arXiv subjects

Jin Ma

Publications and source records attributed to Jin Ma.

At least 91 records · Page 5Linked to original sources

arXiv2022

Domain Adaptive Object Detection for Autonomous Driving under Foggy Weather

Most object detection methods for autonomous driving usually assume a consistent feature distribution between training and testing data, which is not always the case when weathers differ significantly. The object detection model trained under clear weather might not be effective enough in foggy weather because of the domain gap. This paper proposes a novel domain adaptive object detection framework for autonomous driving under foggy weather. Our method leverages both image-level and object-level adaptation to diminish the domain discrepancy in image style and object appearance. To further enhance the model's capabilities under challenging samples, we also come up with a new adversarial gradient reversal layer to perform adversarial mining for the hard examples together with domain adaptation. Moreover, we propose to generate an auxiliary domain by data augmentation to enforce a new domain-level metric regularization. Experimental results on public benchmarks show the effectiveness and accuracy of the proposed method. The code is available at https://github.com/jinlong17/DA-Detect.

cs.CV↗

arXiv2022

ChiQA: A Large Scale Image-based Real-World Question Answering Dataset for Multi-Modal Understanding

Visual question answering is an important task in both natural language and vision understanding. However, in most of the public visual question answering datasets such as VQA, CLEVR, the questions are human generated that specific to the given image, such as `What color are her eyes?'. The human generated crowdsourcing questions are relatively simple and sometimes have the bias toward certain entities or attributes. In this paper, we introduce a new question answering dataset based on image-ChiQA. It contains the real-world queries issued by internet users, combined with several related open-domain images. The system should determine whether the image could answer the question or not. Different from previous VQA datasets, the questions are real-world image-independent queries that are more various and unbiased. Compared with previous image-retrieval or image-caption datasets, the ChiQA not only measures the relatedness but also measures the answerability, which demands more fine-grained vision and language reasoning. ChiQA contains more than 40K questions and more than 200K question-images pairs. A three-level 2/1/0 label is assigned to each pair indicating perfect answer, partially answer and irrelevant. Data analysis shows ChiQA requires a deep understanding of both language and vision, including grounding, comparisons, and reading. We evaluate several state-of-the-art visual-language models such as ALBEF, demonstrating that there is still a large room for improvements on ChiQA.

cs.CL↗

arXiv2022

A Generalized Kyle-Back Strategic Insider Trading Model with Dynamic Information

In this paper we consider a class of generalized Kyle-Back strategic insider trading models in which the insider is able to use the dynamic information obtained by observing the instantaneous movement of an underlying asset that is allowed to be influenced by its market price. Since such a model will be largely outside the Gaussian paradigm, we shall try to Markovize it by introducing an auxiliary diffusion process, in the spirit of the weighted total order process of, e.g., \cite{CCD11}, as a part of the "pricing rule". As the main technical tool in solving the Kyle-Back equilibrium, we study a class of Stochastic Two-Point Boundary Value Problem (STPBVP), which resembles the dynamic Markovian bridge in the literature, but without insisting on its local martingale requirement. In the case when the solution of the STPBVP has an affine structure, we show that the pricing rule functions, whence the Kyle-Back equilibrium, can be determined by the decoupling field of a forward-backward SDE obtained via a non-linear filtering approach, along with a set of compatibility conditions.

math.PR↗

arXiv2021

Boosting Image Outpainting with Semantic Layout Prediction

The objective of image outpainting is to extend image current border and generate new regions based on known ones. Previous methods adopt generative adversarial networks (GANs) to synthesize realistic images. However, the lack of explicit semantic representation leads to blurry and abnormal image pixels when the outpainting areas are complex and with various objects. In this work, we decompose the outpainting task into two stages. Firstly, we train a GAN to extend regions in semantic segmentation domain instead of image domain. Secondly, another GAN model is trained to synthesize real images based on the extended semantic layouts. The first model focuses on low frequent context such as sizes, classes and other semantic cues while the second model focuses on high frequent context like color and texture. By this design, our approach can handle semantic clues more easily and hence works better in complex scenarios. We evaluate our framework on various datasets and make quantitative and qualitative analysis. Experiments demonstrate that our method generates reasonable extended semantic layouts and images, outperforming state-of-the-art models.

cs.CV↗

arXiv2021

A General Conditional McKean-Vlasov Stochastic Differential Equation

In this paper we consider a class of {\it conditional McKean-Vlasov SDEs} (CMVSDE for short). Such an SDE can be considered as an extended version of McKean-Vlasov SDEs with common noises, as well as the general version of the so-called {\it conditional mean-field SDEs} (CMFSDE) studied previously by the authors [1, 14], but with some fundamental differences. In particular, due to the lack of compactness of the iterated conditional laws, the existing arguments of Schauder's fixed point theorem do not seem to apply in this situation, and the heavy nonlinearity on the conditional laws caused by change of probability measure adds more technical subtleties. Under some structure assumptions on the coefficients of the observation equation, we prove the well-posedness of solution in the weak sense along a more direct approach. Our result is the first that deals with McKean-Vlasov type SDEs involving state-dependent conditional laws.

math.PR↗

arXiv2021

Out-of-Step Detection Based On an Improved Line Potential Energy Criterion

The line potential energy in the cutset is used as the criterion for monitoring the generator instability, but the criterion has the following two limitations due to narrowly defined conditions. The assumption of an ideal constant power load is difficult to satisfy, and the condition of the critical cutset is too narrow. The limitations are addressed by analyzing the relationship between the power of the load elements and the power of the cutset based on the two-machine equivalent. Modifications of the theoretical derivation steps of this criterion are presented to extend the applications of the criterion and provide theoretical support for its online use. Two simple strategies are proposed to ensure early detection of the generator instability.

eess.SY↗

arXiv2021

Set-Valued Backward Stochastic Differential Equations

In this paper, we establish an analytic framework for studying set-valued backward stochastic differential equations (set-valued BSDE), motivated largely by the current studies of dynamic set-valued risk measures for multi-asset or network-based financial models. Our framework will make use of the notion of Hukuhara difference between sets, in order to compensate the lack of "inverse" operation of the traditional Minkowski addition, whence the vector space structure in set-valued analysis. While proving the well-posedness of a class of set-valued BSDEs, we shall also address some fundamental issues regarding generalized Aumann-Itô integrals, especially when it is connected to the martingale representation theorem. In particular, we propose some necessary extensions of the integral that can be used to represent set-valued martingales with non-singleton initial values. This extension turns out to be essential for the study of set-valued BSDEs.

math.PR↗

arXiv2021

Research on False Data Injection Attacks in VSC-HVDC Systems

The false data injection (FDI) attack is a crucial form of cyber-physical security problems facing cyber-physical power systems. However, there is no research revealing the problem of FDI attacks facing voltage source converter based high voltage direct current transmission (VSC-HVDC) systems. Firstly, the general form of the model of FDI attack strategies is proposed and the essence of the problem of FDI attack strategies is further analyzed. Moreover, the model of FDI attack strategies aiming at disrupting the operation security of converter stations in VSC-HVDC systems is proposed and its solving algorithm is then presented. And finally, the modified IEEE-14 bus system is utilized to reveal the problem of FDI attacks facing VSC-HVDC systems, demonstrating that attackers are capable of disrupting the operation security of converter stations in VSC-HVDC systems by FDI attacks.

eess.SY↗

arXiv2020

Time-consistent conditional expectation under probability distortion

We introduce a new notion of conditional nonlinear expectation under probability distortion. Such a distorted nonlinear expectation is not sub-additive in general, so it is beyond the scope of Peng's framework of nonlinear expectations. A more fundamental problem when extending the distorted expectation to a dynamic setting is time-inconsistency, that is, the usual "tower property" fails. By localizing the probability distortion and restricting to a smaller class of random variables, we introduce a so-called distorted probability and construct a conditional expectation in such a way that it coincides with the original nonlinear expectation at time zero, but has a time-consistent dynamics in the sense that the tower property remains valid. Furthermore, we show that in the continuous time model this conditional expectation corresponds to a parabolic differential equation whose coefficient involves the law of the underlying diffusion. This work is the first step towards a new understanding of nonlinear expectations under probability distortion, and will potentially be a helpful tool for solving time-inconsistent stochastic optimization problems.

q-fin.MF↗

arXiv2020

The rate of convergence of harmonic explorer to SLE4

Using the estimate of the difference between the discrete harmonic function and its corresponding continuous version we derive a rate of convergence of the Loewner driving function for the harmonic explorer to the Brownian motion with speed 4 on the real line. Based on this convergence rate, the derivative estimate for chordal $\mbox{SLE}_4$, and the estimate of tip structure modulus for harmonic explorer paths, we obtain an explicit power-law rate of convergence of the harmonic explorer paths to the trace of chordal $\mbox{SLE}_4$ in the supremum distance.

math.PR↗

arXiv2020

Equilibrium Model of Limit Order Books: A Mean-field Game View

In this paper we study a continuous time equilibrium model of limit order book (LOB) in which the liquidity dynamics follows a non-local, reflected mean-field stochastic differential equation (SDE) with evolving intensity. Generalizing the basic idea of Ma et al. (2015), we argue that the frontier of the LOB (e.g., the best asking price) is the value function of a mean-field stochastic control problem, as the limiting version of a Bertrand-type competition among the liquidity providers. With a detailed analysis on the $N$-seller static Bertrand game, we formulate a continuous time limiting mean-field control problem of the representative seller. We then validate the dynamic programming principle (DPP), and show that the value function is a viscosity solution of the corresponding Hamilton-Jacobi-Bellman (HJB) equation. We argue that the value function can be used to obtain the equilibrium density function of the LOB, following the idea of Ma et al. (2015).

math.OC↗

arXiv2019

Bayesian Grasp: Robotic visual stable grasp based on prior tactile knowledge

Robotic grasp detection is a fundamental capability for intelligent manipulation in unstructured environments. Previous work mainly employed visual and tactile fusion to achieve stable grasp, while, the whole process depending heavily on regrasping, which wastes much time to regulate and evaluate. We propose a novel way to improve robotic grasping: by using learned tactile knowledge, a robot can achieve a stable grasp from an image. First, we construct a prior tactile knowledge learning framework with novel grasp quality metric which is determined by measuring its resistance to external perturbations. Second, we propose a multi-phases Bayesian Grasp architecture to generate stable grasp configurations through a single RGB image based on prior tactile knowledge. Results show that this framework can classify the outcome of grasps with an average accuracy of 86% on known objects and 79% on novel objects. The prior tactile knowledge improves the successful rate of 55% over traditional vision-based strategies.

cs.RO↗

arXiv2019

On Optimal Dividend and Investment Strategy under Renewal Risk Models

In this paper we continue investigating the optimal dividend and investment problems under the Sparre Andersen model. More precisely, we assume that the claim frequency is a renewal process instead of a standard compound Poisson process, whence semi-Markovian. Building on our previous work \cite{BaiMa17}, where we established the dynamic programming principle via a {\it backward Markovization} procedure and proved that the value function is the unique {\it constrained} viscosity solution of the HJB equation, in this paper we focus on the construction of the optimal strategy. The main difficulties in this effort is two fold: the regularity of the viscosity solution to a non-local, nonlinear, and degenerate parabolic PDE on an unbounded domain, which seems to be new in its own right; and the well-posedness of the closed-loop stochastic system. By introducing an auxiliary PDE, we construct an $\e$-optimal strategy, and prove the well-posedness of the corresponding closed-loop system, via a "bootstrap" technique with the help of a Krylov estimate.

math.PR↗

arXiv2019

IPRE: a Dataset for Inter-Personal Relationship Extraction

Inter-personal relationship is the basis of human society. In order to automatically identify the relations between persons from texts, we need annotated data for training systems. However, there is a lack of a massive amount of such data so far. To address this situation, we introduce IPRE, a new dataset for inter-personal relationship extraction which aims to facilitate information extraction and knowledge graph construction research. In total, IPRE has over 41,000 labeled sentences for 34 types of relations, including about 9,000 sentences annotated by workers. Our data is the first dataset for inter-personal relationship extraction. Additionally, we define three evaluation tasks based on IPRE and provide the baseline systems for further comparison in future work.

cs.CL↗

arXiv2019

Object-Agnostic Suction Grasp Affordance Detection in Dense Cluster Using Self-Supervised Learning.docx

In this paper we study grasp problem in dense cluster, a challenging task in warehouse logistics scenario. By introducing a two-step robust suction affordance detection method, we focus on using vacuum suction pad to clear up a box filled with seen and unseen objects. Two CNN based neural networks are proposed. A Fast Region Estimation Network (FRE-Net) predicts which region contains pickable objects, and a Suction Grasp Point Affordance network (SGPA-Net) determines which point in that region is pickable. So as to enable such two networks, we design a self-supervised learning pipeline to accumulate data, train and test the performance of our method. In both virtual and real environment, within 1500 picks (~5 hours), we reach a picking accuracy of 95% for known objects and 90% for unseen objects with similar geometry features.

cs.RO↗

arXiv2019

Bayesian Optimized Continual Learning with Attention Mechanism

Though neural networks have achieved much progress in various applications, it is still highly challenging for them to learn from a continuous stream of tasks without forgetting. Continual learning, a new learning paradigm, aims to solve this issue. In this work, we propose a new model for continual learning, called Bayesian Optimized Continual Learning with Attention Mechanism (BOCL) that dynamically expands the network capacity upon the arrival of new tasks by Bayesian optimization and selectively utilizes previous knowledge (e.g. feature maps of previous tasks) via attention mechanism. Our experiments on variants of MNIST and CIFAR-100 demonstrate that our methods outperform the state-of-the-art in preventing catastrophic forgetting and fitting new tasks better.

cs.LG↗

arXiv2019

Suction Grasp Region Prediction using Self-supervised Learning for Object Picking in Dense Clutter

This paper focuses on robotic picking tasks in cluttered scenario. Because of the diversity of poses, types of stack and complicated background in bin picking situation, it is much difficult to recognize and estimate their pose before grasping them. Here, this paper combines Resnet with U-net structure, a special framework of Convolution Neural Networks (CNN), to predict picking region without recognition and pose estimation. And it makes robotic picking system learn picking skills from scratch. At the same time, we train the network end to end with online samples. In the end of this paper, several experiments are conducted to demonstrate the performance of our methods.

cs.RO↗

arXiv2018

Deep Feature Aggregation and Image Re-ranking with Heat Diffusion for Image Retrieval

Image retrieval based on deep convolutional features has demonstrated state-of-the-art performance in popular benchmarks. In this paper, we present a unified solution to address deep convolutional feature aggregation and image re-ranking by simulating the dynamics of heat diffusion. A distinctive problem in image retrieval is that repetitive or \emph{bursty} features tend to dominate final image representations, resulting in representations less distinguishable. We show that by considering each deep feature as a heat source, our unsupervised aggregation method is able to avoid over-representation of \emph{bursty} features. We additionally provide a practical solution for the proposed aggregation method and further show the efficiency of our method in experimental evaluation. Inspired by the aforementioned deep feature aggregation method, we also propose a method to re-rank a number of top ranked images for a given query image by considering the query as the heat source. Finally, we extensively evaluate the proposed approach with pre-trained and fine-tuned deep networks on common public benchmarks and show superior performance compared to previous work.

cs.IR↗