arXiv subjects

Yuxiang Zhang

Publications and source records attributed to Yuxiang Zhang.

159 records · Page 9Linked to original sources

arXiv2022

Deepfake Detection System for the ADD Challenge Track 3.2 Based on Score Fusion

This paper describes the deepfake audio detection system submitted to the Audio Deep Synthesis Detection (ADD) Challenge Track 3.2 and gives an analysis of score fusion. The proposed system is a score-level fusion of several light convolutional neural network (LCNN) based models. Various front-ends are used as input features, including low-frequency short-time Fourier transform and Constant Q transform. Due to the complex noise and rich synthesis algorithms, it is difficult to obtain the desired performance using the training set directly. Online data augmentation methods effectively improve the robustness of fake audio detection systems. In particular, the reasons for the poor improvement of score fusion are explored through visualization of the score distributions and comparison with score distribution on another dataset. The overfitting of the model to the training set leads to extreme values of the scores and low correlation of the score distributions, which makes score fusion difficult. Fusion with partially fake audio detection system improves system performance further. The submission on track 3.2 obtained the weighted equal error rate (WEER) of 11.04\%, which is one of the best performing systems in the challenge.

eess.AS↗

arXiv2022

Language-aware Domain Generalization Network for Cross-Scene Hyperspectral Image Classification

Text information including extensive prior knowledge about land cover classes has been ignored in hyperspectral image classification (HSI) tasks. It is necessary to explore the effectiveness of linguistic mode in assisting HSI classification. In addition, the large-scale pre-training image-text foundation models have demonstrated great performance in a variety of downstream applications, including zero-shot transfer. However, most domain generalization methods have never addressed mining linguistic modal knowledge to improve the generalization performance of model. To compensate for the inadequacies listed above, a Language-aware Domain Generalization Network (LDGnet) is proposed to learn cross-domain invariant representation from cross-domain shared prior knowledge. The proposed method only trains on the source domain (SD) and then transfers the model to the target domain (TD). The dual-stream architecture including image encoder and text encoder is used to extract visual and linguistic features, in which coarse-grained and fine-grained text representations are designed to extract two levels of linguistic features. Furthermore, linguistic features are used as cross-domain shared semantic space, and visual-linguistic alignment is completed by supervised contrastive learning in semantic space. Extensive experiments on three datasets demonstrate the superiority of the proposed method when compared with state-of-the-art techniques.

cs.CV↗

arXiv2022

Single-source Domain Expansion Network for Cross-Scene Hyperspectral Image Classification

Currently, cross-scene hyperspectral image (HSI) classification has drawn increasing attention. It is necessary to train a model only on source domain (SD) and directly transferring the model to target domain (TD), when TD needs to be processed in real time and cannot be reused for training. Based on the idea of domain generalization, a Single-source Domain Expansion Network (SDEnet) is developed to ensure the reliability and effectiveness of domain extension. The method uses generative adversarial learning to train in SD and test in TD. A generator including semantic encoder and morph encoder is designed to generate the extended domain (ED) based on encoder-randomization-decoder architecture, where spatial and spectral randomization are specifically used to generate variable spatial and spectral information, and the morphological knowledge is implicitly applied as domain invariant information during domain expansion. Furthermore, the supervised contrastive learning is employed in the discriminator to learn class-wise domain invariant representation, which drives intra-class samples of SD and ED. Meanwhile, adversarial training is designed to optimize the generator to drive intra-class samples of SD and ED to be separated. Extensive experiments on two public HSI datasets and one additional multispectral image (MSI) dataset demonstrate the superiority of the proposed method when compared with state-of-the-art techniques.

cs.CV↗

arXiv2022

Towards No.1 in CLUE Semantic Matching Challenge: Pre-trained Language Model Erlangshen with Propensity-Corrected Loss

This report describes a pre-trained language model Erlangshen with propensity-corrected loss, the No.1 in CLUE Semantic Matching Challenge. In the pre-training stage, we construct a dynamic masking strategy based on knowledge in Masked Language Modeling (MLM) with whole word masking. Furthermore, by observing the specific structure of the dataset, the pre-trained Erlangshen applies propensity-corrected loss (PCL) in the fine-tuning phase. Overall, we achieve 72.54 points in F1 Score and 78.90 points in Accuracy on the test set. Our code is publicly available at: https://github.com/IDEA-CCNL/Fengshenbang-LM/tree/hf-ds/fengshen/examples/clue_sim.

cs.CL↗

arXiv2022

SASV Based on Pre-trained ASV System and Integrated Scoring Module

Based on the assumption that there is a correlation between anti-spoofing and speaker verification, a Total-Divide-Total integrated Spoofing-Aware Speaker Verification (SASV) system based on pre-trained automatic speaker verification (ASV) system and integrated scoring module is proposed and submitted to the SASV 2022 Challenge. The training and scoring of ASV and anti-spoofing countermeasure (CM) in current SASV systems are relatively independent, ignoring the correlation. In this paper, by leveraging the correlation between the two tasks, an integrated SASV system can be obtained by simply training a few more layers on the basis of the baseline pre-trained ASV subsystem. The features in pre-trained ASV system are utilized for logical access spoofing speech detection. Further, speaker embeddings extracted by the pre-trained ASV system are used to improve the performance of the CM. The integrated scoring module takes the embeddings of the ASV and anti-spoofing branches as input and preserves the correlation between the two tasks through matrix operations to produce integrated SASV scores. Submitted primary system achieved equal error rate (EER) of 3.07\% on the development dataset of the SASV 2022 Challenge and 4.30\% on the evaluation part, which is a 25\% improvement over the baseline systems.

eess.AS↗

arXiv2022

Adversarial Training-Aided Time-Varying Channel Prediction for TDD/FDD Systems

In this paper, a time-varying channel prediction method based on conditional generative adversarial network (CPcGAN) is proposed for time division duplexing/frequency division duplexing (TDD/FDD) systems. CPcGAN utilizes a discriminator to calculate the divergence between the predicted downlink channel state information (CSI) and the real sample distributions under a conditional constraint that is previous uplink CSI. The generator of CPcGAN learns the function relationship between the conditional constraint and the predicted downlink CSI and reduces the divergence between predicted CSI and real CSI. The capability of CPcGAN fitting data distribution can capture the time-varying and multipath characteristics of the channel well. Considering the propagation characteristics of real channel, we further develop a channel prediction error indicator to determine whether the generator reaches the best state. Simulations show that the CPcGAN can obtain higher prediction accuracy and lower system bit error rate than the existing methods under the same user speeds.

eess.SP↗

arXiv2022

The HCCL-DKU system for fake audio generation task of the 2022 ICASSP ADD Challenge

The voice conversion task is to modify the speaker identity of continuous speech while preserving the linguistic content. Generally, the naturalness and similarity are two main metrics for evaluating the conversion quality, which has been improved significantly in recent years. This paper presents the HCCL-DKU entry for the fake audio generation task of the 2022 ICASSP ADD challenge. We propose a novel ppg-based voice conversion model that adopts a fully end-to-end structure. Experimental results show that the proposed method outperforms other conversion models, including Tacotron-based and Fastspeech-based models, on conversion quality and spoofing performance against anti-spoofing systems. In addition, we investigate several post-processing methods for better spoofing power. Finally, we achieve second place with a deception success rate of 0.916 in the ADD challenge.

cs.SD↗

arXiv2021

DeepMultiCap: Performance Capture of Multiple Characters Using Sparse Multiview Cameras

We propose DeepMultiCap, a novel method for multi-person performance capture using sparse multi-view cameras. Our method can capture time varying surface details without the need of using pre-scanned template models. To tackle with the serious occlusion challenge for close interacting scenes, we combine a recently proposed pixel-aligned implicit function with parametric model for robust reconstruction of the invisible surface areas. An effective attention-aware module is designed to obtain the fine-grained geometry details from multi-view images, where high-fidelity results can be generated. In addition to the spatial attention method, for video inputs, we further propose a novel temporal fusion method to alleviate the noise and temporal inconsistencies for moving character reconstruction. For quantitative evaluation, we contribute a high quality multi-person dataset, MultiHuman, which consists of 150 static scenes with different levels of occlusions and ground truth 3D human models. Experimental results demonstrate the state-of-the-art performance of our method and the well generalization to real multiview video data, which outperforms the prior works by a large margin.

cs.CV↗

arXiv2021

Lightweight Multi-person Total Motion Capture Using Sparse Multi-view Cameras

Multi-person total motion capture is extremely challenging when it comes to handle severe occlusions, different reconstruction granularities from body to face and hands, drastically changing observation scales and fast body movements. To overcome these challenges above, we contribute a lightweight total motion capture system for multi-person interactive scenarios using only sparse multi-view cameras. By contributing a novel hand and face bootstrapping algorithm, our method is capable of efficient localization and accurate association of the hands and faces even on severe occluded occasions. We leverage both pose regression and keypoints detection methods and further propose a unified two-stage parametric fitting method for achieving pixel-aligned accuracy. Moreover, for extremely self-occluded poses and close interactions, a novel feedback mechanism is proposed to propagate the pixel-aligned reconstructions into the next frame for more accurate association. Overall, we propose the first light-weight total capture system and achieves fast, robust and accurate multi-person total motion capture performance. The results and experiments show that our method achieves more accurate results than existing methods under sparse-view setups.

cs.CV↗

arXiv2020

Geometry-guided Dense Perspective Network for Speech-Driven Facial Animation

Realistic speech-driven 3D facial animation is a challenging problem due to the complex relationship between speech and face. In this paper, we propose a deep architecture, called Geometry-guided Dense Perspective Network (GDPnet), to achieve speaker-independent realistic 3D facial animation. The encoder is designed with dense connections to strengthen feature propagation and encourage the re-use of audio features, and the decoder is integrated with an attention mechanism to adaptively recalibrate point-wise feature responses by explicitly modeling interdependencies between different neuron units. We also introduce a non-linear face reconstruction representation as a guidance of latent space to obtain more accurate deformation, which helps solve the geometry-related deformation and is good for generalization across subjects. Huber and HSIC (Hilbert-Schmidt Independence Criterion) constraints are adopted to promote the robustness of our model and to better exploit the non-linear and high-order correlations. Experimental results on the public dataset and real scanned dataset validate the superiority of our proposed GDPnet compared with state-of-the-art model.

cs.GR↗

arXiv2020

4D Association Graph for Realtime Multi-person Motion Capture Using Multiple Video Cameras

This paper contributes a novel realtime multi-person motion capture algorithm using multiview video inputs. Due to the heavy occlusions in each view, joint optimization on the multiview images and multiple temporal frames is indispensable, which brings up the essential challenge of realtime efficiency. To this end, for the first time, we unify per-view parsing, cross-view matching, and temporal tracking into a single optimization framework, i.e., a 4D association graph that each dimension (image space, viewpoint and time) can be treated equally and simultaneously. To solve the 4D association graph efficiently, we further contribute the idea of 4D limb bundle parsing based on heuristic searching, followed with limb bundle assembling by proposing a bundle Kruskal's algorithm. Our method enables a realtime online motion capture system running at 30fps using 5 cameras on a 5-person scene. Benefiting from the unified parsing, matching and tracking constraints, our method is robust to noisy detection, and achieves high-quality online pose reconstruction quality. The proposed method outperforms the state-of-the-art method quantitatively without using high-level appearance information. We also contribute a multiview video dataset synchronized with a marker-based motion capture system for scientific evaluation.

cs.CV↗

arXiv2016

Training Bit Fully Convolutional Network for Fast Semantic Segmentation

Fully convolutional neural networks give accurate, per-pixel prediction for input images and have applications like semantic segmentation. However, a typical FCN usually requires lots of floating point computation and large run-time memory, which effectively limits its usability. We propose a method to train Bit Fully Convolution Network (BFCN), a fully convolutional neural network that has low bit-width weights and activations. Because most of its computation-intensive convolutions are accomplished between low bit-width numbers, a BFCN can be accelerated by an efficient bit-convolution implementation. On CPU, the dot product operation between two bit vectors can be reduced to bitwise operations and popcounts, which can offer much higher throughput than 32-bit multiplications and additions. To validate the effectiveness of BFCN, we conduct experiments on the PASCAL VOC 2012 semantic segmentation task and Cityscapes. Our BFCN with 1-bit weights and 2-bit activations, which runs 7.8x faster on CPU or requires less than 1\% resources on FPGA, can achieve comparable performance as the 32-bit counterpart.

cs.CV↗

arXiv2015

An Open Source Testing Tool for Evaluating Handwriting Input Methods

This paper presents an open source tool for testing the recognition accuracy of Chinese handwriting input methods. The tool consists of two modules, namely the PC and Android mobile client. The PC client reads handwritten samples in the computer, and transfers them individually to the Android client in accordance with the socket communication protocol. After the Android client receives the data, it simulates the handwriting on screen of client device, and triggers the corresponding handwriting recognition method. The recognition accuracy is recorded by the Android client. We present the design principles and describe the implementation of the test platform. We construct several test datasets for evaluating different handwriting recognition systems, and conduct an objective and comprehensive test using six Chinese handwriting input methods with five datasets. The test results for the recognition accuracy are then compared and analyzed.

cs.HC↗

arXiv2012

Information gain versus coupling strength in quantum measurements

We investigate the relationship between the information gain and the interaction strength between the quantum system and the measuring device. A strategy is proposed to calculate the information gain of the measuring device as the coupling strength is a variable. For qubit systems, we prove that the information gain increases monotonically with the coupling strength. It is obtained that the information gain of the projective measurement along the x-direction reduces with the increasing of the measurement strength along the z-direction, and a complementarity of information gain in the measurements along those two directions is presented.

quant-ph↗

arXiv2011

Quantum measurements with preselection and postselection

We study quantum measurement with preselection and postselection, and derive the precise expressions of the measurement results without any restriction on the coupling strength between the system and the measuring device. For a qubit system, we derive the maximum pointer shifts by choosing appropriate initial and finial states. A significant amplification effect is obtained when the interaction between the system and the measuring device is very weak, and typical ideal quantum measurement results are obtained when the interaction is strong. The improvement of the signal-tonoise ratio (SNR) and the enhancement of the measurement sensitivity (MS) by weak measurements are studied. Without considering the probability decrease due to postselection, the SNR and the MS can be both significantly improved by weak measurements; however, neither SNR nor MS can be effectively improved when the probability decrease is considered.

quant-ph↗