arXiv subjects

Jianwei Zhang

Publications and source records attributed to Jianwei Zhang.

At least 109 records · Page 6Linked to original sources

arXiv2024

Equivariant Local Reference Frames for Unsupervised Non-rigid Point Cloud Shape Correspondence

Unsupervised non-rigid point cloud shape correspondence underpins a multitude of 3D vision tasks, yet itself is non-trivial given the exponential complexity stemming from inter-point degree-of-freedom, i.e., pose transformations. Based on the assumption of local rigidity, one solution for reducing complexity is to decompose the overall shape into independent local regions using Local Reference Frames (LRFs) that are invariant to SE(3) transformations. However, the focus solely on local structure neglects global geometric contexts, resulting in less distinctive LRFs that lack crucial semantic information necessary for effective matching. Furthermore, such complexity introduces out-of-distribution geometric contexts during inference, thus complicating generalization. To this end, we introduce 1) EquiShape, a novel structure tailored to learn pair-wise LRFs with global structural cues for both spatial and semantic consistency, and 2) LRF-Refine, an optimization strategy generally applicable to LRF-based methods, aimed at addressing the generalization challenges. Specifically, for EquiShape, we employ cross-talk within separate equivariant graph neural networks (Cross-GVP) to build long-range dependencies to compensate for the lack of semantic information in local structure modeling, deducing pair-wise independent SE(3)-equivariant LRF vectors for each point. For LRF-Refine, the optimization adjusts LRFs within specific contexts and knowledge, enhancing the geometric and semantic generalizability of point features. Our overall framework surpasses the state-of-the-art methods by a large margin on three benchmarks. Code and models will be publicly available.

cs.CV↗

arXiv2024

Anatomy-Guided Surface Diffusion Model for Alzheimer's Disease Normative Modeling

Normative modeling has emerged as a pivotal approach for characterizing heterogeneity and individual variance in neurodegenerative diseases, notably Alzheimer's disease(AD). One of the challenges of cortical normative modeling is the anatomical structure mismatch due to folding pattern variability. Traditionally, registration is applied to address this issue and recently many studies have utilized deep generative models to generate anatomically align samples for analyzing disease progression; however, these models are predominantly applied to volume-based data, which often falls short in capturing intricate morphological changes on the brain cortex. As an alternative, surface-based analysis has been proven to be more sensitive in disease modeling such as AD, yet, like volume-based data, it also suffers from the mismatch problem. To address these limitations, we proposed a novel generative normative modeling framework by transferring the conditional diffusion generative model to the spherical non-Euclidean domain. Additionally, this approach generates normal feature map distributions by explicitly conditioning on individual anatomical segmentation to ensure better geometrical alignment which helps to reduce anatomical variance between subjects in analysis. We find that our model can generate samples that are better anatomically aligned than registered reference data and through ablation study and normative assessment experiments, the samples are able to better measure individual differences from the normal distribution and increase sensitivity in differentiating cognitively normal (CN), mild cognitive impairment (MCI), and Alzheimer's disease (AD) patients.

eess.IV↗

arXiv2024

A Collision-Aware Cable Grasping Method in Cluttered Environment

We introduce a Cable Grasping-Convolutional Neural Network designed to facilitate robust cable grasping in cluttered environments. Utilizing physics simulations, we generate an extensive dataset that mimics the intricacies of cable grasping, factoring in potential collisions between cables and robotic grippers. We employ the Approximate Convex Decomposition technique to dissect the non-convex cable model, with grasp quality autonomously labeled based on simulated grasping attempts. The CG-CNN is refined using this simulated dataset and enhanced through domain randomization techniques. Subsequently, the trained model predicts grasp quality, guiding the optimal grasp pose to the robot controller for execution. Grasping efficacy is assessed across both synthetic and real-world settings. Given our model implicit collision sensitivity, we achieved commendable success rates of 92.3% for known cables and 88.4% for unknown cables, surpassing contemporary state-of-the-art approaches. Supplementary materials can be found at https://leizhang-public.github.io/cg-cnn/ .

cs.RO↗

arXiv2024

Identity information based on human magnetocardiography signals

We have developed an individual identification system based on magnetocardiography (MCG) signals captured using optically pumped magnetometers (OPMs). Our system utilizes pattern recognition to analyze the signals obtained at different positions on the body, by scanning the matrices composed of MCG signals with a 2*2 window. In order to make use of the spatial information of MCG signals, we transform the signals from adjacent small areas into four channels of a dataset. We further transform the data into time-frequency matrices using wavelet transforms and employ a convolutional neural network (CNN) for classification. As a result, our system achieves an accuracy rate of 97.04% in identifying individuals. This finding indicates that the MCG signal holds potential for use in individual identification systems, offering a valuable tool for personalized healthcare management.

cs.LG↗

arXiv2023

A Closed-Loop Multi-perspective Visual Servoing Approach with Reinforcement Learning

Traditional visual servoing methods suffer from serving between scenes from multiple perspectives, which humans can complete with visual signals alone. In this paper, we investigated how multi-perspective visual servoing could be solved under robot-specific constraints, including self-collision, singularity problems. We presented a novel learning-based multi-perspective visual servoing framework, which iteratively estimates robot actions from latent space representations of visual states using reinforcement learning. Furthermore, our approaches were trained and validated in a Gazebo simulation environment with connection to OpenAI/Gym. Through simulation experiments, we showed that our method can successfully learn an optimal control policy given initial images from different perspectives, and it outperformed the Direct Visual Servoing algorithm with mean success rate of 97.0%.

cs.RO↗

arXiv2023

Search Optimization with Query Likelihood Boosting and Two-Level Approximate Search for Edge Devices

We present a novel search optimization solution for approximate nearest neighbor (ANN) search on resource-constrained edge devices. Traditional ANN approaches fall short in meeting the specific demands of real-world scenarios, e.g., skewed query likelihood distribution and search on large-scale indices with a low latency and small footprint. To address these limitations, we introduce two key components: a Query Likelihood Boosted Tree (QLBT) to optimize average search latency for frequently used small datasets, and a two-level approximate search algorithm to enable efficient retrieval with large datasets on edge devices. We perform thorough evaluation on simulated and real data and demonstrate QLBT can significantly reduce latency by 15% on real data and our two-level search algorithm successfully achieve deployable accuracy and latency on a 10 million dataset for edge devices. In addition, we provide a comprehensive protocol for configuring and optimizing on-device search algorithm through extensive empirical studies.

cs.IR↗

arXiv2023

RobotGPT: Robot Manipulation Learning from ChatGPT

We present RobotGPT, an innovative decision framework for robotic manipulation that prioritizes stability and safety. The execution code generated by ChatGPT cannot guarantee the stability and safety of the system. ChatGPT may provide different answers for the same task, leading to unpredictability. This instability prevents the direct integration of ChatGPT into the robot manipulation loop. Although setting the temperature to 0 can generate more consistent outputs, it may cause ChatGPT to lose diversity and creativity. Our objective is to leverage ChatGPT's problem-solving capabilities in robot manipulation and train a reliable agent. The framework includes an effective prompt structure and a robust learning model. Additionally, we introduce a metric for measuring task difficulty to evaluate ChatGPT's performance in robot manipulation. Furthermore, we evaluate RobotGPT in both simulation and real-world environments. Compared to directly using ChatGPT to generate code, our framework significantly improves task success rates, with an average increase from 38.5% to 91.5%. Therefore, training a RobotGPT by utilizing ChatGPT as an expert is a more stable approach compared to directly using ChatGPT as a task planner.

cs.RO↗

arXiv2023

JarviX: A LLM No code Platform for Tabular Data Analysis and Optimization

In this study, we introduce JarviX, a sophisticated data analytics framework. JarviX is designed to employ Large Language Models (LLMs) to facilitate an automated guide and execute high-precision data analyzes on tabular datasets. This framework emphasizes the significance of varying column types, capitalizing on state-of-the-art LLMs to generate concise data insight summaries, propose relevant analysis inquiries, visualize data effectively, and provide comprehensive explanations for results drawn from an extensive data analysis pipeline. Moreover, JarviX incorporates an automated machine learning (AutoML) pipeline for predictive modeling. This integration forms a comprehensive and automated optimization cycle, which proves particularly advantageous for optimizing machine configuration. The efficacy and adaptability of JarviX are substantiated through a series of practical use case studies.

cs.LG↗

arXiv2023

Key Frame Mechanism For Efficient Conformer Based End-to-end Speech Recognition

Recently, Conformer as a backbone network for end-to-end automatic speech recognition achieved state-of-the-art performance. The Conformer block leverages a self-attention mechanism to capture global information, along with a convolutional neural network to capture local information, resulting in improved performance. However, the Conformer-based model encounters an issue with the self-attention mechanism, as computational complexity grows quadratically with the length of the input sequence. Inspired by previous Connectionist Temporal Classification (CTC) guided blank skipping during decoding, we introduce intermediate CTC outputs as guidance into the downsampling procedure of the Conformer encoder. We define the frame with non-blank output as key frame. Specifically, we introduce the key frame-based self-attention (KFSA) mechanism, a novel method to reduce the computation of the self-attention mechanism using key frames. The structure of our proposed approach comprises two encoders. Following the initial encoder, we introduce an intermediate CTC loss function to compute the label frame, enabling us to extract the key frames and blank frames for KFSA. Furthermore, we introduce the key frame-based downsampling (KFDS) mechanism to operate on high-dimensional acoustic features directly and drop the frames corresponding to blank labels, which results in new acoustic feature sequences as input to the second encoder. By using the proposed method, which achieves comparable or higher performance than vanilla Conformer and other similar work such as Efficient Conformer. Meantime, our proposed method can discard more than 60\% useless frames during model training and inference, which will accelerate the inference speed significantly. This work code is available in {https://github.com/scufan1990/Key-Frame-Mechanism-For-Efficient-Conformer}

cs.SD↗

arXiv2023

Learning Repeatable Speech Embeddings Using An Intra-class Correlation Regularizer

A good supervised embedding for a specific machine learning task is only sensitive to changes in the label of interest and is invariant to other confounding factors. We leverage the concept of repeatability from measurement theory to describe this property and propose to use the intra-class correlation coefficient (ICC) to evaluate the repeatability of embeddings. We then propose a novel regularizer, the ICC regularizer, as a complementary component for contrastive losses to guide deep neural networks to produce embeddings with higher repeatability. We use simulated data to explain why the ICC regularizer works better on minimizing the intra-class variance than the contrastive loss alone. We implement the ICC regularizer and apply it to three speech tasks: speaker verification, voice style conversion, and a clinical application for detecting dysphonic voice. The experimental results demonstrate that adding an ICC regularizer can improve the repeatability of learned embeddings compared to only using the contrastive loss; further, these embeddings lead to improved performance in these downstream tasks.

cs.SD↗

arXiv2023

Qwen Technical Report

Large language models (LLMs) have revolutionized the field of artificial intelligence, enabling natural language processing tasks that were previously thought to be exclusive to humans. In this work, we introduce Qwen, the first installment of our large language model series. Qwen is a comprehensive language model series that encompasses distinct models with varying parameter counts. It includes Qwen, the base pretrained language models, and Qwen-Chat, the chat models finetuned with human alignment techniques. The base language models consistently demonstrate superior performance across a multitude of downstream tasks, and the chat models, particularly those trained using Reinforcement Learning from Human Feedback (RLHF), are highly competitive. The chat models possess advanced tool-use and planning capabilities for creating agent applications, showcasing impressive performance even when compared to bigger models on complex tasks like utilizing a code interpreter. Furthermore, we have developed coding-specialized models, Code-Qwen and Code-Qwen-Chat, as well as mathematics-focused models, Math-Qwen-Chat, which are built upon base language models. These models demonstrate significantly improved performance in comparison with open-source models, and slightly fall behind the proprietary models.

cs.CL↗

arXiv2023

3D Semantic Subspace Traverser: Empowering 3D Generative Model with Shape Editing Capability

Shape generation is the practice of producing 3D shapes as various representations for 3D content creation. Previous studies on 3D shape generation have focused on shape quality and structure, without or less considering the importance of semantic information. Consequently, such generative models often fail to preserve the semantic consistency of shape structure or enable manipulation of the semantic attributes of shapes during generation. In this paper, we proposed a novel semantic generative model named 3D Semantic Subspace Traverser that utilizes semantic attributes for category-specific 3D shape generation and editing. Our method utilizes implicit functions as the 3D shape representation and combines a novel latent-space GAN with a linear subspace model to discover semantic dimensions in the local latent space of 3D shapes. Each dimension of the subspace corresponds to a particular semantic attribute, and we can edit the attributes of generated shapes by traversing the coefficients of those dimensions. Experimental results demonstrate that our method can produce plausible shapes with complex structures and enable the editing of semantic attributes. The code and trained models are available at https://github.com/TrepangCat/3D_Semantic_Subspace_Traverser

cs.CV↗

arXiv2023

Learning Semantic-Agnostic and Spatial-Aware Representation for Generalizable Visual-Audio Navigation

Visual-audio navigation (VAN) is attracting more and more attention from the robotic community due to its broad applications, \emph{e.g.}, household robots and rescue robots. In this task, an embodied agent must search for and navigate to the sound source with egocentric visual and audio observations. However, the existing methods are limited in two aspects: 1) poor generalization to unheard sound categories; 2) sample inefficient in training. Focusing on these two problems, we propose a brain-inspired plug-and-play method to learn a semantic-agnostic and spatial-aware representation for generalizable visual-audio navigation. We meticulously design two auxiliary tasks for respectively accelerating learning representations with the above-desired characteristics. With these two auxiliary tasks, the agent learns a spatially-correlated representation of visual and audio inputs that can be applied to work on environments with novel sounds and maps. Experiment results on realistic 3D scenes (Replica and Matterport3D) demonstrate that our method achieves better generalization performance when zero-shot transferred to scenes with unseen maps and unheard sound categories.

cs.RO↗

arXiv2023

Deep Active Learning with Structured Neural Depth Search

Previous work optimizes traditional active learning (AL) processes with incremental neural network architecture search (Active-iNAS) based on data complexity change, which improves the accuracy and learning efficiency. However, Active-iNAS trains several models and selects the model with the best generalization performance for querying the subsequent samples after each active learning cycle. The independent training processes lead to an insufferable computational budget, which is significantly inefficient and limits search flexibility and final performance. To address this issue, we propose a novel active strategy with the method called structured variational inference (SVI) or structured neural depth search (SNDS) whereby we could use the gradient descent method in neural network depth search during AL processes. At the same time, we theoretically demonstrate that the current VI-based methods based on the mean-field assumption could lead to poor performance. We apply our strategy using three querying techniques and three datasets and show that our strategy outperforms current methods.

cs.LG↗

arXiv2023

PoseFusion: Robust Object-in-Hand Pose Estimation with SelectLSTM

Accurate estimation of the relative pose between an object and a robot hand is critical for many manipulation tasks. However, most of the existing object-in-hand pose datasets use two-finger grippers and also assume that the object remains fixed in the hand without any relative movements, which is not representative of real-world scenarios. To address this issue, a 6D object-in-hand pose dataset is proposed using a teleoperation method with an anthropomorphic Shadow Dexterous hand. Our dataset comprises RGB-D images, proprioception and tactile data, covering diverse grasping poses, finger contact states, and object occlusions. To overcome the significant hand occlusion and limited tactile sensor contact in real-world scenarios, we propose PoseFusion, a hybrid multi-modal fusion approach that integrates the information from visual and tactile perception channels. PoseFusion generates three candidate object poses from three estimators (tactile only, visual only, and visuo-tactile fusion), which are then filtered by a SelectLSTM network to select the optimal pose, avoiding inferior fusion poses resulting from modality collapse. Extensive experiments demonstrate the robustness and advantages of our framework. All data and codes are available on the project website: https://elevenjiang1.github.io/ObjectInHand-Dataset/

cs.RO↗

arXiv2023

Capillary filling of polymer chains in nanopores

We performed molecular dynamics simulations with a coarse-grained model to investigate the capillary filling dynamics of polymer chains in nanopores. Short chains fill slower than predicted by the Lucas-Washburn equation but long chains fill faster. The analysis shows that the combination of the confinement effect on the free energy of chains and the reduction of the effective radius due to the "dead zone" slow down the imbibition. Reduction of the entanglements is the main factor behind the reversing dynamics because of the lower effective viscosity, which leads to a faster filling. This effect is enhanced in the smaller capillary and more profound for longer chains. The observed increase in the mean square radius of gyration during capillary filling provides a clear evidence of chain orientation, which leads to the decrease in the number of entanglements. For the scaling relation between the effective viscosity and the degree of polymerization, we find the exponent will increase in the larger nanopore.

cond-mat.soft↗

arXiv2023

A Survey on Machine Learning from Few Samples

Few sample learning (FSL) is significant and challenging in the field of machine learning. The capability of learning and generalizing from very few samples successfully is a noticeable demarcation separating artificial intelligence and human intelligence since humans can readily establish their cognition to novelty from just a single or a handful of examples whereas machine learning algorithms typically entail hundreds or thousands of supervised samples to guarantee generalization ability. Despite the long history dated back to the early 2000s and the widespread attention in recent years with booming deep learning technologies, little surveys or reviews for FSL are available until now. In this context, we extensively review 300+ papers of FSL spanning from the 2000s to 2019 and provide a timely and comprehensive survey for FSL. In this survey, we review the evolution history as well as the current progress on FSL, categorize FSL approaches into the generative model based and discriminative model based kinds in principle, and emphasize particularly on the meta learning based FSL approaches. We also summarize several recently emerging extensional topics of FSL and review the latest advances on these topics. Furthermore, we highlight the important FSL applications covering many research hotspots in computer vision, natural language processing, audio and speech, reinforcement learning and robotic, data analysis, etc. Finally, we conclude the survey with a discussion on promising trends in the hope of providing guidance and insights to follow-up researches.

cs.LG↗

arXiv2023

Reinforcement Learning Based Pushing and Grasping Objects from Ungraspable Poses

Grasping an object when it is in an ungraspable pose is a challenging task, such as books or other large flat objects placed horizontally on a table. Inspired by human manipulation, we address this problem by pushing the object to the edge of the table and then grasping it from the hanging part. In this paper, we develop a model-free Deep Reinforcement Learning framework to synergize pushing and grasping actions. We first pre-train a Variational Autoencoder to extract high-dimensional features of input scenario images. One Proximal Policy Optimization algorithm with the common reward and sharing layers of Actor-Critic is employed to learn both pushing and grasping actions with high data efficiency. Experiments show that our one network policy can converge 2.5 times faster than the policy using two parallel networks. Moreover, the experiments on unseen objects show that our policy can generalize to the challenging case of objects with curved surfaces and off-center irregularly shaped objects. Lastly, our policy can be transferred to a real robot without fine-tuning by using CycleGAN for domain adaption and outperforms the push-to-wall baseline.

cs.RO↗