defined templates), the inability to use cryptographic hash to guarantee strong security (exists in CB and methods using NN to learn latent templates). In this paper, we propose a framework called BioDeepHash based on deep hashing and cryptographic hashing to address the above four problems, where different biometric data of the same user are mapped to a stable code using deep hashing instead of predefined binary codes thus avoiding the use of ECC. An application-specific binary string is employed to achieve revocability. Then cryptographic hashing is used to get the final protected template to ensure strong security. Ultimately our framework achieves not storing any data that would leak part of the original biometric data. We also conduct extensive experiments on facial and iris datasets. Our method achieves an improvement of 10.12$\%$ on the average Genuine Acceptance Rate (GAR) for iris data and 3.12$\%$ for facial data compared to existing methods. In addition, BioDeepHash achieves extremely low False Acceptance Rate (FAR), i.e. 0$\%$ FAR on the iris dataset and the highest FAR on the facial dataset is only 0.0002$\%$.

cs.CR↗

arXiv2024

Blockchain-Enabled Dynamic Spectrum Sharing for Satellite and Terrestrial Communication Networks

Dynamic spectrum sharing (DSS) between satellite and terrestrial networks has increasingly engaged the academic and industrial sectors. Nevertheless, facilitating secure, efficient and scalable sharing continues to pose a pivotal challenge. Emerging as a promising technology to bridge the trust gap among multiple participants, blockchain has been envisioned to enable DSS in a decentralized manner. However, satellites with limited resources may struggle to support the frequent interactions required by blockchain networks. Additionally,given the extensive coverage of satellites, spectrum sharing needs vary by regions, challenging traditional blockchain approaches to accommodate differences. In this work, a partitioned, self-governed, and customized dynamic spectrum sharing approach (PSC-DSS) is proposed for spectrum sharing between satellite access networks and terrestrial access networks. This approach establishes a sharded and tiered architecture which allows various regions to manage spectrum autonomously while jointly maintaining a single blockchain ledger. Moreover, a spectrum-consensus integrated mechanism, which decouples DSS process and couples it with blockchain consensus protocol, is designed to enable regions to conduct DSS transactions in parallel and dynamically innovate spectrum sharing schemes without affecting others. Furthermore, a theoretical framework is derived to justify the stability performance of PSC-DSS. Finally, simulations and experiments are conducted to validate the advantageous performance of PSC-DSS in terms of low-overhead, high efficiency, and robust stability.

cs.DC↗

arXiv2024

Near-Field Sensing Enabled Predictive Beamforming: From Estimation to Tracking

A near-field sensing (NISE) enabled predictive beamforming framework is proposed to facilitate wireless communications with high-mobility channels. Unlike conventional far-field sensing, which only captures the angle and the radial velocity of the user, NISE enables the estimation of the full motion state, including additional distance and transverse velocity information. Two full-motion state sensing approaches are proposed based on the concepts of estimation and tracking, respectively. 1)AGD-AO approach: The full motion state of the user is estimated within a single CPI. In particular, the gradient descent is adopted to estimate the transverse and radial velocities of the user based on the maximum likelihood criteria, while the distance and the angle are calculated by the kinematic model. In this process, moment estimations are leveraged to adaptively tune the step size, thereby leading to a smoother and faster gradient descent. 2) EKF approach: The full motion state of the user is tracked across multiple CPIs. Based on the noisy measurements in multiple CPIs, the EKF iteratively predicts and updates the current motion state to achieve a low tracking error. Based on the obtained full motion state, the beam prediction, and Doppler frequency compensation can be carried out with minimum pilot overhead. Numerical results are provided to validate the effectiveness and efficiency of the proposed approach compared to the conventional far-field predictive beamforming and feedback-based approaches. It is also revealed that: 1)the proposed AGD-AO can achieve stable descending with small gradients, thereby accelerating convergence; 2) compared to far-field predictive beamforming and feedback-based schemes, both of the proposed methods exhibit superior performance; and 3) by incorporating multiple CPIs, the EKF method exhibits greater robustness in low SNR regions.

eess.SP↗

arXiv2024

Sense-Then-Train: An Active-Sensing-Based Beam Training Design for Near-Field MIMO Systems

An active-sensing-based sense-then-train (STT) scheme is proposed for beam training in near-field multiple-input multiple-output (MIMO) systems. Compared to conventional codebook-based schemes, the proposed STT scheme is capable of not only addressing the complex spherical-wave propagation but also effectively exploiting the additional degrees-of-freedoms (DoFs). The STT scheme is tailored for both single-beam and multi-beam cases. 1) For the single-beam case, the STT scheme first utilizes a sensing phase to estimate a low-dimensional representation of the near-field MIMO channel in the truncated wavenumber domain. Then, in the subsequent training phase, the neural network modules at transceivers are updated online to align beams, utilizing sequentially received ping-pong pilots. This approach can efficiently obtain the aligned beam pair without relying on predefined codebooks or training datasets. 2) For the multi-beam case, based on the single-beam STT, a Gram-Schmidt method is further utilized to guarantee the orthogonality between beams in the training phase. Numerical results unveil that 1) the proposed STT scheme can significantly enhance the beam training performance in the near field compared to the conventional far-field codebook-based schemes, and 2) the proposed STT scheme can perform fast and low-complexity beam training, while achieving a near-optimal performance without full channel state information in both cases.

cs.IT↗

arXiv2024

On the Evaluation Consistency of Attribution-based Explanations

Attribution-based explanations are garnering increasing attention recently and have emerged as the predominant approach towards \textit{eXplanable Artificial Intelligence}~(XAI). However, the absence of consistent configurations and systematic investigations in prior literature impedes comprehensive evaluations of existing methodologies. In this work, we introduce {Meta-Rank}, an open platform for benchmarking attribution methods in the image domain. Presently, Meta-Rank assesses eight exemplary attribution methods using six renowned model architectures on four diverse datasets, employing both the \textit{Most Relevant First} (MoRF) and \textit{Least Relevant First} (LeRF) evaluation protocols. Through extensive experimentation, our benchmark reveals three insights in attribution evaluation endeavors: 1) evaluating attribution methods under disparate settings can yield divergent performance rankings; 2) although inconsistent across numerous cases, the performance rankings exhibit remarkable consistency across distinct checkpoints along the same training trajectory; 3) prior attempts at consistent evaluation fare no better than baselines when extended to more heterogeneous models and datasets. Our findings underscore the necessity for future research in this domain to conduct rigorous evaluations encompassing a broader range of models and datasets, and to reassess the assumptions underlying the empirical success of different attribution methods. Our code is publicly available at \url{https://github.com/TreeThree-R/Meta-Rank}.

cs.CV↗

arXiv2024

3GPP-Like GBSM THz Channel Characterization, Modeling, and Simulation Based on Experimental Observations

Terahertz (THz) communication is envisioned as one of the possible technologies for the sixth-generation (6G) communication system due to its rich spectrum. To evaluate the performance of THz communication, it is essential to propose THz channel models within the common framework of the geometry-based stochastic model (GBSM) in the 3rd Generation Partnership Project (3GPP). This paper focuses on THz channel modeling and simulation by a 3GPP-like GBSM, based on channel measurements. We first present channel measurements at 100 GHz in an indoor office scenario and 132 GHz in an urban microcellular scenario. Subsequently, channel characteristics such as path loss, delay spread, angle spread, K-factor, cluster characteristic, cross-correlations, and correlation distances are obtained and analyzed based on channel measurement. Additionally, the channel characteristics are modeled by the statistical distribution of 3GPP channel models, which can be used to reconstruct the channel impulse response (CIR). Furthermore, these obtained distributions are studied referring to the default models in the 3GPP, revealing the channel sparsity in the THz channel. For instance, in the case of line-of-sight links in the indoor office, the mean of the measured cluster number is 4 while the default value is 15. Finally, we propose the THz channel model and its simulation framework to reconstruct CIRs based on the obtained models, which aim at characterizing the sparser THz channels. The obvious channel sparsity is characterized in both scenarios, as the Gini factors obtained by the proposed model only have the maximum deviation of 0.04 for those of the measurement. Overall, these findings are helpful in understanding and modeling the THz channel, facilitating the application of THz communication techniques for 6G.

eess.SP↗