arXiv subjects

Tianyu Wang

Publications and source records attributed to Tianyu Wang.

At least 235 records · Page 13Linked to original sources

arXiv2021

Revisiting Shadow Detection: A New Benchmark Dataset for Complex World

Shadow detection in general photos is a nontrivial problem, due to the complexity of the real world. Though recent shadow detectors have already achieved remarkable performance on various benchmark data, their performance is still limited for general real-world situations. In this work, we collected shadow images for multiple scenarios and compiled a new dataset of 10,500 shadow images, each with labeled ground-truth mask, for supporting shadow detection in the complex world. Our dataset covers a rich variety of scene categories, with diverse shadow sizes, locations, contrasts, and types. Further, we comprehensively analyze the complexity of the dataset, present a fast shadow detection network with a detail enhancement module to harvest shadow details, and demonstrate the effectiveness of our method to detect shadows in general situations.

cs.CV↗

arXiv2021

Inverse reinforcement learning for autonomous navigation via differentiable semantic mapping and planning

This paper focuses on inverse reinforcement learning for autonomous navigation using distance and semantic category observations. The objective is to infer a cost function that explains demonstrated behavior while relying only on the expert's observations and state-control trajectory. We develop a map encoder, that infers semantic category probabilities from the observation sequence, and a cost encoder, defined as a deep neural network over the semantic features. Since the expert cost is not directly observable, the model parameters can only be optimized by differentiating the error between demonstrated controls and a control policy computed from the cost estimate. We propose a new model of expert behavior that enables error minimization using a closed-form subgradient computed only over a subset of promising states via a motion planning algorithm. Our approach allows generalizing the learned behavior to new environments with new spatial configurations of the semantic categories. We analyze the different components of our model in a minigrid environment. We also demonstrate that our approach learns to follow traffic rules in the autonomous driving CARLA simulator by relying on semantic observations of buildings, sidewalks, and road lanes.

cs.LG↗

arXiv2020

Adaptive Discretization for Model-Based Reinforcement Learning

We introduce the technique of adaptive discretization to design an efficient model-based episodic reinforcement learning algorithm in large (potentially continuous) state-action spaces. Our algorithm is based on optimistic one-step value iteration extended to maintain an adaptive discretization of the space. From a theoretical perspective we provide worst-case regret bounds for our algorithm which are competitive compared to the state-of-the-art model-based algorithms. Moreover, our bounds are obtained via a modular proof technique which can potentially extend to incorporate additional structure on the problem. From an implementation standpoint, our algorithm has much lower storage and computational requirements due to maintaining a more efficient partition of the state and action spaces. We illustrate this via experiments on several canonical control problems, which shows that our algorithm empirically performs significantly better than fixed discretization in terms of both faster convergence and lower memory usage. Interestingly, we observe empirically that while fixed-discretization model-based algorithms vastly outperform their model-free counterparts, the two achieve comparable performance with adaptive discretization.

cs.LG↗

arXiv2020

Bandits for BMO Functions

We study the bandit problem where the underlying expected reward is a Bounded Mean Oscillation (BMO) function. BMO functions are allowed to be discontinuous and unbounded, and are useful in modeling signals with infinities in the do-main. We develop a toolset for BMO bandits, and provide an algorithm that can achieve poly-log $δ$-regret -- a regret measured against an arm that is optimal after removing a $δ$-sized portion of the arm space.

cs.LG↗

arXiv2020

Learning Navigation Costs from Demonstration with Semantic Observations

This paper focuses on inverse reinforcement learning (IRL) for autonomous robot navigation using semantic observations. The objective is to infer a cost function that explains demonstrated behavior while relying only on the expert's observations and state-control trajectory. We develop a map encoder, which infers semantic class probabilities from the observation sequence, and a cost encoder, defined as deep neural network over the semantic features. Since the expert cost is not directly observable, the representation parameters can only be optimized by differentiating the error between demonstrated controls and a control policy computed from the cost estimate. The error is optimized using a closed-form subgradient computed only over a subset of promising states via a motion planning algorithm. We show that our approach learns to follow traffic rules in the autonomous driving CARLA simulator by relying on semantic observations of cars, sidewalks and road lanes.

cs.LG↗

arXiv2020

Instance Shadow Detection

Instance shadow detection is a brand new problem, aiming to find shadow instances paired with object instances. To approach it, we first prepare a new dataset called SOBA, named after Shadow-OBject Association, with 3,623 pairs of shadow and object instances in 1,000 photos, each with individual labeled masks. Second, we design LISA, named after Light-guided Instance Shadow-object Association, an end-to-end framework to automatically predict the shadow and object instances, together with the shadow-object associations and light direction. Then, we pair up the predicted shadow and object instances, and match them with the predicted shadow-object associations to generate the final results. In our evaluations, we formulate a new metric named the shadow-object average precision to measure the performance of our results. Further, we conducted various experiments and demonstrate our method's applicability on light direction estimation and photo editing.

cs.CV↗

arXiv2020

SAC-Net: Spatial Attenuation Context for Salient Object Detection

This paper presents a new deep neural network design for salient object detection by maximizing the integration of local and global image context within, around, and beyond the salient objects. Our key idea is to adaptively propagate and aggregate the image context features with variable attenuation over the entire feature maps. To achieve this, we design the spatial attenuation context (SAC) module to recurrently translate and aggregate the context features independently with different attenuation factors and then to attentively learn the weights to adaptively integrate the aggregated context features. By further embedding the module to process individual layers in a deep network, namely SAC-Net, we can train the network end-to-end and optimize the context features for detecting salient objects. Compared with 29 state-of-the-art methods, experimental results show that our method performs favorably over all the others on six common benchmark data, both quantitatively and visually.

cs.CV↗

arXiv2020

Directional Compliance in Obstacle-Aided Navigation for Snake Robots

Snake robots have the potential to maneuver through tightly packed and complex environments. One challenge in enabling them to do so is the complexity in determining how to coordinate their many degrees-of-freedom to create purposeful motion. This is especially true in the types of terrains considered in this work: environments full of unmodeled features that even the best of maps would not capture, motivating us to develop closed-loop controls to react to those features. To accomplish this, this work uses proprioceptive sensing, mainly the force information measured by the snake robot's joints, to react to unmodeled terrain. We introduce a biologically-inspired strategy called directional compliance which modulates the effective stiffness of the robot so that it conforms to the terrain in some directions and resists in others. We present a dynamical system that switches between modes of locomotion to handle situations in which the robot gets wedged or stuck. This approach enables the snake robot to reliably traverse a planar peg array and an outdoor three-dimensional pile of rocks.

cs.RO↗

arXiv2020

Learning Navigation Costs from Demonstration in Partially Observable Environments

This paper focuses on inverse reinforcement learning (IRL) to enable safe and efficient autonomous navigation in unknown partially observable environments. The objective is to infer a cost function that explains expert-demonstrated navigation behavior while relying only on the observations and state-control trajectory used by the expert. We develop a cost function representation composed of two parts: a probabilistic occupancy encoder, with recurrent dependence on the observation sequence, and a cost encoder, defined over the occupancy features. The representation parameters are optimized by differentiating the error between demonstrated controls and a control policy computed from the cost encoder. Such differentiation is typically computed by dynamic programming through the value function over the whole state space. We observe that this is inefficient in large partially observable environments because most states are unexplored. Instead, we rely on a closed-form subgradient of the cost-to-go obtained only over a subset of promising states via an efficient motion-planning algorithm such as A* or RRT. Our experiments show that our model exceeds the accuracy of baseline IRL algorithms in robot navigation tasks, while substantially improving the efficiency of training and test-time inference.

cs.LG↗

arXiv2019

The Controlled Large-Area Synthesis of Two Dimensional Metals

The rise of nanotechnology has been propelled by low dimensional metals. Albeit the long perceived importance, synthesis of freestanding metallic nanomembranes, or the so-called 2D metals, however has been restricted to simple metals with a very limited in-plane size (< 10μm). In this work, we developed a low-cost method to synthesize 2D metals through polymer surface buckling enabled exfoliation. The 2D metals so obtained could be as chemically complex as high entropy alloys while possessing in-plane dimensions at the scale of bulk metals (> 1 cm). With our approach, we successfully synthesized a variety of 2D metals, such as 2D high entropy alloy and 2D metallic glass, with controllable geometries and morphologies. Moreover, our approach can be readily extended to non-metals and composites, thereby opening a large window to the fabrication of a wide range of 2D materials of technologic importance which have never been reported before.

physics.app-ph↗

arXiv2019

Unique equilibrium states, large deviations and Lyapunov spectra for the Katok Map

We study the thermodynamic formalism of a $C^{\infty}$ non-uniformly hyperbolic diffeomorphism on the 2-torus, known as the Katok map. We prove for a Hölder continuous potential with one additional condition, or the geometric t-potential $φ_t$ with $t<1$, the equilibrium state exists and is unique. We derive the level-2 large deviation principle for the equilibrium state of $φ_t$. We study the multifractal spectra of the Katok map for the entropy and dimension of level sets of Lyapunov exponents.

math.DS↗

arXiv2019

Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset

Removing rain streaks from a single image has been drawing considerable attention as rain streaks can severely degrade the image quality and affect the performance of existing outdoor vision tasks. While recent CNN-based derainers have reported promising performances, deraining remains an open problem for two reasons. First, existing synthesized rain datasets have only limited realism, in terms of modeling real rain characteristics such as rain shape, direction and intensity. Second, there are no public benchmarks for quantitative comparisons on real rain images, which makes the current evaluation less objective. The core challenge is that real world rain/clean image pairs cannot be captured at the same time. In this paper, we address the single image rain removal problem in two ways. First, we propose a semi-automatic method that incorporates temporal priors and human supervision to generate a high-quality clean image from each input sequence of real rain images. Using this method, we construct a large-scale dataset of $\sim$$29.5K$ rain/rain-free image pairs that covers a wide range of natural rain scenes. Second, to better cover the stochastic distribution of real rain streaks, we propose a novel SPatial Attentive Network (SPANet) to remove rain streaks in a local-to-global manner. Extensive experiments demonstrate that our network performs favorably against the state-of-the-art deraining methods.

cs.CV↗

arXiv2019

Shortest Paths in HSI Space for Color Texture Classification

Color texture representation is an important step in the task of texture classification. Shortest paths was used to extract color texture features from RGB and HSV color spaces. In this paper, we propose to use shortest paths in the HSI space to build a texture representation for classification. In particular, two undirected graphs are used to model the H channel and the S and I channels respectively in order to represent a color texture image. Moreover, the shortest paths is constructed by using four pairs of pixels according to different scales and directions of the texture image. Experimental results on colored Brodatz and USPTex databases reveal that our proposed method is effective, and the highest classification accuracy rate is 96.93% in the Brodatz database.

cs.CV↗

arXiv2017

Electric Field Effect in Multilayer Cr2Ge2Te6: a Ferromagnetic Two-Dimensional Material

The emergence of two-dimensional (2D) materials has attracted a great deal of attention due to their fascinating physical properties and potential applications for future nanoelectronic devices. Since the first isolation of graphene, a Dirac material, a large family of new functional 2D materials have been discovered and characterized, including insulating 2D boron nitride, semiconducting 2D transition metal dichalcogenides and black phosphorus, and superconducting 2D bismuth strontium calcium copper oxide, molybdenum disulphide and niobium selenide, etc. Here, we report the identification of ferromagnetic thin flakes of Cr2Ge2Te6 (CGT) with thickness down to a few nanometers, which provides a very important piece to the van der Waals structures consisting of various 2D materials. We further demonstrate the giant modulation of the channel resistance of 2D CGT devices via electric field effect. Our results illustrate the gate voltage tunability of 2D CGT and the potential of CGT, a ferromagnetic 2D material, as a new functional quantum material for applications in future nanoelectronics and spintronics.

cond-mat.mtrl-sci↗

arXiv2017

Objective Image Quality Assessment for High Resolution Photospheric Images by Median Filter Gradient Similarity

All next generation ground-based and space-based solar telescopes require a good quality assessment metric in order to evaluate their imaging performance. In this paper, a new image quality metric, the median filter gradient similarity (MFGS) is proposed for photospheric images. MFGS is a no-reference/blind objective image quality metric (IQM) by a measurement result between 0 and 1 and has been performed on short-exposure photospheric images captured by the New Vacuum Solar Telescope (NVST) of the Fuxian Solar Observatory and by the Solar Optical Telescope (SOT) onboard the Hinode satellite, respectively. The results show that: (1)the measured value of MFGS changes monotonically from 1 to 0 with degradation of image quality; (2)there exists a linear correlation between the measured values of MFGS and root-mean-square-contrast (RMS-contrast) of granulation; (3)MFGS is less affected by the image contents than the granular RMS-contrast. Overall, MFGS is a good alternative for the quality assessment of photospheric images.

astro-ph.IM↗

arXiv2016

Spin Injection and Inverse Edelstein Effect in the Surface States of Topological Kondo Insulator SmB6

There has been considerable interest in exploiting the spin degrees of freedom of electrons for potential information storage and computing technologies. Topological insulators (TI), a class of quantum materials, have special gapless edge/surface states, where the spin polarization of the Dirac fermions is locked to the momentum direction. This spin-momentum locking property gives rise to very interesting spin-dependent physical phenomena such as the Edelstein and inverse Edelstein effects. However, the spin injection in pure surface states of TI is very challenging because of the coexistence of the highly conducting bulk states. Here, we experimentally demonstrate the spin injection and observe the inverse Edelstein effect in the surface states of a topological Kondo insulator, SmB6. At low temperatures when only surface carriers are present, a clear spin signal is observed. Furthermore, the magnetic field angle dependence of the spin signal is consistent with spin-momentum locking property of surface states of SmB6.

cond-mat.mes-hall↗

arXiv2016

Positive Exchange Bias between Permalloy and Twined (10-10)-Cr2O3 Films

We report the discovery of a positive exchange bias between Ni80Fe20 (Py) and twined (10-10)-Cr2O3 film near its blocking temperature (TB) when it is cooled in an in-plane magnetic field applied along 45 degrees from the two spin configurations of the Cr atoms. This is an abnormal behavior compared to the negative exchange bias at all temperatures below TB when the cooling and measuring magnetic fields are applied along one of the two spin configurations of the Cr atoms. We speculate these results could be related to the exchange interactions between the twined structure of the (10-10)-Cr2O3 film epitaxially grown on the rutile (001)-TiO2 substrate.

cond-mat.mtrl-sci↗

arXiv2016

Collaborative Smartphone Sensing using Overlapping Coalition Formation Games

With the rapid growth of sensor technology, smartphone sensing has become an effective approach to improve the quality of smartphone applications. However, due to time-varying wireless channels and lack of incentives for the users to participate, the quality and quantity of the data uploaded by the smartphone users are not always satisfying. In this paper, we consider a smartphone sensing system in which a platform publicizes multiple tasks, and the smartphone users choose a set of tasks to participate in. In the traditional non-cooperative approach with incentives, each smartphone user gets rewards from the platform as an independent individual and the limit of the wireless channel resources is often omitted. To tackle this problem, we introduce a novel cooperative approach with an overlapping coalition formation game (OCF-game) model, in which the smartphone users can cooperate with each other to form the overlapping coalitions for different sensing tasks. We also utilize a centralized case to describe the upper bound of the system sensing performance. Simulation results show that the cooperative approach achieves a better performance than the non-cooperative one in various situations.

cs.DC↗