arXiv subjects

Kai Li

Publications and source records attributed to Kai Li.

At least 253 records · Page 14Linked to original sources

arXiv2024

Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-Language Models

This study addresses the Domain-Class Incremental Learning problem, a realistic but challenging continual learning scenario where both the domain distribution and target classes vary across tasks. To handle these diverse tasks, pre-trained Vision-Language Models (VLMs) are introduced for their strong generalizability. However, this incurs a new problem: the knowledge encoded in the pre-trained VLMs may be disturbed when adapting to new tasks, compromising their inherent zero-shot ability. Existing methods tackle it by tuning VLMs with knowledge distillation on extra datasets, which demands heavy computation overhead. To address this problem efficiently, we propose the Distribution-aware Interference-free Knowledge Integration (DIKI) framework, retaining pre-trained knowledge of VLMs from a perspective of avoiding information interference. Specifically, we design a fully residual mechanism to infuse newly learned knowledge into a frozen backbone, while introducing minimal adverse impacts on pre-trained knowledge. Besides, this residual property enables our distribution-aware integration calibration scheme, explicitly controlling the information implantation process for test data from unseen distributions. Experiments demonstrate that our DIKI surpasses the current state-of-the-art approach using only 0.86% of the trained parameters and requiring substantially less training time. Code is available at: https://github.com/lloongx/DIKI .

cs.CV↗

arXiv2024

Transmission spectroscopy of CF$_4$ molecules in intense x-ray fields

The nonlinear interaction of x-rays with matter is at the heart of understanding and controlling ultrafast molecular dynamics from an atom-specific viewpoint, providing new scientific and analytical opportunities to explore the structure and dynamics of small quantum systems. At increasingly high x-ray intensity, the sensitivity of ultrashort x-ray pulses to specific electronic states and emerging short-lived transient intermediates is of particular relevance for our understanding of fundamental multi-photon absorption processes. In this work, intense x-ray free-electron laser (XFEL) pulses at the European XFEL (EuXFEL) are combined with a gas cell and grating spectrometer for a high-intensity transmission spectroscopy study of multiphoton-induced ultrafast molecular fragmentation dynamics in CF$_4$. This approach unlocks the direct intra-pulse observation of transient fragments, including neutral atoms, by their characteristic absorption lines in the transmitted broad-band x-ray spectrum. The dynamics with and without initially producing fluorine K-shell holes are studied by tuning the central photon energy. The absorption spectra are measured at different FEL intensities to observe nonlinear effects. Transient isolated fluorine atoms and ions are spectroscopically recorded within the ultrashort pulse duration of few tens of femtoseconds. An isosbestic point that signifies the correlated transition between intact neutral CF$_4$ molecules and charged atomic fragments is observed near the fluorine K-edge. The dissociation dynamics and the multiphoton absorption-induced dynamics encoded in the spectra are theoretically interpreted. Overall, this study demonstrates the potential of high-intensity x-ray transmission spectroscopy to study ultrafast molecular dynamics with sensitivity to specific intermediate species and their electronic structure.

physics.atom-ph↗

arXiv2024

Deep Reinforcement Learning for Adverse Garage Scenario Generation

Autonomous vehicles need to travel over 11 billion miles to ensure their safety. Therefore, the importance of simulation testing before real-world testing is self-evident. In recent years, the release of 3D simulators for autonomous driving, represented by Carla and CarSim, marks the transition of autonomous driving simulation testing environments from simple 2D overhead views to complex 3D models. During simulation testing, experimenters need to build static scenes and dynamic traffic flows, pedestrian flows, and other experimental elements to construct experimental scenarios. When building static scenes in 3D simulators, experimenters often need to manually construct 3D models, set parameters and attributes, which is time-consuming and labor-intensive. This thesis proposes an automated program generation framework. Based on deep reinforcement learning, this framework can generate different 2D ground script codes, on which 3D model files and map model files are built. The generated 3D ground scenes are displayed in the Carla simulator, where experimenters can use this scene for navigation algorithm simulation testing.

cs.AI↗

arXiv2024

A Novel Defense Against Poisoning Attacks on Federated Learning: LayerCAM Augmented with Autoencoder

Recent attacks on federated learning (FL) can introduce malicious model updates that circumvent widely adopted Euclidean distance-based detection methods. This paper proposes a novel defense strategy, referred to as LayerCAM-AE, designed to counteract model poisoning in federated learning. The LayerCAM-AE puts forth a new Layer Class Activation Mapping (LayerCAM) integrated with an autoencoder (AE), significantly enhancing detection capabilities. Specifically, LayerCAM-AE generates a heat map for each local model update, which is then transformed into a more compact visual format. The autoencoder is designed to process the LayerCAM heat maps from the local model updates, improving their distinctiveness and thereby increasing the accuracy in spotting anomalous maps and malicious local models. To address the risk of misclassifications with LayerCAM-AE, a voting algorithm is developed, where a local model update is flagged as malicious if its heat maps are consistently suspicious over several rounds of communication. Extensive tests of LayerCAM-AE on the SVHN and CIFAR-100 datasets are performed under both Independent and Identically Distributed (IID) and non-IID settings in comparison with existing ResNet-50 and REGNETY-800MF defense models. Experimental results show that LayerCAM-AE increases detection rates (Recall: 1.0, Precision: 1.0, FPR: 0.0, Accuracy: 1.0, F1 score: 1.0, AUC: 1.0) and test accuracy in FL, surpassing the performance of both the ResNet-50 and REGNETY-800MF. Our code is available at: https://github.com/jjzgeeks/LayerCAM-AE

cs.CR↗

arXiv2024

Analytical photoresponses of Schottky contact MoS2 phototransistors

High-gain photodetectors based on two-dimensional (2D) semiconductors, in particular those in photoconductive mode, have been extensively investigated in the past decade. However, the classical photoconductive theory was derived on two misplaced assumptions. In this work, we established an explicit analytical device model for Schottky contact MoS2 phototransistors that fits well with experimental data. From the fitting results, we found that the Richardson constant of the MoS2 Schottky contact is temperature dependent, indicating that the Schottky contacts for the 2D material is best described by the mixed thermionic emission and diffusion model. Based on this device model, we further established an analytical photoresponse for the few-layer MoS2 phototransistors, from which we found the voltage distribution on the two Schottky contacts and the channel, and extracted the minority carrier recombination lifetimes. The lifetimes are comparable with the values found from transient photoluminescence measurements, which therefore validates our analytical photoresponses for Schottky contact 2D semiconducting phototransistors.

cond-mat.mes-hall↗

arXiv2024

Minimizing Weighted Counterfactual Regret with Optimistic Online Mirror Descent

Counterfactual regret minimization (CFR) is a family of algorithms for effectively solving imperfect-information games. It decomposes the total regret into counterfactual regrets, utilizing local regret minimization algorithms, such as Regret Matching (RM) or RM+, to minimize them. Recent research establishes a connection between Online Mirror Descent (OMD) and RM+, paving the way for an optimistic variant PRM+ and its extension PCFR+. However, PCFR+ assigns uniform weights for each iteration when determining regrets, leading to substantial regrets when facing dominated actions. This work explores minimizing weighted counterfactual regret with optimistic OMD, resulting in a novel CFR variant PDCFR+. It integrates PCFR+ and Discounted CFR (DCFR) in a principled manner, swiftly mitigating negative effects of dominated actions and consistently leveraging predictions to accelerate convergence. Theoretical analyses prove that PDCFR+ converges to a Nash equilibrium, particularly under distinct weighting schemes for regrets and average strategies. Experimental results demonstrate PDCFR+'s fast convergence in common imperfect-information games. The code is available at https://github.com/rpSebastian/PDCFRPlus.

cs.LG↗

arXiv2024

Age of Information Minimization using Multi-agent UAVs based on AI-Enhanced Mean Field Resource Allocation

Unmanned Aerial Vehicle (UAV) swarms play an effective role in timely data collection from ground sensors in remote and hostile areas. Optimizing the collective behavior of swarms can improve data collection performance. This paper puts forth a new mean field flight resource allocation optimization to minimize age of information (AoI) of sensory data, where balancing the trade-off between the UAVs movements and AoI is formulated as a mean field game (MFG). The MFG optimization yields an expansive solution space encompassing continuous state and action, resulting in significant computational complexity. To address practical situations, we propose, a new mean field hybrid proximal policy optimization (MF-HPPO) scheme to minimize the average AoI by optimizing the UAV's trajectories and data collection scheduling of the ground sensors given mixed continuous and discrete actions. Furthermore, a long short term memory (LSTM) is leveraged in MF-HPPO to predict the time-varying network state and stabilize the training. Numerical results demonstrate that the proposed MF-HPPO reduces the average AoI by up to 45 percent and 57 percent in the considered simulation setting, as compared to multi-agent deep Q-learning (MADQN) method and non-learning random algorithm, respectively.

eess.SY↗

arXiv2024

Leverage Variational Graph Representation For Model Poisoning on Federated Learning

This paper puts forth a new training data-untethered model poisoning (MP) attack on federated learning (FL). The new MP attack extends an adversarial variational graph autoencoder (VGAE) to create malicious local models based solely on the benign local models overheard without any access to the training data of FL. Such an advancement leads to the VGAE-MP attack that is not only efficacious but also remains elusive to detection. VGAE-MP attack extracts graph structural correlations among the benign local models and the training data features, adversarially regenerates the graph structure, and generates malicious local models using the adversarial graph structure and benign models' features. Moreover, a new attacking algorithm is presented to train the malicious local models using VGAE and sub-gradient descent, while enabling an optimal selection of the benign local models for training the VGAE. Experiments demonstrate a gradual drop in FL accuracy under the proposed VGAE-MP attack and the ineffectiveness of existing defense mechanisms in detecting the attack, posing a severe threat to FL.

cs.CR↗

arXiv2024

The Sound Demixing Challenge 2023 $\unicode{x2013}$ Cinematic Demixing Track

This paper summarizes the cinematic demixing (CDX) track of the Sound Demixing Challenge 2023 (SDX'23). We provide a comprehensive summary of the challenge setup, detailing the structure of the competition and the datasets used. Especially, we detail CDXDB23, a new hidden dataset constructed from real movies that was used to rank the submissions. The paper also offers insights into the most successful approaches employed by participants. Compared to the cocktail-fork baseline, the best-performing system trained exclusively on the simulated Divide and Remaster (DnR) dataset achieved an improvement of 1.8 dB in SDR, whereas the top-performing system on the open leaderboard, where any data could be used for training, saw a significant improvement of 5.7 dB. A significant source of this improvement was making the simulated data better match real cinematic audio, which we further investigate in detail.

eess.AS↗

arXiv2024

Online/Offline Learning to Enable Robust Beamforming: Limited Feedback Meets Deep Generative Models

Robust beamforming is a pivotal technique in massive multiple-input multiple-output (MIMO) systems as it mitigates interference among user equipment (UE). One current risk-neutral approach to robust beamforming is the stochastic weighted minimum mean square error method (WMMSE). However, this method necessitates statistical channel information, which is typically inaccessible, particularly in fifth-generation new radio frequency division duplex cellular systems with limited feedback. To tackle this challenge, we propose a novel approach that leverages a channel variational auto-encoder (CVAE) to simulate channel behaviors using limited feedback, eliminating the need for specific distribution assumptions present in existing methods. To seamlessly integrate model learning into practical wireless communication systems, this paper introduces two learning strategies to prepare the CVAE model for practical deployment. Firstly, motivated by the digital twin technology, we advocate employing a high-performance channel simulator to generate training data, enabling pretraining of the proposed CVAE while ensuring non-disruption to the practical wireless communication system. Moreover, we present an alternative online method for CVAE learning, where online training data is sourced based on channel estimations using Type II codebook. Numerical results demonstrate the effectiveness of these strategies, highlighting their exceptional performance in channel generation and robust beamforming applications.

stat.AP↗

arXiv2024

High-Fidelity Lake Extraction via Two-Stage Prompt Enhancement: Establishing a Novel Baseline and Benchmark

Lake extraction from remote sensing imagery is a complex challenge due to the varied lake shapes and data noise. Current methods rely on multispectral image datasets, making it challenging to learn lake features accurately from pixel arrangements. This, in turn, affects model learning and the creation of accurate segmentation masks. This paper introduces a prompt-based dataset construction approach that provides approximate lake locations using point, box, and mask prompts. We also propose a two-stage prompt enhancement framework, LEPrompter, with prompt-based and prompt-free stages during training. The prompt-based stage employs a prompt encoder to extract prior information, integrating prompt tokens and image embedding through self- and cross-attention in the prompt decoder. Prompts are deactivated to ensure independence during inference, enabling automated lake extraction without introducing additional parameters and GFlops. Extensive experiments showcase performance improvements of our proposed approach compared to the previous state-of-the-art method. The source code is available at https://github.com/BastianChen/LEPrompter.

cs.CV↗

arXiv2024

An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuits

Audio-visual approaches involving visual inputs have laid the foundation for recent progress in speech separation. However, the optimization of the concurrent usage of auditory and visual inputs is still an active research area. Inspired by the cortico-thalamo-cortical circuit, in which the sensory processing mechanisms of different modalities modulate one another via the non-lemniscal sensory thalamus, we propose a novel cortico-thalamo-cortical neural network (CTCNet) for audio-visual speech separation (AVSS). First, the CTCNet learns hierarchical auditory and visual representations in a bottom-up manner in separate auditory and visual subnetworks, mimicking the functions of the auditory and visual cortical areas. Then, inspired by the large number of connections between cortical regions and the thalamus, the model fuses the auditory and visual information in a thalamic subnetwork through top-down connections. Finally, the model transmits this fused information back to the auditory and visual subnetworks, and the above process is repeated several times. The results of experiments on three speech separation benchmark datasets show that CTCNet remarkably outperforms existing AVSS methods with considerably fewer parameters. These results suggest that mimicking the anatomical connectome of the mammalian brain has great potential for advancing the development of deep neural networks. Project repo is https://github.com/JusperLee/CTCNet.

cs.SD↗

arXiv2024

RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation

Audio-visual speech separation methods aim to integrate different modalities to generate high-quality separated speech, thereby enhancing the performance of downstream tasks such as speech recognition. Most existing state-of-the-art (SOTA) models operate in the time domain. However, their overly simplistic approach to modeling acoustic features often necessitates larger and more computationally intensive models in order to achieve SOTA performance. In this paper, we present a novel time-frequency domain audio-visual speech separation method: Recurrent Time-Frequency Separation Network (RTFS-Net), which applies its algorithms on the complex time-frequency bins yielded by the Short-Time Fourier Transform. We model and capture the time and frequency dimensions of the audio independently using a multi-layered RNN along each dimension. Furthermore, we introduce a unique attention-based fusion technique for the efficient integration of audio and visual information, and a new mask separation approach that takes advantage of the intrinsic spectral nature of the acoustic features for a clearer separation. RTFS-Net outperforms the prior SOTA method in both inference speed and separation quality while reducing the number of parameters by 90% and MACs by 83%. This is the first time-frequency domain audio-visual speech separation method to outperform all contemporary time-domain counterparts.

cs.SD↗

arXiv2024

Ultrafast Nuclear Dynamics in Double-Core Ionized Water Molecules

Double-core-hole (DCH) states in isolated water and heavy water molecules, resulting from the sequential absorption of two x-ray photons, have been investigated. A comparison of the subsequent Auger emission spectra from the two isotopes provides direct evidence of ultrafast nuclear motion during the 1.5 fs lifetime of these DCH states. Our numerical results align well with the experimental data, providing for various DCH states an in-depth study of the dynamics responsible of the observed isotope effect.

physics.chem-ph↗

arXiv2024

Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects

Camouflaged object detection (COD) is the challenging task of identifying camouflaged objects visually blended into surroundings. Albeit achieving remarkable success, existing COD detectors still struggle to obtain precise results in some challenging cases. To handle this problem, we draw inspiration from the prey-vs-predator game that leads preys to develop better camouflage and predators to acquire more acute vision systems and develop algorithms from both the prey side and the predator side. On the prey side, we propose an adversarial training framework, Camouflageator, which introduces an auxiliary generator to generate more camouflaged objects that are harder for a COD method to detect. Camouflageator trains the generator and detector in an adversarial way such that the enhanced auxiliary generator helps produce a stronger detector. On the predator side, we introduce a novel COD method, called Internal Coherence and Edge Guidance (ICEG), which introduces a camouflaged feature coherence module to excavate the internal coherence of camouflaged objects, striving to obtain more complete segmentation results. Additionally, ICEG proposes a novel edge-guided separated calibration module to remove false predictions to avoid obtaining ambiguous boundaries. Extensive experiments show that ICEG outperforms existing COD detectors and Camouflageator is flexible to improve various COD detectors, including ICEG, which brings state-of-the-art COD performance.

cs.CV↗

arXiv2024

Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model

Illumination degradation image restoration (IDIR) techniques aim to improve the visibility of degraded images and mitigate the adverse effects of deteriorated illumination. Among these algorithms, diffusion model (DM)-based methods have shown promising performance but are often burdened by heavy computational demands and pixel misalignment issues when predicting the image-level distribution. To tackle these problems, we propose to leverage DM within a compact latent space to generate concise guidance priors and introduce a novel solution called Reti-Diff for the IDIR task. Reti-Diff comprises two key components: the Retinex-based latent DM (RLDM) and the Retinex-guided transformer (RGformer). To ensure detailed reconstruction and illumination correction, RLDM is empowered to acquire Retinex knowledge and extract reflectance and illumination priors. These priors are subsequently utilized by RGformer to guide the decomposition of image features into their respective reflectance and illumination components. Following this, RGformer further enhances and consolidates the decomposed features, resulting in the production of refined images with consistent content and robustness to handle complex degradation scenarios. Extensive experiments show that Reti-Diff outperforms existing methods on three IDIR tasks, as well as downstream applications. Code will be available at \url{https://github.com/ChunmingHe/Reti-Diff}.

cs.CV↗

arXiv2024

Failure Analysis in Next-Generation Critical Cellular Communication Infrastructures

The advent of communication technologies marks a transformative phase in critical infrastructure construction, where the meticulous analysis of failures becomes paramount in achieving the fundamental objectives of continuity, security, and availability. This survey enriches the discourse on failures, failure analysis, and countermeasures in the context of the next-generation critical communication infrastructures. Through an exhaustive examination of existing literature, we discern and categorize prominent research orientations with focuses on, namely resource depletion, security vulnerabilities, and system availability concerns. We also analyze constructive countermeasures tailored to address identified failure scenarios and their prevention. Furthermore, the survey emphasizes the imperative for standardization in addressing failures related to Artificial Intelligence (AI) within the ambit of the sixth-generation (6G) networks, accounting for the forward-looking perspective for the envisioned intelligence of 6G network architecture. By identifying new challenges and delineating future research directions, this survey can help guide stakeholders toward unexplored territories, fostering innovation and resilience in critical communication infrastructure development and failure prevention.

eess.SY↗

arXiv2024

IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation

Recent research has made significant progress in designing fusion modules for audio-visual speech separation. However, they predominantly focus on multi-modal fusion at a single temporal scale of auditory and visual features without employing selective attention mechanisms, which is in sharp contrast with the brain. To address this issue, We propose a novel model called Intra- and Inter-Attention Network (IIANet), which leverages the attention mechanism for efficient audio-visual feature fusion. IIANet consists of two types of attention blocks: intra-attention (IntraA) and inter-attention (InterA) blocks, where the InterA blocks are distributed at the top, middle and bottom of IIANet. Heavily inspired by the way how human brain selectively focuses on relevant content at various temporal scales, these blocks maintain the ability to learn modality-specific features and enable the extraction of different semantics from audio-visual features. Comprehensive experiments on three standard audio-visual separation benchmarks (LRS2, LRS3, and VoxCeleb2) demonstrate the effectiveness of IIANet, outperforming previous state-of-the-art methods while maintaining comparable inference time. In particular, the fast version of IIANet (IIANet-fast) has only 7% of CTCNet's MACs and is 40% faster than CTCNet on CPUs while achieving better separation quality, showing the great potential of attention mechanism for efficient and effective multimodal fusion.

cs.SD↗