arXiv subjects

Feng Jiang

Publications and source records attributed to Feng Jiang.

At least 109 records · Page 6Linked to original sources

arXiv2023

Topic-driven Distant Supervision Framework for Macro-level Discourse Parsing

Discourse parsing, the task of analyzing the internal rhetorical structure of texts, is a challenging problem in natural language processing. Despite the recent advances in neural models, the lack of large-scale, high-quality corpora for training remains a major obstacle. Recent studies have attempted to overcome this limitation by using distant supervision, which utilizes results from other NLP tasks (e.g., sentiment polarity, attention matrix, and segmentation probability) to parse discourse trees. However, these methods do not take into account the differences between in-domain and out-of-domain tasks, resulting in lower performance and inability to leverage the high-quality in-domain data for further improvement. To address these issues, we propose a distant supervision framework that leverages the relations between topic structure and rhetorical structure. Specifically, we propose two distantly supervised methods, based on transfer learning and the teacher-student model, that narrow the gap between in-domain and out-of-domain tasks through label mapping and oracle annotation. Experimental results on the MCDTB and RST-DT datasets show that our methods achieve the best performance in both distant-supervised and supervised scenarios.

cs.CL↗

arXiv2023

Topic Shift Detection in Chinese Dialogues: Corpus and Benchmark

Dialogue topic shift detection is to detect whether an ongoing topic has shifted or should shift in a dialogue, which can be divided into two categories, i.e., response-known task and response-unknown task. Currently, only a few investigated the latter, because it is still a challenge to predict the topic shift without the response information. In this paper, we first annotate a Chinese Natural Topic Dialogue (CNTD) corpus consisting of 1308 dialogues to fill the gap in the Chinese natural conversation topic corpus. And then we focus on the response-unknown task and propose a teacher-student framework based on hierarchical contrastive learning to predict the topic shift without the response. Specifically, the response at high-level teacher-student is introduced to build the contrastive learning between the response and the context, while the label contrastive learning is constructed at low-level student. The experimental results on our Chinese CNTD and English TIAGE show the effectiveness of our proposed model.

cs.CL↗

arXiv2023

Multi-to-Single Knowledge Distillation for Point Cloud Semantic Segmentation

3D point cloud semantic segmentation is one of the fundamental tasks for environmental understanding. Although significant progress has been made in recent years, the performance of classes with few examples or few points is still far from satisfactory. In this paper, we propose a novel multi-to-single knowledge distillation framework for the 3D point cloud semantic segmentation task to boost the performance of those hard classes. Instead of fusing all the points of multi-scans directly, only the instances that belong to the previously defined hard classes are fused. To effectively and sufficiently distill valuable knowledge from multi-scans, we leverage a multilevel distillation framework, i.e., feature representation distillation, logit distillation, and affinity distillation. We further develop a novel instance-aware affinity distillation algorithm for capturing high-level structural knowledge to enhance the distillation efficacy for hard classes. Finally, we conduct experiments on the SemanticKITTI dataset, and the results on both the validation and test sets demonstrate that our method yields substantial improvements compared with the baseline method. The code is available at \Url{https://github.com/skyshoumeng/M2SKD}.

cs.CV↗

arXiv2023

Knowledge Distillation from 3D to Bird's-Eye-View for LiDAR Semantic Segmentation

LiDAR point cloud segmentation is one of the most fundamental tasks for autonomous driving scene understanding. However, it is difficult for existing models to achieve both high inference speed and accuracy simultaneously. For example, voxel-based methods perform well in accuracy, while Bird's-Eye-View (BEV)-based methods can achieve real-time inference. To overcome this issue, we develop an effective 3D-to-BEV knowledge distillation method that transfers rich knowledge from 3D voxel-based models to BEV-based models. Our framework mainly consists of two modules: the voxel-to-pillar distillation module and the label-weight distillation module. Voxel-to-pillar distillation distills sparse 3D features to BEV features for middle layers to make the BEV-based model aware of more structural and geometric information. Label-weight distillation helps the model pay more attention to regions with more height information. Finally, we conduct experiments on the SemanticKITTI dataset and Paris-Lille-3D. The results on SemanticKITTI show more than 5% improvement on the test set, especially for classes such as motorcycle and person, with more than 15% improvement. The code can be accessed at https://github.com/fengjiang5/Knowledge-Distillation-from-Cylinder3D-to-PolarNet.

cs.CV↗

arXiv2023

Phoenix: Democratizing ChatGPT across Languages

This paper presents our efforts to democratize ChatGPT across language. We release a large language model "Phoenix", achieving competitive performance among open-source English and Chinese models while excelling in languages with limited resources (covering both Latin and non-Latin languages). We believe this work will be beneficial to make ChatGPT more accessible, especially in countries where people cannot use ChatGPT due to restrictions from OpenAI or local goverments. Our data, code, and models are available at https://github.com/FreedomIntelligence/LLMZoo.

cs.CL↗

arXiv2023

Hierarchical Interactive Reconstruction Network For Video Compressive Sensing

Deep network-based image and video Compressive Sensing(CS) has attracted increasing attentions in recent years. However, in the existing deep network-based CS methods, a simple stacked convolutional network is usually adopted, which not only weakens the perception of rich contextual prior knowledge, but also limits the exploration of the correlations between temporal video frames. In this paper, we propose a novel Hierarchical InTeractive Video CS Reconstruction Network(HIT-VCSNet), which can cooperatively exploit the deep priors in both spatial and temporal domains to improve the reconstruction quality. Specifically, in the spatial domain, a novel hierarchical structure is designed, which can hierarchically extract deep features from keyframes and non-keyframes. In the temporal domain, a novel hierarchical interaction mechanism is proposed, which can cooperatively learn the correlations among different frames in the multiscale space. Extensive experiments manifest that the proposed HIT-VCSNet outperforms the existing state-of-the-art video and image CS methods in a large margin.

cs.CV↗

arXiv2023

ActiveSelfHAR: Incorporating Self Training into Active Learning to Improve Cross-Subject Human Activity Recognition

Deep learning-based human activity recognition (HAR) methods have shown great promise in the applications of smart healthcare systems and wireless body sensor network (BSN). Despite their demonstrated performance in laboratory settings, the real-world implementation of such methods is still hindered by the cross-subject issue when adapting to new users. To solve this issue, we propose ActiveSelfHAR, a framework that combines active learning's benefit of sparsely acquiring data with actual labels and self- training's benefit of effectively utilizing unlabeled data to enable the deep model to adapt to the target domain, i.e., the new users. In this framework, the model trained in the last iteration or the source domain is first utilized to generate pseudo labels of the target-domain samples and construct a self-training set based on the confidence score. Second, we propose to use the spatio-temporal relationships among the samples in the non-self-training set to augment the core set selected by active learning. Finally, we combine the self-training set and the augmented core set to fine-tune the model. We demonstrate our method by comparing it with state-of-the-art methods on two IMU-based datasets and an EMG-based dataset. Our method presents similar HAR accuracies with the upper bound, i.e. fully supervised fine-tuning with less than 1\% labeled data of the target dataset and significantly improves data efficiency and time cost. Our work highlights the potential of implementing user-independent HAR methods into smart healthcare systems and BSN.

cs.HC↗

arXiv2022

Solid-state Janus nanoprecipitation enables amorphous-like heat conduction in crystalline Mg3Sb2-based thermoelectric materials

Solid-state precipitation can be used to tailor materials properties, ranging from ferromagnets and catalysts to mechanical strengthening and energy storage. Thermoelectric properties can be modified by precipitation to enhance phonon scattering while retaining charge-carrier transmission. Here, we uncover unconventional dual Janus-type nanoprecipitates in Mg3Sb1.5Bi0.5 formed by side-by-side Bi- and Ge-rich appendages, in contrast to separate nanoprecipitate formation. These Janus nanoprecipitates result from local co-melting of Bi and Ge during sintering, enabling an amorphous-like lattice thermal conductivity. A precipitate size effect on phonon scattering is observed due to the balance between alloy-disorder and nanoprecipitate scattering. The thermoelectric figure-of-merit ZT reaches 0.6 near room temperature and 1.6 at 773 K. The Janus nanoprecipitation can be introduced into other materials and may act as a general property-tailoring mechanism.

cond-mat.mtrl-sci↗

arXiv2021

Image Compressed Sensing Using Non-local Neural Network

Deep network-based image Compressed Sensing (CS) has attracted much attention in recent years. However, the existing deep network-based CS schemes either reconstruct the target image in a block-by-block manner that leads to serious block artifacts or train the deep network as a black box that brings about limited insights of image prior knowledge. In this paper, a novel image CS framework using non-local neural network (NL-CSNet) is proposed, which utilizes the non-local self-similarity priors with deep network to improve the reconstruction quality. In the proposed NL-CSNet, two non-local subnetworks are constructed for utilizing the non-local self-similarity priors in the measurement domain and the multi-scale feature domain respectively. Specifically, in the subnetwork of measurement domain, the long-distance dependencies between the measurements of different image blocks are established for better initial reconstruction. Analogically, in the subnetwork of multi-scale feature domain, the affinities between the dense feature representations are explored in the multi-scale space for deep reconstruction. Furthermore, a novel loss function is developed to enhance the coupling between the non-local representations, which also enables an end-to-end training of NL-CSNet. Extensive experiments manifest that NL-CSNet outperforms existing state-of-the-art CS methods, while maintaining fast computational speed.

eess.IV↗

arXiv2021

Residual Relaxation for Multi-view Representation Learning

Multi-view methods learn representations by aligning multiple views of the same image and their performance largely depends on the choice of data augmentation. In this paper, we notice that some other useful augmentations, such as image rotation, are harmful for multi-view methods because they cause a semantic shift that is too large to be aligned well. This observation motivates us to relax the exact alignment objective to better cultivate stronger augmentations. Taking image rotation as a case study, we develop a generic approach, Pretext-aware Residual Relaxation (Prelax), that relaxes the exact alignment by allowing an adaptive residual vector between different views and encoding the semantic shift through pretext-aware learning. Extensive experiments on different backbones show that our method can not only improve multi-view methods with existing augmentations, but also benefit from stronger image augmentations like rotation.

cs.LG↗

arXiv2021

A minimalistic approach to simulate multiple failure mechanisms of metal matrix fiber-reinforced composites by the phase field and cohesive zone models

The mechanical properties of metal matrix fiber-reinforced composites depend on many aspects of their structure in a complicated way. In this paper, we propose a \emph{minimalistic} approach to study interface debonding, matrix cracking, and their competition in metal matrix fiber-reinforced elastoplastic composites by numerical simulation. This approach combines a cohesive zone model for interface debonding and a phase field model for matrix cracking. The features of this framework are: (1) crack nucleation, propagation, and branching can be easily tracked without the need of geometric programming; (2) the interface debonding is determined merely by the CZM, but not interfered by the phase field in the bulk; (3) the cohesive interface has zero thickness instead of being regularized; (4) any reasonable cohesive law of interest is readily incorporated with very few constraints; (5) elastoplasticity of the matrix is conveniently taken into account, as strains in the model are all well defined; (6) the competition of the two failure mechanisms, namely, matrix cracking and interface debonding, is accurately captured. Accuracy of this framework is verified with existing analytical and numerical results. The proposed framework shows a potential in investigating various complicated crack behaviors in composites.

cond-mat.mtrl-sci↗

arXiv2021

Detecting and Correcting IMU Movements During Joint Angle Estimation

Inertial measurement units (IMUs) increasingly function as a basic component of wearable sensor network (WSN)systems. IMU-based joint angle estimation (JAE) is a relatively typical usage of IMUs, with extensive applications. However, the issue that IMUs move with respect to their original placement during JAE is still a research gap, and limits the robustness of deploying the technique in real-world application scenarios. In this study, we propose to detect and correct the IMU movement online in a relatively computationally lightweight manner. Particularly, we first experimentally investigate the influence of IMU movements. Second, we design the metrics for detecting IMU movements by mathematically formulating how the IMU movement affects the IMU measurements. Third, we determine the optimal thresholds of metrics by synthetic IMU data from a significantly amended simulation model. Finally, a correction method is proposed to correct the effects of IMU movements. We demonstrate our method on both synthetic data and real-user data. The results demonstrate our method is a promising solution to detecting and correcting IMU movements during JAE.

eess.SP↗

arXiv2021

On Compression of Unsupervised Neural Nets by Pruning Weak Connections

Unsupervised neural nets such as Restricted Boltzmann Machines(RBMs) and Deep Belif Networks(DBNs), are powerful in automatic feature extraction,unsupervised weight initialization and density estimation. In this paper,we demonstrate that the parameters of these neural nets can be dramatically reduced without affecting their performance. We describe a method to reduce the parameters required by RBM which is the basic building block for deep architectures. Further we propose an unsupervised sparse deep architectures selection algorithm to form sparse deep neural networks.Experimental results show that there is virtually no loss in either generative or discriminative performance.

cs.CV↗

arXiv2021

Excited state fluid mechanics and mathematical principles of separation and transition

Transition and separation are difficult but important problems in the field of fluid mechanics. Hitherto, separation and transition problems have not been described accurately in mathematical terms, leading to design errors and prediction problems in fluid machine engineering. The nonlinear uncertainty involved in separation and transition makes it difficult to accurately analyze these phenomena using experimental methods. Thus, new ideas and methods are required for the mathematical prediction of fluid separation and transition. In this article, after an axiomatic treatment of fluid mechanics, the concept of an excited state is derived by generating a fluctuation velocity, and it is revealed that fluid separation and transition are special forms of this excited state. This allows us to clarify the state conditions of fluid separation and transition. Mathematical analysis of the Navier--Stokes equations leads to a general excited state theorem suitable for flowfields. Finally, the conditions of separation and transition are derived, and the corresponding general laws are established. The results presented in this article provide a foundation for future research on the mechanism of turbulence and the solution of engineering problems.

physics.flu-dyn↗

arXiv2021

Continuous Prediction of Lower-Limb Kinematics From Multi-Modal Biomedical Signals

The fast-growing techniques of measuring and fusing multi-modal biomedical signals enable advanced motor intent decoding schemes of lowerlimb exoskeletons, meeting the increasing demand for rehabilitative or assistive applications of take-home healthcare. Challenges of exoskeletons motor intent decoding schemes remain in making a continuous prediction to compensate for the hysteretic response caused by mechanical transmission. In this paper, we solve this problem by proposing an ahead of time continuous prediction of lower limb kinematics, with the prediction of knee angles during level walking as a case study. Firstly, an end-to-end kinematics prediction network(KinPreNet), consisting of a feature extractor and an angle predictor, is proposed and experimentally compared with features and methods traditionally used in ahead-of-time prediction of gait phases. Secondly, inspired by the electromechanical delay(EMD), we further explore our algorithm's capability of compensating response delay of mechanical transmission by validating the performance of the different sections of prediction time. And we experimentally reveal the time boundary of compensating the hysteretic response. Thirdly, a comparison of employing EMG signals or not is performed to reveal the EMG and kinematic signals collaborated contributions to the continuous prediction. During the experiments, EMG signals of nine muscles and knee angles calculated from inertial measurement unit (IMU) signals are recorded from ten healthy subjects. To the best of our knowledge, this is the first study of continuously predicting lower-limb kinematics in an ahead-of-time manner based on the electromechanical delay (EMD).

eess.SP↗

arXiv2021

Multi-Stage Residual Hiding for Image-into-Audio Steganography

The widespread application of audio communication technologies has speeded up audio data flowing across the Internet, which made it a popular carrier for covert communication. In this paper, we present a cross-modal steganography method for hiding image content into audio carriers while preserving the perceptual fidelity of the cover audio. In our framework, two multi-stage networks are designed: the first network encodes the decreasing multilevel residual errors inside different audio subsequences with the corresponding stage sub-networks, while the second network decodes the residual errors from the modified carrier with the corresponding stage sub-networks to produce the final revealed results. The multi-stage design of proposed framework not only make the controlling of payload capacity more flexible, but also make hiding easier because of the gradual sparse characteristic of residual errors. Qualitative experiments suggest that modifications to the carrier are unnoticeable by human listeners and that the decoded images are highly intelligible.

cs.CV↗

arXiv2020

Hierarchical Complementary Learning for Weakly Supervised Object Localization

Weakly supervised object localization (WSOL) is a challenging problem which aims to localize objects with only image-level labels. Due to the lack of ground truth bounding boxes, class labels are mainly employed to train the model. This model generates a class activation map (CAM) which activates the most discriminate features. However, the main drawback of CAM is the ability to detect just a part of the object. To solve this problem, some researchers have removed parts from the detected object \cite{b1, b2, b4}, or the image \cite{b3}. The aim of removing parts from image or detected parts of the object is to force the model to detect the other features. However, these methods require one or many hyper-parameters to erase the appropriate pixels on the image, which could involve a loss of information. In contrast, this paper proposes a Hierarchical Complementary Learning Network method (HCLNet) that helps the CNN to perform better classification and localization of objects on the images. HCLNet uses a complementary map to force the network to detect the other parts of the object. Unlike previous works, this method does not need any extras hyper-parameters to generate different CAMs, as well as does not introduce a big loss of information. In order to fuse these different maps, two different fusion strategies known as the addition strategy and the l1-norm strategy have been used. These strategies allowed to detect the whole object while excluding the background. Extensive experiments show that HCLNet obtains better performance than state-of-the-art methods.

cs.CV↗

arXiv2020

Entropy Guided Adversarial Model for Weakly Supervised Object Localization

Weakly Supervised Object Localization is challenging because of the lack of bounding box annotations. Previous works tend to generate a class activation map i.e CAM to localize the object. Unfortunately, the network activates only the features that discriminate the object and does not activate the whole object. Some methods tend to remove some parts of the object to force the CNN to detect other features, whereas, others change the network structure to generate multiple CAMs from different levels of the model. In this present article, we propose to take advantage of the generalization ability of the network and train the model using clean examples and adversarial examples to localize the whole object. Adversarial examples are typically used to train robust models and are images where a perturbation is added. To get a good classification accuracy, the CNN trained with adversarial examples is forced to detect more features that discriminate the object. We futher propose to apply the shannon entropy on the CAMs generated by the network to guide it during training. Our method does not erase any part of the image neither does it change the network architecure and extensive experiments show that our Entropy Guided Adversarial model (EGA model) improved performance on state of the arts benchmarks for both localization and classification accuracy.

cs.CV↗