Searcharxiv⌕ Search

arXiv subjects

Xiao Ma

Publications and source records attributed to Xiao Ma.

At least 145 records · Page 8Linked to original sources
arXiv2021

Ab Initio Particle-based Object Manipulation

This paper presents Particle-based Object Manipulation (Prompt), a new approach to robot manipulation of novel objects ab initio, without prior object models or pre-training on a large object data set. The key element of Prompt is a particle-based object representation, in which each particle represents a point in the object, the local geometric, physical, and other features of the point, and also its relation with other particles. Like the model-based analytic approaches to manipulation, the particle representation enables the robot to reason about the object's geometry and dynamics in order to choose suitable manipulation actions. Like the data-driven approaches, the particle representation is learned online in real-time from visual sensor input, specifically, multi-view RGB images. The particle representation thus connects visual perception with robot control. Prompt combines the benefits of both model-based reasoning and data-driven learning. We show empirically that Prompt successfully handles a variety of everyday objects, some of which are transparent. It handles various manipulation tasks, including grasping, pushing, etc,. Our experiments also show that Prompt outperforms a state-of-the-art data-driven grasping method on the daily objects, even though it does not use any offline training data.

cs.RO↗
arXiv2021

Detecting and modelling real percolation and phase transitions of information on social media

It is widely believed that information spread on social media is a percolation process, with parallels to phase transitions in theoretical physics. However, evidence for this hypothesis is limited, as phase transitions have not been directly observed in any social media. Here, through analysis of 100 million Weibo and 40 million Twitter users, we identify percolation-like spread, and find that it happens more readily than current theoretical models would predict. The lower percolation threshold can be explained by the existence of positive feedback in the coevolution between network structure and user activity level, such that more active users gain more followers. Moreover, this coevolution induces an extreme imbalance in users' influence. Our findings indicate that the ability of information to spread across social networks is higher than expected, with implications for many information spread problems.

physics.soc-ph↗
arXiv2021

Twisted-Pair Superposition Transmission

We propose in this paper a new coding scheme called twisted-pair superposition transmission (TPST). The encoding is to "mix together" a pair of basic codes by superposition, while the decoding can be implemented as a successive cancellation list decoding algorithm. The most significant features of the TPST code are its predictable performance that can be estimated numerically from the basic codes and its flexible construction in the sense that it can be easily adapted to different coding rates. To construct good TPST codes in the finite length regime, we propose two design approaches-rate allocation and partial superposition. By taking tail-biting convolutional codes (TBCC) as basic codes, we show by numerical results that the TPST codes can have near-capacity performance in the short length regime.

cs.IT↗
arXiv2021

HAVANA: Hierarchical and Variation-Normalized Autoencoder for Person Re-identification

Person Re-Identification (Re-ID) is of great importance to the many video surveillance systems. Learning discriminative features for Re-ID remains a challenge due to the large variations in the image space, e.g., continuously changing human poses, illuminations and point of views. In this paper, we propose HAVANA, a novel extensible, light-weight HierArchical and VAriation-Normalized Autoencoder that learns features robust to intra-class variations. In contrast to existing generative approaches that prune the variations with heavy extra supervised signals, HAVANA suppresses the intra-class variations with a Variation-Normalized Autoencoder trained with no additional supervision. We also introduce a novel Jensen-Shannon triplet loss for contrastive distribution learning in Re-ID. In addition, we present Hierarchical Variation Distiller, a hierarchical VAE to factorize the latent representation and explicitly model the variations. To the best of our knowledge, HAVANA is the first VAE-based framework for person ReID.

cs.CV↗
arXiv2020

Towards Overcoming False Positives in Visual Relationship Detection

In this paper, we investigate the cause of the high false positive rate in Visual Relationship Detection (VRD). We observe that during training, the relationship proposal distribution is highly imbalanced: most of the negative relationship proposals are easy to identify, e.g., the inaccurate object detection, which leads to the under-fitting of low-frequency difficult proposals. This paper presents Spatially-Aware Balanced negative pRoposal sAmpling (SABRA), a robust VRD framework that alleviates the influence of false positives. To effectively optimize the model under imbalanced distribution, SABRA adopts Balanced Negative Proposal Sampling (BNPS) strategy for mini-batch sampling. BNPS divides proposals into 5 well defined sub-classes and generates a balanced training distribution according to the inverse frequency. BNPS gives an easier optimization landscape and significantly reduces the number of false positives. To further resolve the low-frequency challenging false positive proposals with high spatial ambiguity, we improve the spatial modeling ability of SABRA on two aspects: a simple and efficient multi-head heterogeneous graph attention network (MH-GAT) that models the global spatial interactions of objects, and a spatial mask decoder that learns the local spatial configuration. SABRA outperforms SOTA methods by a large margin on two human-object interaction (HOI) datasets and one general VRD dataset.

cs.CV↗
arXiv2020

Balanced Meta-Softmax for Long-Tailed Visual Recognition

Deep classifiers have achieved great success in visual recognition. However, real-world data is long-tailed by nature, leading to the mismatch between training and testing distributions. In this paper, we show that the Softmax function, though used in most classification tasks, gives a biased gradient estimation under the long-tailed setup. This paper presents Balanced Softmax, an elegant unbiased extension of Softmax, to accommodate the label distribution shift between training and testing. Theoretically, we derive the generalization bound for multiclass Softmax regression and show our loss minimizes the bound. In addition, we introduce Balanced Meta-Softmax, applying a complementary Meta Sampler to estimate the optimal class sample rate and further improve long-tailed learning. In our experiments, we demonstrate that Balanced Meta-Softmax outperforms state-of-the-art long-tailed classification solutions on both visual recognition and instance segmentation tasks.

cs.LG↗
arXiv2020

Contrastive Variational Reinforcement Learning for Complex Observations

Deep reinforcement learning (DRL) has achieved significant success in various robot tasks: manipulation, navigation, etc. However, complex visual observations in natural environments remains a major challenge. This paper presents Contrastive Variational Reinforcement Learning (CVRL), a model-based method that tackles complex visual observations in DRL. CVRL learns a contrastive variational model by maximizing the mutual information between latent states and observations discriminatively, through contrastive learning. It avoids modeling the complex observation space unnecessarily, as the commonly used generative observation model often does, and is significantly more robust. CVRL achieves comparable performance with state-of-the-art model-based DRL methods on standard Mujoco tasks. It significantly outperforms them on Natural Mujoco tasks and a robot box-pushing task with complex observations, e.g., dynamic shadows. The CVRL code is available publicly at https://github.com/Yusufma03/CVRL.

cs.LG↗
arXiv2020

Hierarchical Federated Learning through LAN-WAN Orchestration

Federated learning (FL) was designed to enable mobile phones to collaboratively learn a global model without uploading their private data to a cloud server. However, exiting FL protocols has a critical communication bottleneck in a federated network coupled with privacy concerns, usually powered by a wide-area network (WAN). Such a WAN-driven FL design leads to significantly high cost and much slower model convergence. In this work, we propose an efficient FL protocol, which involves a hierarchical aggregation mechanism in the local-area network (LAN) due to its abundant bandwidth and almost negligible monetary cost than WAN. Our proposed FL can accelerate the learning process and reduce the monetary cost with frequent local aggregation in the same LAN and infrequent global aggregation on a cloud across WAN. We further design a concrete FL platform, namely LanFL, that incorporates several key techniques to handle those challenges introduced by LAN: cloud-device aggregation architecture, intra-LAN peer-to-peer (p2p) topology generation, inter-LAN bandwidth capacity heterogeneity. We evaluate LanFL on 2 typical Non-IID datasets, which reveals that LanFL can significantly accelerate FL training (1.5x-6.0x), save WAN traffic (18.3x-75.6x), and reduce monetary cost (3.8x-27.2x) while preserving the model accuracy.

cs.LG↗
arXiv2020

Optimal control and stablilization for linear continuous-time mean-field systems with delay

This paper studies optimal control and stabilization problems for continuous-time mean-field systems with input delay, which are the fundamental development of control and stabilization problems for mean-field systems. There are two main contributions: 1) To the best of our knowledge, the present paper is first to establish the necessary and sufficient solvability condition for this kind of optimal control problem with delay, and to derive an optimal controller through overcoming the obstacle that separation principle no longer holds for multiplicative-noise systems; 2) For the stabilization problem, under the assumption of exact observability, we strictly prove thatthe system is stabilizable if and only if the algebraic Riccati equation has a unique positive definite solution.

math.OC↗
arXiv2020

Transmitting Extra Bits by Rotating Signal Constellations

In this letter, we propose a novel LDPC coding scheme to transmit extra bits aided by rotated signal constellations without any additional cost in transmission power or bandwidth. In the proposed scheme, the LDPC coded data are modulated by a rotated two-dimensional signal constellation, in which the rotation angle is specified by the given extra bits. At the receiver, the rotation angle is estimated with the aid of the statistical learning of the syndrome of the LDPC code. After recovering the rotation angle, the coded payload data can be decoded by the LDPC decoder. The simulation results show that, for an LDPC code of length 2304, up to four extra bits can be transmitted with negligible influence on the reliability of the LDPC coded data.

cs.IT↗
arXiv2020

Successive Cancellation List Decoding of Semi-random Unit Memory Convolutional Codes

We present in this paper a special class of unit memory convolutional codes (UMCCs), called semi-random UMCCs (SRUMCCs), where the information block is first encoded by a short block code and then transmitted in a block Markov (random) superposition manner. We propose a successive cancellation list decoding algorithm, by which a list of candidate codewords are generated serially until one passes an empirical divergence test instead of the conventional cyclic redundancy check (CRC). The threshold for testing the correctness of candidate codewords can be learned off-line based on the statistical behavior of the introduced empirical divergence function (EDF). The performance-complexity tradeoff and the performance-delay tradeoff can be achieved by adjusting the statistical threshold and the decoding window size. To analyze the performance, a closed-form upper bound and a simulated lower bound are derived. Simulation results verify our analysis and show that: 1) The proposed list decoding algorithm with empirical divergence test outperforms the sequential decoding in high signal-to-noise ratio (SNR) region; 2) Taking the tail-biting convolutional codes (TBCC) as the basic codes, the proposed list decoding of SRUMCCs have comparable performance with the polar codes under the constraint of equivalent decoding delay.

cs.IT↗
arXiv2020

Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction

Understanding crowd motion dynamics is critical to real-world applications, e.g., surveillance systems and autonomous driving. This is challenging because it requires effectively modeling the socially aware crowd spatial interaction and complex temporal dependencies. We believe attention is the most important factor for trajectory prediction. In this paper, we present STAR, a Spatio-Temporal grAph tRansformer framework, which tackles trajectory prediction by only attention mechanisms. STAR models intra-graph crowd interaction by TGConv, a novel Transformer-based graph convolution mechanism. The inter-graph temporal dependencies are modeled by separate temporal Transformers. STAR captures complex spatio-temporal interactions by interleaving between spatial and temporal Transformers. To calibrate the temporal prediction for the long-lasting effect of disappeared pedestrians, we introduce a read-writable external memory module, consistently being updated by the temporal Transformer. We show that with only attention mechanism, STAR achieves state-of-the-art performance on 5 commonly used real-world pedestrian prediction datasets.

cs.CV↗
arXiv2020

DinerDash Gym: A Benchmark for Policy Learning in High-Dimensional Action Space

It has been arduous to assess the progress of a policy learning algorithm in the domain of hierarchical task with high dimensional action space due to the lack of a commonly accepted benchmark. In this work, we propose a new light-weight benchmark task called Diner Dash for evaluating the performance in a complicated task with high dimensional action space. In contrast to the traditional Atari games that only have a flat structure of goals and very few actions, the proposed benchmark task has a hierarchical task structure and size of 57 for the action space and hence can facilitate the development of policy learning in complicated tasks. On top of that, we introduce Decomposed Policy Graph Modelling (DPGM), an algorithm that combines both graph modelling and deep learning to allow explicit domain knowledge embedding and achieves significant improvement comparing to the baseline. In the experiments, we have shown the effectiveness of the domain knowledge injection via a specially designed imitation algorithm as well as results of other popular algorithms.

cs.LG↗
arXiv2020

R3: A Reading Comprehension Benchmark Requiring Reasoning Processes

Existing question answering systems can only predict answers without explicit reasoning processes, which hinder their explainability and make us overestimate their ability of understanding and reasoning over natural language. In this work, we propose a novel task of reading comprehension, in which a model is required to provide final answers and reasoning processes. To this end, we introduce a formalism for reasoning over unstructured text, namely Text Reasoning Meaning Representation (TRMR). TRMR consists of three phrases, which is expressive enough to characterize the reasoning process to answer reading comprehension questions. We develop an annotation platform to facilitate TRMR's annotation, and release the R3 dataset, a \textbf{R}eading comprehension benchmark \textbf{R}equiring \textbf{R}easoning processes. R3 contains over 60K pairs of question-answer pairs and their TRMRs. Our dataset is available at: \url{http://anonymous}.

cs.CL↗
arXiv2020

Challenges in Supporting Exploratory Search through Voice Assistants

Voice assistants have been successfully adopted for simple, routine tasks, such as asking for the weather or setting an alarm. However, as people get more familiar with voice assistants, they may increase their expectations for more complex tasks, such as exploratory search-- e.g., "What should I do when I visit Paris with kids? Oh, and ideally not too expensive." Compared to simple search tasks such as "How tall is the Eiffel Tower?", which can be answered with a single-shot answer, the response to exploratory search is more nuanced, especially through voice-based assistants. In this paper, we outline four challenges in designing voice assistants that can better support exploratory search: addressing situationally induced impairments; working with mixed-modal interactions; designing for diverse populations; and meeting users' expectations and gaining their trust. Addressing these challenges is important for developing more "intelligent" voice-based personal assistants.

cs.HC↗
arXiv2020

AI-Mediated Exchange Theory

As Artificial Intelligence (AI) plays an ever-expanding role in sociotechnical systems, it is important to articulate the relationships between humans and AI. However, the scholarly communities studying human-AI relationships -- including but not limited to social computing, machine learning, science and technology studies, and other social sciences -- are divided by the perspectives that define them. These perspectives vary both by their focus on humans or AI, and in the micro/macro lenses through which they approach subjects. These differences inhibit the integration of findings, and thus impede science and interdisciplinarity. In this position paper, we propose the development of a framework AI-Mediated Exchange Theory (AI-MET) to bridge these divides. As an extension to Social Exchange Theory (SET) in the social sciences, AI-MET views AI as influencing human-to-human relationships via a taxonomy of mediation mechanisms. We list initial ideas of these mechanisms, and show how AI-MET can be used to help human-AI research communities speak to one another.

cs.HC↗
arXiv2020

Binary Representaion for Non-binary LDPC Code with Decoder Design

The equivalent binary parity check matrices for the binary images of the cycle-free non-binary LDPC codes have numerous bit-level cycles. In this paper, we show how to transform these binary parity check matrices into their cycle-free forms. It is shown that the proposed methodology can be adopted not only for the binary images of non-binary LDPC codes but also for a large class of binary LDPC codes. Specifically, we present an extended $p$-reducible (EPR) LDPC code structure to eliminate the bit-level cycles. For the non-binary LDPC codes with short length symbol-level cycles, the EPR-LDPC codes can largely avoid the corresponding short length bit-level cycles. As to the decoding of the EPR-LDPC codes, we propose a hybrid hard-decision decoder and a hybrid parallel decoder for binary symmetric channel and binary input Gaussian channel, respectively. A simple code optimization algorithm for these binary decoders is also provided. Simulations show the comparative results and justify the advantages, i.e., better performance and lower decoding complexity, of the proposed binary constructions.

eess.SP↗