arXiv subjects

Jia Li

Publications and source records attributed to Jia Li.

At least 559 records · Page 31Linked to original sources

arXiv2019

Spatiotemporal Knowledge Distillation for Efficient Estimation of Aerial Video Saliency

The performance of video saliency estimation techniques has achieved significant advances along with the rapid development of Convolutional Neural Networks (CNNs). However, devices like cameras and drones may have limited computational capability and storage space so that the direct deployment of complex deep saliency models becomes infeasible. To address this problem, this paper proposes a dynamic saliency estimation approach for aerial videos via spatiotemporal knowledge distillation. In this approach, five components are involved, including two teachers, two students and the desired spatiotemporal model. The knowledge of spatial and temporal saliency is first separately transferred from the two complex and redundant teachers to their simple and compact students, and the input scenes are also degraded from high-resolution to low-resolution to remove the probable data redundancy so as to greatly speed up the feature extraction process. After that, the desired spatiotemporal model is further trained by distilling and encoding the spatial and temporal saliency knowledge of two students into a unified network. In this manner, the inter-model redundancy can be further removed for the effective estimation of dynamic saliency on aerial videos. Experimental results show that the proposed approach outperforms ten state-of-the-art models in estimating visual saliency on aerial videos, while its speed reaches up to 28,738 FPS on the GPU platform.

cs.CV↗

arXiv2019

Learning from Large-scale Noisy Web Data with Ubiquitous Reweighting for Image Classification

Many advances of deep learning techniques originate from the efforts of addressing the image classification task on large-scale datasets. However, the construction of such clean datasets is costly and time-consuming since the Internet is overwhelmed by noisy images with inadequate and inaccurate tags. In this paper, we propose a Ubiquitous Reweighting Network (URNet) that learns an image classification model from large-scale noisy data. By observing the web data, we find that there are five key challenges, i.e., imbalanced class sizes, high intra-classes diversity and inter-class similarity, imprecise instances, insufficient representative instances, and ambiguous class labels. To alleviate these challenges, we assume that every training instance has the potential to contribute positively by alleviating the data bias and noise via reweighting the influence of each instance according to different class sizes, large instance clusters, its confidence, small instance bags and the labels. In this manner, the influence of bias and noise in the web data can be gradually alleviated, leading to the steadily improving performance of URNet. Experimental results in the WebVision 2018 challenge with 16 million noisy training images from 5000 classes show that our approach outperforms state-of-the-art models and ranks the first place in the image classification task.

cs.CV↗

arXiv2019

Low-resolution Face Recognition in the Wild via Selective Knowledge Distillation

Typically, the deployment of face recognition models in the wild needs to identify low-resolution faces with extremely low computational cost. To address this problem, a feasible solution is compressing a complex face model to achieve higher speed and lower memory at the cost of minimal performance drop. Inspired by that, this paper proposes a learning approach to recognize low-resolution faces via selective knowledge distillation. In this approach, a two-stream convolutional neural network (CNN) is first initialized to recognize high-resolution faces and resolution-degraded faces with a teacher stream and a student stream, respectively. The teacher stream is represented by a complex CNN for high-accuracy recognition, and the student stream is represented by a much simpler CNN for low-complexity recognition. To avoid significant performance drop at the student stream, we then selectively distil the most informative facial features from the teacher stream by solving a sparse graph optimization problem, which are then used to regularize the fine-tuning process of the student stream. In this way, the student stream is actually trained by simultaneously handling two tasks with limited computational resources: approximating the most informative facial cues via feature regression, and recovering the missing facial cues via low-resolution face classification. Experimental results show that the student stream performs impressively in recognizing low-resolution faces and costs only 0.15MB memory and runs at 418 faces per second on CPU and 9,433 faces per second on GPU.

cs.CV↗

arXiv2019

Harmonic Unpaired Image-to-image Translation

The recent direction of unpaired image-to-image translation is on one hand very exciting as it alleviates the big burden in obtaining label-intensive pixel-to-pixel supervision, but it is on the other hand not fully satisfactory due to the presence of artifacts and degenerated transformations. In this paper, we take a manifold view of the problem by introducing a smoothness term over the sample graph to attain harmonic functions to enforce consistent mappings during the translation. We develop HarmonicGAN to learn bi-directional translations between the source and the target domains. With the help of similarity-consistency, the inherent self-consistency property of samples can be maintained. Distance metrics defined on two types of features including histogram and CNN are exploited. Under an identical problem setting as CycleGAN, without additional manual inputs and only at a small training-time cost, HarmonicGAN demonstrates a significant qualitative and quantitative improvement over the state of the art, as well as improved interpretability. We show experimental results in a number of applications including medical imaging, object transfiguration, and semantic labeling. We outperform the competing methods in all tasks, and for a medical imaging task in particular our method turns CycleGAN from a failure to a success, halving the mean-squared error, and generating images that radiologists prefer over competing methods in 95% of cases.

cs.CV↗

arXiv2018

Detecting Comma-shaped Clouds for Severe Weather Forecasting using Shape and Motion

Meteorologists use shapes and movements of clouds in satellite images as indicators of several major types of severe storms. Satellite imaginary data are in increasingly higher resolution, both spatially and temporally, making it impossible for humans to fully leverage the data in their forecast. Automatic satellite imagery analysis methods that can find storm-related cloud patterns as soon as they are detectable are in demand. We propose a machine learning and pattern recognition based approach to detect "comma-shaped" clouds in satellite images, which are specific cloud distribution patterns strongly associated with the cyclone formulation. In order to detect regions with the targeted movement patterns, our method is trained on manually annotated cloud examples represented by both shape and motion-sensitive features. Sliding windows in different scales are used to ensure that dense clouds will be captured, and we implement effective selection rules to shrink the region of interest among these sliding windows. Finally, we evaluate the method on a hold-out annotated comma-shaped cloud dataset and cross-match the results with recorded storm events in the severe weather database. The validated utility and accuracy of our method suggest a high potential for assisting meteorologists in weather forecasting.

cs.CV↗

arXiv2018

Visual Attention on the Sun: What Do Existing Models Actually Predict?

Visual attention prediction is a classic problem that seems to be well addressed in the deep learning era. One compelling concern, however, gradually arise along with the rapidly growing performance scores over existing visual attention datasets: do existing deep models really capture the inherent mechanism of human visual attention? To address this concern, this paper proposes a new dataset, named VASUN, that records the free-viewing human attention on solar images. Different from previous datasets, images in VASUN contain many irregular visual patterns that existing deep models have never seen. By benchmarking existing models on VASUN, we find the performances of many state-of-the-art deep models drop remarkably, while many classic shallow models perform impressively. From these results, we find that the significant performance advance of existing deep attention models may come from their capabilities of memorizing and predicting the occurrence of some specific visual patterns other than learning the inherent mechanism of human visual attention. In addition, we also train several baseline models on VASUN to demonstrate the feasibility and key issues of predicting visual attention on the sun. These baseline models, together with the proposed dataset, can be used to revisit the problem of visual attention prediction from a novel perspective that are complementary to existing ones.

cs.CV↗

arXiv2018

Complementary Segmentation of Primary Video Objects with Reversible Flows

Segmenting primary objects in a video is an important yet challenging problem in computer vision, as it exhibits various levels of foreground/background ambiguities. To reduce such ambiguities, we propose a novel formulation via exploiting foreground and background context as well as their complementary constraint. Under this formulation, a unified objective function is further defined to encode each cue. For implementation, we design a Complementary Segmentation Network (CSNet) with two separate branches, which can simultaneously encode the foreground and background information along with joint spatial constraints. The CSNet is trained on massive images with manually annotated salient objects in an end-to-end manner. By applying CSNet on each video frame, the spatial foreground and background maps can be initialized. To enforce temporal consistency effectively and efficiently, we divide each frame into superpixels and construct neighborhood reversible flow that reflects the most reliable temporal correspondences between superpixels in far-away frames. With such flow, the initialized foregroundness and backgroundness can be propagated along the temporal dimension so that primary video objects gradually pop-out and distractors are well suppressed. Extensive experimental results on three video datasets show that the proposed approach achieves impressive performance in comparisons with 18 state-of-the-art models.

cs.CV↗

arXiv2018

Updated Core Libraries of the ALPS Project

The open source ALPS (Algorithms and Libraries for Physics Simulations) project provides a collection of physics libraries and applications, with a focus on simulations of lattice models and strongly correlated electron systems. The libraries provide a convenient set of well-documented and reusable components for developing condensed matter physics simulation codes, and the applications strive to make commonly used and proven computational algorithms available to a non-expert community. In this paper we present an update of the core ALPS libraries. We present in particular new Monte Carlo libraries and new Green's function libraries.

physics.comp-ph↗

arXiv2018

Coordinating Disaster Emergency Response with Heuristic Reinforcement Learning

A crucial and time-sensitive task when any disaster occurs is to rescue victims and distribute resources to the right groups and locations. This task is challenging in populated urban areas, due to the huge burst of help requests generated in a very short period. To improve the efficiency of the emergency response in the immediate aftermath of a disaster, we propose a heuristic multi-agent reinforcement learning scheduling algorithm, named as ResQ, which can effectively schedule the rapid deployment of volunteers to rescue victims in dynamic settings. The core concept is to quickly identify victims and volunteers from social network data and then schedule rescue parties with an adaptive learning algorithm. This framework performs two key functions: 1) identify trapped victims and rescue volunteers, and 2) optimize the volunteers' rescue strategy in a complex time-sensitive environment. The proposed ResQ algorithm can speed up the training processes through a heuristic function which reduces the state-action space by identifying the set of particular actions over others. Experimental results showed that the proposed heuristic multi-agent reinforcement learning based scheduling outperforms several state-of-art methods, in terms of both reward rate and response times.

cs.LG↗

arXiv2018

Hierarchical Deep Co-segmentation of Primary Objects in Aerial Videos

Primary object segmentation plays an important role in understanding videos generated by unmanned aerial vehicles. In this paper, we propose a large-scale dataset with 500 aerial videos and manually annotated primary objects. To the best of our knowledge, it is the largest dataset to date for primary object segmentation in aerial videos. From this dataset, we find most aerial videos contain large-scale scenes, small primary objects as well as consistently varying scales and viewpoints. Inspired by that, we propose a hierarchical deep co-segmentation approach that repeatedly divides a video into two sub-videos formed by the odd and even frames, respectively. In this manner, the primary objects shared by sub-videos can be co-segmented by training two-stream CNNs and finally refined within the neighborhood reversible flows. Experimental results show that our approach remarkably outperforms 17 state-of-the-art methods in segmenting primary objects in various types of aerial videos.

cs.CV↗

arXiv2018

Lifted Proximal Operator Machines

We propose a new optimization method for training feed-forward neural networks. By rewriting the activation function as an equivalent proximal operator, we approximate a feed-forward neural network by adding the proximal operators to the objective function as penalties, hence we call the lifted proximal operator machine (LPOM). LPOM is block multi-convex in all layer-wise weights and activations. This allows us to use block coordinate descent to update the layer-wise weights and activations in parallel. Most notably, we only use the mapping of the activation function itself, rather than its derivatives, thus avoiding the gradient vanishing or blow-up issues in gradient based training methods. So our method is applicable to various non-decreasing Lipschitz continuous activation functions, which can be saturating and non-differentiable. LPOM does not require more auxiliary variables than the layer-wise activations, thus using roughly the same amount of memory as stochastic gradient descent (SGD) does. We further prove the convergence of updating the layer-wise weights and activations. Experiments on MNIST and CIFAR-10 datasets testify to the advantages of LPOM.

cs.LG↗

arXiv2018

Learning a Saliency Evaluation Metric Using Crowdsourced Perceptual Judgments

In the area of human fixation prediction, dozens of computational saliency models are proposed to reveal certain saliency characteristics under different assumptions and definitions. As a result, saliency model benchmarking often requires several evaluation metrics to simultaneously assess saliency models from multiple perspectives. However, most computational metrics are not designed to directly measure the perceptual similarity of saliency maps so that the evaluation results may be sometimes inconsistent with the subjective impression. To address this problem, this paper first conducts extensive subjective tests to find out how the visual similarities between saliency maps are perceived by humans. Based on the crowdsourced data collected in these tests, we conclude several key factors in assessing saliency maps and quantize the performance of existing metrics. Inspired by these factors, we propose to learn a saliency evaluation metric based on a two-stream convolutional neural network using crowdsourced perceptual judgements. Specifically, the relative saliency score of each pair from the crowdsourced data is utilized to regularize the network during the training process. By capturing the key factors shared by various subjects in comparing saliency maps, the learned metric better aligns with human perception of saliency maps, making it a good complement to the existing metrics. Experimental results validate that the learned metric can be generalized to the comparisons of saliency maps from new images, new datasets, new models and synthetic data. Due to the effectiveness of the learned metric, it also can be used to facilitate the development of new models for fixation prediction.

cs.CV↗

arXiv2018

Collaborative Annotation of Semantic Objects in Images with Multi-granularity Supervisions

Per-pixel masks of semantic objects are very useful in many applications, which, however, are tedious to be annotated. In this paper, we propose a human-agent collaborative annotation approach that can efficiently generate per-pixel masks of semantic objects in tagged images with multi-granularity supervisions. Given a set of tagged image, a computer agent is first dynamically generated to roughly localize the semantic objects described by the tag. The agent first extracts massive object proposals from an image and then infer the tag-related ones under the weak and strong supervisions from linguistically and visually similar images and previously annotated object masks. By representing such supervisions by over-complete dictionaries, the tag-related object proposals can pop-out according to their sparse coding length, which are then converted to superpixels with binary labels. After that, human annotators participate in the annotation process by flipping labels and dividing superpixels with mouse clicks, which are used as click supervisions that teach the agent to recover false positives/negatives in processing images with the same tags. Experimental results show that our approach can facilitate the annotation process and generate object masks that are highly consistent with those generated by the LabelMe toolbox.

cs.CV↗

arXiv2018

Ultra-fast wide band spectrum analyzer based on a rapidly tuned spin-torque nano-oscillator

A spintronic method of ultra-fast broadband microwave spectrum analysis is proposed. It uses a rapidly tuned spin torque nano-oscillator (STNO), and does not require injection locking. This method treats an STNO generating a microwave signal as an element with an oscillating resistance. When an external signal is applied to this "resistor" for analysis, it is mixed with the signal generated by the STNO. The resulting mixed voltage contains the "sum" and "difference" frequencies, and the latter produces a DC component when the external frequency matches the frequency generated by the STNO. The mixed voltage is processed using a low pass filter to exclude the "sum" frequency components, and a matched filter to exclude the dependence of the resultant DC voltage on the phase difference between the two signals. It is found analytically and by numerical simulation, that the proposed spectrum analyzer has a frequency resolution at a theoretical limit in a real-time scanning bandwidth of 10~GHz, and a frequency scanning rate above 1~GHz/ns, while remaining sensitive to signal power as low as the Johnson-Nyquist thermal noise floor.

cond-mat.mes-hall↗

arXiv2018

Grid-side Flexibility of Power Systems in Integrating Large-scale Renewable Generations: A Critical Review on Concepts, Formulations and Solution Approaches

Though considerable effort has been devoted to exploiting generation-side and demand-side operational flexibility in order to cope with uncertain renewable generations, grid-side operational flexibility has not been fully investigated. In this review, we define grid-side flexibility as the ability of a power network to deploy its flexibility resources to cope with the changes of power system state, particularly due to variation of renewable generation. Starting with a survey on the metrics of operational flexibility, we explain the definition from both physical and mathematical point of views. Then conceptual examples are presented to demonstrate the impacts of grid-side flexibility graphically, providing a geometric interpretation for a better understanding of the concepts. Afterwards the formulations and solution approaches in terms of grid-side flexibility in power system operation and planning are reviewed, based on which future research directions and challenges are outlined.

math.OC↗

arXiv2018

Resilience Control of DC Shipboard Power Systems

Direct current (DC) network has been recognized as a promising technique, especially for shipboard power systems (SPSs). Fast resilience control is required for an SPS to survive after faults. Towards this end, this paper proposes the indices of survivability and functionality, based on which a two-phase resilience control method is derived. The on/off status of loads are determined in the first phase to maximize survivability, while the functionality of supplying loads are maximized in the second phase. Based on a comprehensive model of a DC shipboard power systems (DC-SPS), the two-phase method renders two mixed-integer non-convex problems. To make the problems tractable, we develop second-order-cone-based convex relaxations, thus converting the problems into mixed-integer convex problems. Though this approach does not necessarily guarantee feasible, hence global, solutions to the original non-convex formulations, we provide additional mild assumptions, which ensures that the convex relaxations are exact when line constraints are not binding. In the case of inexactness, we provide a simple heuristic approach to ensure feasible solutions. Numerical tests empirically confirm the efficacy of the proposed method.

math.OC↗

arXiv2018

Image Co-segmentation via Multi-scale Local Shape Transfer

Image co-segmentation is a challenging task in computer vision that aims to segment all pixels of the objects from a predefined semantic category. In real-world cases, however, common foreground objects often vary greatly in appearance, making their global shapes highly inconsistent across images and difficult to be segmented. To address this problem, this paper proposes a novel co-segmentation approach that transfers patch-level local object shapes which appear more consistent across different images. In our framework, a multi-scale patch neighbourhood system is first generated using proposal flow on arbitrary image-pair, which is further refined by Locally Linear Embedding. Based on the patch relationships, we propose an efficient algorithm to jointly segment the objects in each image while transferring their local shapes across different images. Extensive experiments demonstrate that the proposed method can robustly and effectively segment common objects from an image set. On iCoseg, MSRC and Coseg-Rep dataset, the proposed approach performs comparable or better than the state-of-thearts, while on a more challenging benchmark Fashionista dataset, our method achieves significant improvements.

cs.CV↗

arXiv2018

Salient Object Detection: A Benchmark

We extensively compare, qualitatively and quantitatively, 40 state-of-the-art models (28 salient object detection, 10 fixation prediction, 1 objectness, and 1 baseline) over 6 challenging datasets for the purpose of benchmarking salient object detection and segmentation methods. From the results obtained so far, our evaluation shows a consistent rapid progress over the last few years in terms of both accuracy and running time. The top contenders in this benchmark significantly outperform the models identified as the best in the previous benchmark conducted just two years ago. We find that the models designed specifically for salient object detection generally work better than models in closely related areas, which in turn provides a precise definition and suggests an appropriate treatment of this problem that distinguishes it from other problems. In particular, we analyze the influences of center bias and scene complexity in model performance, which, along with the hard cases for state-of-the-art models, provide useful hints towards constructing more challenging large scale datasets and better saliency models. Finally, we propose probable solutions for tackling several open problems such as evaluation scores and dataset bias, which also suggest future research directions in the rapidly-growing field of salient object detection.

cs.CV↗