Searcharxiv⌕ Search

arXiv subjects

Tao Wang

Publications and source records attributed to Tao Wang.

At least 451 records · Page 25Linked to original sources
arXiv2024

Research on Multilingual Natural Scene Text Detection Algorithm

Natural scene text detection is a significant challenge in computer vision, with tremendous potential applications in multilingual, diverse, and complex text scenarios. We propose a multilingual text detection model to address the issues of low accuracy and high difficulty in detecting multilingual text in natural scenes. In response to the challenges posed by multilingual text images with multiple character sets and various font styles, we introduce the SFM Swin Transformer feature extraction network to enhance the model's robustness in detecting characters and fonts across different languages. Dealing with the considerable variation in text scales and complex arrangements in natural scene text images, we present the AS-HRFPN feature fusion network by incorporating an Adaptive Spatial Feature Fusion module and a Spatial Pyramid Pooling module. The feature fusion network improvements enhance the model's ability to detect text sizes and orientations. Addressing diverse backgrounds and font variations in multilingual scene text images is a challenge for existing methods. Limited local receptive fields hinder detection performance. To overcome this, we propose a Global Semantic Segmentation Branch, extracting and preserving global features for more effective text detection, aligning with the need for comprehensive information. In this study, we collected and built a real-world multilingual natural scene text image dataset and conducted comprehensive experiments and analyses. The experimental results demonstrate that the proposed algorithm achieves an F-measure of 85.02\%, which is 4.71\% higher than the baseline model. We also conducted extensive cross-dataset validation on MSRA-TD500, ICDAR2017MLT, and ICDAR2015 datasets to verify the generality of our approach. The code and dataset can be found at https://github.com/wangmelon/CEMLT.

cs.CV↗
arXiv2024

VSFormer: Visual-Spatial Fusion Transformer for Correspondence Pruning

Correspondence pruning aims to find correct matches (inliers) from an initial set of putative correspondences, which is a fundamental task for many applications. The process of finding is challenging, given the varying inlier ratios between scenes/image pairs due to significant visual differences. However, the performance of the existing methods is usually limited by the problem of lacking visual cues (\eg texture, illumination, structure) of scenes. In this paper, we propose a Visual-Spatial Fusion Transformer (VSFormer) to identify inliers and recover camera poses accurately. Firstly, we obtain highly abstract visual cues of a scene with the cross attention between local features of two-view images. Then, we model these visual cues and correspondences by a joint visual-spatial fusion module, simultaneously embedding visual cues into correspondences for pruning. Additionally, to mine the consistency of correspondences, we also design a novel module that combines the KNN-based graph and the transformer, effectively capturing both local and global contexts. Extensive experiments have demonstrated that the proposed VSFormer outperforms state-of-the-art methods on outdoor and indoor benchmarks. Our code is provided at the following repository: https://github.com/sugar-fly/VSFormer.

cs.CV↗
arXiv2024

Dual Teacher Knowledge Distillation with Domain Alignment for Face Anti-spoofing

Face recognition systems have raised concerns due to their vulnerability to different presentation attacks, and system security has become an increasingly critical concern. Although many face anti-spoofing (FAS) methods perform well in intra-dataset scenarios, their generalization remains a challenge. To address this issue, some methods adopt domain adversarial training (DAT) to extract domain-invariant features. However, the competition between the encoder and the domain discriminator can cause the network to be difficult to train and converge. In this paper, we propose a domain adversarial attack (DAA) method to mitigate the training instability problem by adding perturbations to the input images, which makes them indistinguishable across domains and enables domain alignment. Moreover, since models trained on limited data and types of attacks cannot generalize well to unknown attacks, we propose a dual perceptual and generative knowledge distillation framework for face anti-spoofing that utilizes pre-trained face-related models containing rich face priors. Specifically, we adopt two different face-related models as teachers to transfer knowledge to the target student model. The pre-trained teacher models are not from the task of face anti-spoofing but from perceptual and generative tasks, respectively, which implicitly augment the data. By combining both DAA and dual-teacher knowledge distillation, we develop a dual teacher knowledge distillation with domain alignment framework (DTDA) for face anti-spoofing. The advantage of our proposed method has been verified through extensive ablation studies and comparison with state-of-the-art methods on public datasets across multiple protocols.

cs.CV↗
arXiv2023

Minimally-Supervised Speech Synthesis with Conditional Diffusion Model and Language Model: A Comparative Study of Semantic Coding

Recently, there has been a growing interest in text-to-speech (TTS) methods that can be trained with minimal supervision by combining two types of discrete speech representations and using two sequence-to-sequence tasks to decouple TTS. However, existing methods suffer from three problems: the high dimensionality and waveform distortion of discrete speech representations, the prosodic averaging problem caused by the duration prediction model in non-autoregressive frameworks, and the information redundancy and dimension explosion problems of existing semantic encoding methods. To address these problems, three progressive methods are proposed. First, we propose Diff-LM-Speech, an autoregressive structure consisting of a language model and diffusion models, which models the semantic embedding into the mel-spectrogram based on a diffusion model to achieve higher audio quality. We also introduce a prompt encoder structure based on a variational autoencoder and a prosody bottleneck to improve prompt representation ability. Second, we propose Tetra-Diff-Speech, a non-autoregressive structure consisting of four diffusion model-based modules that design a duration diffusion model to achieve diverse prosodic expressions. Finally, we propose Tri-Diff-Speech, a non-autoregressive structure consisting of three diffusion model-based modules that verify the non-necessity of existing semantic encoding models and achieve the best results. Experimental results show that our proposed methods outperform baseline methods. We provide a website with audio samples.

cs.SD↗
arXiv2023

Learning Speech Representation From Contrastive Token-Acoustic Pretraining

For fine-grained generation and recognition tasks such as minimally-supervised text-to-speech (TTS), voice conversion (VC), and automatic speech recognition (ASR), the intermediate representations extracted from speech should serve as a "bridge" between text and acoustic information, containing information from both modalities. The semantic content is emphasized, while the paralinguistic information such as speaker identity and acoustic details should be de-emphasized. However, existing methods for extracting fine-grained intermediate representations from speech suffer from issues of excessive redundancy and dimension explosion. Contrastive learning is a good method for modeling intermediate representations from two modalities. However, existing contrastive learning methods in the audio field focus on extracting global descriptive information for downstream audio classification tasks, making them unsuitable for TTS, VC, and ASR tasks. To address these issues, we propose a method named "Contrastive Token-Acoustic Pretraining (CTAP)", which uses two encoders to bring phoneme and speech into a joint multimodal space, learning how to connect phoneme and speech at the frame level. The CTAP model is trained on 210k speech and phoneme pairs, achieving minimally-supervised TTS, VC, and ASR. The proposed CTAP method offers a promising solution for fine-grained generation and recognition downstream tasks in speech processing. We provide a website with audio samples.

eess.AS↗
arXiv2023

Half-Truth: A Partially Fake Audio Detection Dataset

Diverse promising datasets have been designed to hold back the development of fake audio detection, such as ASVspoof databases. However, previous datasets ignore an attacking situation, in which the hacker hides some small fake clips in real speech audio. This poses a serious threat since that it is difficult to distinguish the small fake clip from the whole speech utterance. Therefore, this paper develops such a dataset for half-truth audio detection (HAD). Partially fake audio in the HAD dataset involves only changing a few words in an utterance.The audio of the words is generated with the very latest state-of-the-art speech synthesis technology. We can not only detect fake uttrances but also localize manipulated regions in a speech using this dataset. Some benchmark results are presented on this dataset. The results show that partially fake audio presents much more challenging than fully fake audio for fake audio detection. The HAD dataset is publicly available: https://zenodo.org/records/10377492.

cs.SD↗
arXiv2023

IoTGAN: GAN Powered Camouflage Against Machine Learning Based IoT Device Identification

With the proliferation of IoT devices, researchers have developed a variety of IoT device identification methods with the assistance of machine learning. Nevertheless, the security of these identification methods mostly depends on collected training data. In this research, we propose a novel attack strategy named IoTGAN to manipulate an IoT device's traffic such that it can evade machine learning based IoT device identification. In the development of IoTGAN, we have two major technical challenges: (i) How to obtain the discriminative model in a black-box setting, and (ii) How to add perturbations to IoT traffic through the manipulative model, so as to evade the identification while not influencing the functionality of IoT devices. To address these challenges, a neural network based substitute model is used to fit the target model in black-box settings, it works as a discriminative model in IoTGAN. A manipulative model is trained to add adversarial perturbations into the IoT device's traffic to evade the substitute model. Experimental results show that IoTGAN can successfully achieve the attack goals. We also develop efficient countermeasures to protect machine learning based IoT device identification from been undermined by IoTGAN.

cs.CR↗
arXiv2023

A Survey on Post-Quantum Cryptography: State-of-the-Art and Challenges

The paper explains that post-quantum cryptography is necessary due to the introduction of quantum computing causing certain algorithms to be broken. We analyze the different types of post-quantum cryptography, quantum cryptography and quantum-resistant cryptography, to provide a thorough understanding of the current solutions to the problems and their limitations. We explain the current state of quantum computing and how it has changed over time while discussing possible attacks on both types of post-quantum cryptography. Next, current post-quantum algorithms are discussed, and implementations are demonstrated. Lastly, we conclude that due to quantum cryptography's present limitations it is not a viable solution like it is often presented to be and that it is currently better to use quantum-resistant cryptography.

cs.CR↗
arXiv2023

The Evolution of Keylogger Technologies: A Survey from Historical Origins to Emerging Opportunities

As the digital world evolves, so do the threats to our security do too. Keyloggers were once a large threat to the cyber world. Though undergoing many transformations alongside the technological advancements of today, it is important to raise questions about the importance of Anti-Keyloggers in our current state of cyber security. This survey dives into the historical evolution of Keyloggers and investigates their current day forms. Within this inspection of Keyloggers, we must propose whether Anti-Keyloggers serve a purpose to this ever-changing landscape before us or if emerging strategies have rendered them obsolete.

cs.CR↗
arXiv2023

The Cascaded Forward Algorithm for Neural Network Training

Backpropagation algorithm has been widely used as a mainstream learning procedure for neural networks in the past decade, and has played a significant role in the development of deep learning. However, there exist some limitations associated with this algorithm, such as getting stuck in local minima and experiencing vanishing/exploding gradients, which have led to questions about its biological plausibility. To address these limitations, alternative algorithms to backpropagation have been preliminarily explored, with the Forward-Forward (FF) algorithm being one of the most well-known. In this paper we propose a new learning framework for neural networks, namely Cascaded Forward (CaFo) algorithm, which does not rely on BP optimization as that in FF. Unlike FF, our framework directly outputs label distributions at each cascaded block, which does not require generation of additional negative samples and thus leads to a more efficient process at both training and testing. Moreover, in our framework each block can be trained independently, so it can be easily deployed into parallel acceleration systems. The proposed method is evaluated on four public image classification benchmarks, and the experimental results illustrate significant improvement in prediction accuracy in comparison with the baseline.

cs.CV↗
arXiv2023

Blind Face Restoration for Under-Display Camera via Dictionary Guided Transformer

By hiding the front-facing camera below the display panel, Under-Display Camera (UDC) provides users with a full-screen experience. However, due to the characteristics of the display, images taken by UDC suffer from significant quality degradation. Methods have been proposed to tackle UDC image restoration and advances have been achieved. There are still no specialized methods and datasets for restoring UDC face images, which may be the most common problem in the UDC scene. To this end, considering color filtering, brightness attenuation, and diffraction in the imaging process of UDC, we propose a two-stage network UDC Degradation Model Network named UDC-DMNet to synthesize UDC images by modeling the processes of UDC imaging. Then we use UDC-DMNet and high-quality face images from FFHQ and CelebA-Test to create UDC face training datasets FFHQ-P/T and testing datasets CelebA-Test-P/T for UDC face restoration. We propose a novel dictionary-guided transformer network named DGFormer. Introducing the facial component dictionary and the characteristics of the UDC image in the restoration makes DGFormer capable of addressing blind face restoration in UDC scenarios. Experiments show that our DGFormer and UDC-DMNet achieve state-of-the-art performance.

cs.CV↗
arXiv2023

Learning to Skip for Language Modeling

Overparameterized large-scale language models have impressive generalization performance of in-context few-shot learning. However, most language models allocate the same amount of parameters or computation to each token, disregarding the complexity or importance of the input data. We argue that in language model pretraining, a variable amount of computation should be assigned to different tokens, and this can be efficiently achieved via a simple routing mechanism. Different from conventional early stopping techniques where tokens can early exit at only early layers, we propose a more general method that dynamically skips the execution of a layer (or module) for any input token with a binary router. In our extensive evaluation across 24 NLP tasks, we demonstrate that the proposed method can significantly improve the 1-shot performance compared to other competitive baselines only at mild extra cost for inference.

cs.CL↗
arXiv2023

Boost Adversarial Transferability by Uniform Scale and Mix Mask Method

Adversarial examples generated from surrogate models often possess the ability to deceive other black-box models, a property known as transferability. Recent research has focused on enhancing adversarial transferability, with input transformation being one of the most effective approaches. However, existing input transformation methods suffer from two issues. Firstly, certain methods, such as the Scale-Invariant Method, employ exponentially decreasing scale invariant parameters that decrease the adaptability in generating effective adversarial examples across multiple scales. Secondly, most mixup methods only linearly combine candidate images with the source image, leading to reduced features blending effectiveness. To address these challenges, we propose a framework called Uniform Scale and Mix Mask Method (US-MM) for adversarial example generation. The Uniform Scale approach explores the upper and lower boundaries of perturbation with a linear factor, minimizing the negative impact of scale copies. The Mix Mask method introduces masks into the mixing process in a nonlinear manner, significantly improving the effectiveness of mixing strategies. Ablation experiments are conducted to validate the effectiveness of each component in US-MM and explore the effect of hyper-parameters. Empirical evaluations on standard ImageNet datasets demonstrate that US-MM achieves an average of 7% better transfer attack success rate compared to state-of-the-art methods.

cs.CV↗
arXiv2023

Semantic-aware Consistency Network for Cloth-changing Person Re-Identification

Cloth-changing Person Re-Identification (CC-ReID) is a challenging task that aims to retrieve the target person across multiple surveillance cameras when clothing changes might happen. Despite recent progress in CC-ReID, existing approaches are still hindered by the interference of clothing variations since they lack effective constraints to keep the model consistently focused on clothing-irrelevant regions. To address this issue, we present a Semantic-aware Consistency Network (SCNet) to learn identity-related semantic features by proposing effective consistency constraints. Specifically, we generate the black-clothing image by erasing pixels in the clothing area, which explicitly mitigates the interference from clothing variations. In addition, to fully exploit the fine-grained identity information, a head-enhanced attention module is introduced, which learns soft attention maps by utilizing the proposed part-based matching loss to highlight head information. We further design a semantic consistency loss to facilitate the learning of high-level identity-related semantic features, forcing the model to focus on semantically consistent cloth-irrelevant regions. By using the consistency constraint, our model does not require any extra auxiliary segmentation module to generate the black-clothing image or locate the head region during the inference stage. Extensive experiments on four cloth-changing person Re-ID datasets (LTCC, PRCC, Vc-Clothes, and DeepChange) demonstrate that our proposed SCNet makes significant improvements over prior state-of-the-art approaches. Our code is available at: https://github.com/Gpn-star/SCNet.

cs.CV↗
arXiv2023

Complementary Advantages of ChatGPTs and Human Readers in Reasoning: Evidence from English Text Reading Comprehension

ChatGPT has shown its great power in text processing, including its reasoning ability from text reading. However, there has not been any direct comparison between human readers and ChatGPT in reasoning ability related to text reading. This study was undertaken to investigate how ChatGPTs (i.e., ChatGPT and ChatGPT Plus) and Chinese senior school students as ESL learners exhibited their reasoning ability from English narrative texts. Additionally, we compared the two ChatGPTs in the reasoning performances when commands were updated elaborately. The whole study was composed of three reasoning tests: Test 1 for commonsense inference, Test 2 for emotional inference, and Test 3 for causal inference. The results showed that in Test 1, the students outdid the two ChatGPT versions in local-culture-related inferences but performed worse than the chatbots in daily-life inferences. In Test 2, ChatGPT Plus excelled whereas ChatGPT lagged behind in accuracy. In association with both accuracy and frequency of correct responses, the students were inferior to the two chatbots. Compared with ChatGPTs' better performance in positive emotions, the students showed their superiority in inferring negative emotions. In Test 3, the students demonstrated better logical analysis, outdoing both chatbots. In updating command condition, ChatGPT Plus displayed good causal reasoning ability while ChatGPT kept unchanged. Our study reveals that human readers and ChatGPTs have their respective advantages and disadvantages in drawing inferences from text reading comprehension, unlocking a complementary relationship in text-based reasoning.

cs.CL↗
arXiv2023

Pseudo Label-Guided Data Fusion and Output Consistency for Semi-Supervised Medical Image Segmentation

Supervised learning algorithms based on Convolutional Neural Networks have become the benchmark for medical image segmentation tasks, but their effectiveness heavily relies on a large amount of labeled data. However, annotating medical image datasets is a laborious and time-consuming process. Inspired by semi-supervised algorithms that use both labeled and unlabeled data for training, we propose the PLGDF framework, which builds upon the mean teacher network for segmenting medical images with less annotation. We propose a novel pseudo-label utilization scheme, which combines labeled and unlabeled data to augment the dataset effectively. Additionally, we enforce the consistency between different scales in the decoder module of the segmentation network and propose a loss function suitable for evaluating the consistency. Moreover, we incorporate a sharpening operation on the predicted results, further enhancing the accuracy of the segmentation. Extensive experiments on three publicly available datasets demonstrate that the PLGDF framework can largely improve performance by incorporating the unlabeled data. Meanwhile, our framework yields superior performance compared to six state-of-the-art semi-supervised learning methods. The codes of this study are available at https://github.com/ortonwang/PLGDF.

eess.IV↗
arXiv2023

The \ion{H}{I}-rich Ultra-diffuse Galaxies follow the Extended Schmidt Law

The \ion{H}{I}-rich ultra-diffuse galaxies (HUDGs) offer a unique case for studies of star formation laws (SFLs) as they host low star formation efficiency (SFE) and low-metallicity environments where gas is predominantly atomic. We collect a sample of six HUDGs in the field and investigate their location in the extended Schmidt law($Σ_{\text {SFR }} \propto \left(Σ_{\text{star}}^{0.5} Σ_{\text{gas}}\right)^{1.09}$). They are consistent with this relationship well (with deviations of only 1.1 sigma). Furthermore, we find that HUDGs follow the tight correlation between the hydrostatic pressure in the galaxy mid-plane and the quantity on the x-axis ($\rm log(Σ_{star}^{0.5}Σ_{gas})$) of the extended Schmidt law. This result indicates that these HUDGs can be self-regulated systems that reach the dynamical and thermal equilibrium. In this framework, the stellar gravity compresses the disk vertically and counteracts the gas pressure in the galaxy mid-plane to regulate the star formation as suggested by some theoretical models.

astro-ph.GA↗