arXiv subjects

Yu Xiang

Publications and source records attributed to Yu Xiang.

At least 55 records · Page 3Linked to original sources

arXiv2025

HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction

We introduce a data capture system and a new dataset, HO-Cap, for 3D reconstruction and pose tracking of hands and objects in videos. The system leverages multiple RGBD cameras and a HoloLens headset for data collection, avoiding the use of expensive 3D scanners or mocap systems. We propose a semi-automatic method for annotating the shape and pose of hands and objects in the collected videos, significantly reducing the annotation time compared to manual labeling. With this system, we captured a video dataset of humans interacting with objects to perform various tasks, including simple pick-and-place actions, handovers between hands, and using objects according to their affordance, which can serve as human demonstrations for research in embodied AI and robot manipulation. Our data capture setup and annotation framework will be available for the community to use in reconstructing 3D shapes of objects and human hands and tracking their poses in videos.

cs.CV↗

arXiv2025

Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation

Novel Instance Detection and Segmentation (NIDS) aims at detecting and segmenting novel object instances given a few examples of each instance. We propose a unified, simple, yet effective framework (NIDS-Net) comprising object proposal generation, embedding creation for both instance templates and proposal regions, and embedding matching for instance label assignment. Leveraging recent advancements in large vision methods, we utilize Grounding DINO and Segment Anything Model (SAM) to obtain object proposals with accurate bounding boxes and masks. Central to our approach is the generation of high-quality instance embeddings. We utilized foreground feature averages of patch embeddings from the DINOv2 ViT backbone, followed by refinement through a weight adapter mechanism that we introduce. We show experimentally that our weight adapter can adjust the embeddings locally within their feature space and effectively limit overfitting in the few-shot setting. Furthermore, the weight adapter optimizes weights to enhance the distinctiveness of instance embeddings during similarity computation. This methodology enables a straightforward matching strategy that results in significant performance gains. Our framework surpasses current state-of-the-art methods, demonstrating notable improvements in four detection datasets. In the segmentation tasks on seven core datasets of the BOP challenge, our method outperforms the leading published RGB methods and remains competitive with the best RGB-D method. We have also verified our method using real-world images from a Fetch robot and a RealSense camera. Project Page: https://irvlutd.github.io/NIDSNet/

cs.CV↗

arXiv2025

RobotFingerPrint: Unified Gripper Coordinate Space for Multi-Gripper Grasp Synthesis and Transfer

We introduce a novel grasp representation named the Unified Gripper Coordinate Space (UGCS) for grasp synthesis and grasp transfer. Our representation leverages spherical coordinates to create a shared coordinate space across different robot grippers, enabling it to synthesize and transfer grasps for both novel objects and previously unseen grippers. The strength of this representation lies in the ability to map palm and fingers of a gripper and the unified coordinate space. Grasp synthesis is formulated as predicting the unified spherical coordinates on object surface points via a conditional variational autoencoder. The predicted unified gripper coordinates establish exact correspondences between the gripper and object points, which is used to optimize grasp pose and joint values. Grasp transfer is facilitated through the point-to-point correspondence between any two (potentially unseen) grippers and solved via a similar optimization. Extensive simulation and real-world experiments showcase the efficacy of the unified grasp representation for grasp synthesis in generating stable and diverse grasps. Similarly, we showcase real-world grasp transfer from human demonstrations across different objects.

cs.RO↗

arXiv2024

CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities

Following step-by-step procedures is an essential component of various activities carried out by individuals in their daily lives. These procedures serve as a guiding framework that helps to achieve goals efficiently, whether it is assembling furniture or preparing a recipe. However, the complexity and duration of procedural activities inherently increase the likelihood of making errors. Understanding such procedural activities from a sequence of frames is a challenging task that demands an accurate interpretation of visual information and the ability to reason about the structure of the activity. To this end, we collect a new egocentric 4D dataset, CaptainCook4D, comprising 384 recordings (94.5 hours) of people performing recipes in real kitchen environments. This dataset consists of two distinct types of activity: one in which participants adhere to the provided recipe instructions and another in which they deviate and induce errors. We provide 5.3K step annotations and 10K fine-grained action annotations and benchmark the dataset for the following tasks: supervised error recognition, multistep localization, and procedure learning

cs.CV↗

arXiv2024

One-Sided Device-Independent Random Number Generation Through Fiber Channels

Randomness is an essential resource and plays important roles in various applications ranging from cryptography to simulation of complex systems. Certified randomness from quantum process is ensured to have the element of privacy but usually relies on the device's behavior. To certify randomness without the characterization for device, it is crucial to realize the one-sided device-independent random number generation based on quantum steering, which guarantees security of randomness and relaxes the demands of one party's device. Here, we distribute quantum steering between two distant users through a 2 km fiber channel and generate quantum random numbers at the remote station with untrustworthy device. We certify the steering-based randomness by reconstructing covariance matrix of the Gaussian entangled state shared between distant parties. Then, the quantum random numbers with a generation rate of 7.06 Mbits/s are extracted from the measured amplitude quadrature fluctuation of the state owned by the remote party. Our results demonstrate the first realization of steering-based random numbers extraction in a practical fiber channel, which paves the way to the quantum random numbers generation in asymmetric networks.

quant-ph↗

arXiv2024

Learning with Geometry: Including Riemannian Geometric Features in Coefficient of Pressure Prediction on Aircraft Wings

We propose to incorporate Riemannian geometric features from the geometry of aircraft wing surfaces in the prediction of coefficient of pressure (CP) on the aircraft wing. Contrary to existing approaches that treat the wing surface as a flat object, we represent the wing as a piecewise smooth manifold and calculate a set of Riemannian geometric features (Riemannian metric, connection, and curvature) over points of the wing. Combining these features in neighborhoods of points on the wing with coordinates and flight conditions gives inputs to a deep learning model that predicts CP distributions. Experimental results show that the method with incorporation of Riemannian geometric features, compared to state-of-the-art Deep Attention Network (DAN), reduces the predicted mean square error (MSE) of CP by an average of 15.00% for the DLR-F11 aircraft test set.

cs.LG↗

arXiv2024

Isometric Immersion Learning with Riemannian Geometry

Manifold learning has been proven to be an effective method for capturing the implicitly intrinsic structure of non-Euclidean data, in which one of the primary challenges is how to maintain the distortion-free (isometry) of the data representations. Actually, there is still no manifold learning method that provides a theoretical guarantee of isometry. Inspired by Nash's isometric theorem, we introduce a new concept called isometric immersion learning based on Riemannian geometry principles. Following this concept, an unsupervised neural network-based model that simultaneously achieves metric and manifold learning is proposed by integrating Riemannian geometry priors. What's more, we theoretically derive and algorithmically implement a maximum likelihood estimation-based training method for the new model. In the simulation experiments, we compared the new model with the state-of-the-art baselines on various 3-D geometry datasets, demonstrating that the new model exhibited significantly superior performance in multiple evaluation metrics. Moreover, we applied the Riemannian metric learned from the new model to downstream prediction tasks in real-world scenarios, and the accuracy was improved by an average of 8.8%.

cs.LG↗

arXiv2024

Necessary and Sufficient Condition for Randomness Certification from Incompatibility

Quantum randomness can be certified from probabilistic behaviors demonstrating Bell nonlocality or Einstein-Podolsky-Rosen steering, leveraging outcomes from uncharacterized devices. However, such nonlocal correlations are not always sufficient for this task, necessitating the identification of required minimum quantum resources. In this work, we provide the necessary and sufficient condition for nonzero certifiable randomness in terms of measurement incompatibility and develop approaches to detect them. Firstly, we show that the steering-based randomness can be certified if and only if the correlations arise from a measurement compatibility structure that is not isomorphic to a hypergraph containing a star subgraph. In such a structure, the central measurement is individually compatible with the measurements at branch sites, precluding certifiable randomness in the central measurement outcomes. Subsequently, we generalize this result to the Bell scenario, proving that the violation of any chain inequality involving $m$ inputs and $d$ outputs rules out such a compatibility structure, thereby validating all chain inequalities as credible witnesses for randomness certification. Our results point out the role of incompatibility structure in generating random numbers, offering a way to identify minimum quantum resources for the task.

quant-ph↗

arXiv2024

Randomness versus Nonlocality in Multi-input and Multi-output Quantum Scenario

Device-independent randomness certification based on Bell nonlocality does not require any assumptions about the devices and therefore provides adequate security. Great effort has been made to demonstrate that nonlocality is necessary for generating quantum randomness, but the minimal resource required for random number generation has not been clarified. Here we first prove and experimentally demonstrate that violating any two-input Bell inequality is both necessary and sufficient for certifying randomness, however, for the multi-input cases, this sufficiency ceases to apply, leading to certain states exhibiting Bell nonlocality without the capability to certify randomness. We examine two typical classes of Bell inequalities with multi-input and multi-output, the facet inequalities and Salavrakos-Augusiak-Tura-Wittek-Acín-Pironio Bell inequalities, in the high-dimensional photonic system, and observe the violation of the latter one can always certify randomness which is not true for the former. The private randomness with a generation rate of 1.867\pm0.018 bits per photon pair is obtained in the scenario of Salavrakos-Augusiak-Tura-Wittek-Acín-Pironio Bell inequalities with 3-input and 4-output. Our work unravels the internal connection between randomness and nonlocality, and effectively enhances the performance of tasks such as device-independent random number generation.

quant-ph↗

arXiv2024

MultiGripperGrasp: A Dataset for Robotic Grasping from Parallel Jaw Grippers to Dexterous Hands

We introduce a large-scale dataset named MultiGripperGrasp for robotic grasping. Our dataset contains 30.4M grasps from 11 grippers for 345 objects. These grippers range from two-finger grippers to five-finger grippers, including a human hand. All grasps in the dataset are verified in the robot simulator Isaac Sim to classify them as successful and unsuccessful grasps. Additionally, the object fall-off time for each grasp is recorded as a grasp quality measurement. Furthermore, the grippers in our dataset are aligned according to the orientation and position of their palms, allowing us to transfer grasps from one gripper to another. The grasp transfer significantly increases the number of successful grasps for each gripper in the dataset. Our dataset is useful to study generalized grasp planning and grasp transfer across different grippers. Data, code and videos for the project are available at https://irvlutd.github.io/MultiGripperGrasp

cs.RO↗

arXiv2024

Grasping Trajectory Optimization with Point Clouds

We introduce a new trajectory optimization method for robotic grasping based on a point-cloud representation of robots and task spaces. In our method, robots are represented by 3D points on their link surfaces. The task space of a robot is represented by a point cloud that can be obtained from depth sensors. Using the point-cloud representation, goal reaching in grasping can be formulated as point matching, while collision avoidance can be efficiently achieved by querying the signed distance values of the robot points in the signed distance field of the scene points. Consequently, a constrained nonlinear optimization problem is formulated to solve the joint motion and grasp planning problem. The advantage of our method is that the point-cloud representation is general to be used with any robot in any environment. We demonstrate the effectiveness of our method by performing experiments on a tabletop scene and a shelf scene for grasping with a Fetch mobile manipulator and a Franka Panda arm. The project page is available at \url{https://irvlutd.github.io/GraspTrajOpt}

cs.RO↗

arXiv2024

Proto-CLIP: Vision-Language Prototypical Network for Few-Shot Learning

We propose a novel framework for few-shot learning by leveraging large-scale vision-language models such as CLIP. Motivated by unimodal prototypical networks for few-shot learning, we introduce Proto-CLIP which utilizes image prototypes and text prototypes for few-shot learning. Specifically, Proto-CLIP adapts the image and text encoder embeddings from CLIP in a joint fashion using few-shot examples. The embeddings from the two encoders are used to compute the respective prototypes of image classes for classification. During adaptation, we propose aligning the image and text prototypes of the corresponding classes. Such alignment is beneficial for few-shot classification due to the reinforced contributions from both types of prototypes. Proto-CLIP has both training-free and fine-tuned variants. We demonstrate the effectiveness of our method by conducting experiments on benchmark datasets for few-shot learning, as well as in the real world for robot perception. The project page is available at https://irvlutd.github.io/Proto-CLIP

cs.CV↗

arXiv2024

Faithful geometric measures for genuine tripartite entanglement

We present a faithful geometric picture for genuine tripartite entanglement of discrete, continuous, and hybrid quantum systems. We first find that the triangle relation $\mathcal{E}^α_{i|jk}\leq \mathcal{E}^α_{j|ik}+\mathcal{E}^α_{k|ij}$ holds for all subadditive bipartite entanglement measure $\mathcal{E}$, all permutations under parties $i, j, k$, all $α\in [0, 1]$, and all pure tripartite states. It provides a geometric interpretation that bipartition entanglement, measured by $\mathcal{E}^α$, corresponds to the side of a triangle, of which the area with $α\in (0, 1)$ is nonzero if and only if the underlying state is genuinely entangled. Then, we rigorously prove the non-obtuse triangle area with $0<α\leq 1/2$ is a measure for genuine tripartite entanglement. Useful lower and upper bounds for these measures are obtained, and generalizations of our results are also presented. Finally, it is significantly strengthened for qubits that, given a set of subadditive and non-additive measures, some state is always found to violate the triangle relation for any $α>1$, and the triangle area is not a measure for any $α>1/2$. Hence, our results are expected to aid significant progress in studying both discrete and continuous multipartite entanglement.

quant-ph↗

arXiv2024

Mining Invariance from Nonlinear Multi-Environment Data: Binary Classification

Making predictions in an unseen environment given data from multiple training environments is a challenging task. We approach this problem from an invariance perspective, focusing on binary classification to shed light on general nonlinear data generation mechanisms. We identify a unique form of invariance that exists solely in a binary setting that allows us to train models invariant over environments. We provide sufficient conditions for such invariance and show it is robust even when environmental conditions vary greatly. Our formulation admits a causal interpretation, allowing us to compare it with various frameworks. Finally, we propose a heuristic prediction method and conduct experiments using real and synthetic datasets.

stat.ME↗

arXiv2024

Causal Inference from Slowly Varying Nonstationary Processes

Causal inference from observational data following the restricted structural causal models (SCM) framework hinges largely on the asymmetry between cause and effect from the data generating mechanisms, such as non-Gaussianity or non-linearity. This methodology can be adapted to stationary time series, yet inferring causal relationships from nonstationary time series remains a challenging task. In this work, we propose a new class of restricted SCM, via a time-varying filter and stationary noise, and exploit the asymmetry from nonstationarity for causal identification in both bivariate and network settings. We propose efficient procedures by leveraging powerful estimates of the bivariate evolutionary spectra for slowly varying processes. Various synthetic and real datasets that involve high-order and non-smooth filters are evaluated to demonstrate the effectiveness of our proposed methodology.

cs.LG↗

arXiv2024

Low-Rank Approximation of Structural Redundancy for Self-Supervised Learning

We study the data-generating mechanism for reconstructive SSL to shed light on its effectiveness. With an infinite amount of labeled samples, we provide a sufficient and necessary condition for perfect linear approximation. The condition reveals a full-rank component that preserves the label classes of Y, along with a redundant component. Motivated by the condition, we propose to approximate the redundant component by a low-rank factorization and measure the approximation quality by introducing a new quantity $ε_s$, parameterized by the rank of factorization s. We incorporate $ε_s$ into the excess risk analysis under both linear regression and ridge regression settings, where the latter regularization approach is to handle scenarios when the dimension of the learned features is much larger than the number of labeled samples n for downstream tasks. We design three stylized experiments to compare SSL with supervised learning under different settings to support our theoretical findings.

stat.ML↗

arXiv2024

AMPLIFY:Attention-based Mixup for Performance Improvement and Label Smoothing in Transformer

Mixup is an effective data augmentation method that generates new augmented samples by aggregating linear combinations of different original samples. However, if there are noises or aberrant features in the original samples, Mixup may propagate them to the augmented samples, leading to over-sensitivity of the model to these outliers . To solve this problem, this paper proposes a new Mixup method called AMPLIFY. This method uses the Attention mechanism of Transformer itself to reduce the influence of noises and aberrant values in the original samples on the prediction results, without increasing additional trainable parameters, and the computational cost is very low, thereby avoiding the problem of high resource consumption in common Mixup methods such as Sentence Mixup . The experimental results show that, under a smaller computational resource cost, AMPLIFY outperforms other Mixup methods in text classification tasks on 7 benchmark datasets, providing new ideas and new ways to further improve the performance of pre-trained models based on the Attention mechanism, such as BERT, ALBERT, RoBERTa, and GPT. Our code can be obtained at https://github.com/kiwi-lilo/AMPLIFY.

cs.LG↗

arXiv2024

Training-Conditional Coverage Bounds for Uniformly Stable Learning Algorithms

The training-conditional coverage performance of the conformal prediction is known to be empirically sound. Recently, there have been efforts to support this observation with theoretical guarantees. The training-conditional coverage bounds for jackknife+ and full-conformal prediction regions have been established via the notion of $(m,n)$-stability by Liang and Barber~[2023]. Although this notion is weaker than uniform stability, it is not clear how to evaluate it for practical models. In this paper, we study the training-conditional coverage bounds of full-conformal, jackknife+, and CV+ prediction regions from a uniform stability perspective which is known to hold for empirical risk minimization over reproducing kernel Hilbert spaces with convex regularization. We derive coverage bounds for finite-dimensional models by a concentration argument for the (estimated) predictor function, and compare the bounds with existing ones under ridge regression.

stat.ML↗