PyTorchKR Papers

최신 논문

총 55편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:1605.04996

SemiContour: A Semi-supervised Learning Approach for Contour Detection

Supervised contour detection methods usually require many labeled training images to obtain satisfactory performance. However, a large set of annotated data might be unavailable or extremely labor intensive. In this paper, we investigate the usage of semi-supervised learning (SSL) to obtain competitive detection accuracy with very limited training data (three labeled images). Specifically, we propose a semi-supervised structured ensemble learning approach for contour detection built on structured random forests (SRF). To allow SRF to be applicable to unlabeled data, we present an effective sparse representation approach to capture inherent structure in image patches by finding a compact and discriminative low-dimensional subspace representation in an unsupervised manner, enabling the incorporation of abundant unlabeled patches with their estimated structured labels to help SRF perform better node splitting. We re-examine the role of sparsity and propose a novel and fast sparse coding algorithm to boost the overall learning efficiency. To the best of our knowledge, this is the first attempt to apply SSL for contour detection. Extensive experiments on the BSDS500 segmentation dataset and the NYU Depth dataset demonstrate the superiority of the proposed method.

arXiv:1608.02755

Convolutional Oriented Boundaries

We present Convolutional Oriented Boundaries (COB), which produces multiscale oriented contours and region hierarchies starting from generic image classification Convolutional Neural Networks (CNNs). COB is computationally efficient, because it requires a single CNN forward pass for contour detection and it uses a novel sparse boundary representation for hierarchical segmentation; it gives a significant leap in performance over the state-of-the-art, and it generalizes very well to unseen categories and datasets. Particularly, we show that learning to estimate not only contour strength but also orientation provides more accurate results. We perform extensive experiments on BSDS, PASCAL Context, PASCAL Segmentation, and MS-COCO, showing that COB provides state-of-the-art contours, region hierarchies, and object proposals in all datasets.

arXiv:1701.04658

Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks

We present Convolutional Oriented Boundaries (COB), which produces multiscale oriented contours and region hierarchies starting from generic image classification Convolutional Neural Networks (CNNs). COB is computationally efficient, because it requires a single CNN forward pass for multi-scale contour detection and it uses a novel sparse boundary representation for hierarchical segmentation; it gives a significant leap in performance over the state-of-the-art, and it generalizes very well to unseen categories and datasets. Particularly, we show that learning to estimate not only contour strength but also orientation provides more accurate results. We perform extensive experiments for low-level applications on BSDS, PASCAL Context, PASCAL Segmentation, and NYUD to evaluate boundary detection performance, showing that COB provides state-of-the-art contours and region hierarchies in all datasets. We also evaluate COB on high-level tasks when coupled with multiple pipelines for object proposals, semantic contours, semantic segmentation, and object detection on MS-COCO, SBD, and PASCAL; showing that COB also improves the results for all tasks.

arXiv:1705.03159

Contour Detection from Deep Patch-level Boundary Prediction

In this paper, we present a novel approach for contour detection with Convolutional Neural Networks. A multi-scale CNN learning framework is designed to automatically learn the most relevant features for contour patch detection. Our method uses patch-level measurements to create contour maps with overlapping patches. We show the proposed CNN is able to to detect large-scale contours in an image efficienly. We further propose a guided filtering method to refine the contour maps produced from large-scale contours. Experimental results on the major contour benchmark databases demonstrate the effectiveness of the proposed technique. We show our method can achieve good detection of both fine-scale and large-scale contours.

arXiv:1705.04456

Learning to Refine Object Contours with a Top-Down Fully Convolutional Encoder-Decoder Network

We develop a novel deep contour detection algorithm with a top-down fully convolutional encoder-decoder network. Our proposed method, named TD-CEDN, solves two important issues in this low-level vision problem: (1) learning multi-scale and multi-level features; and (2) applying an effective top-down refined approach in the networks. TD-CEDN performs the pixel-wise prediction by means of leveraging features at all layers of the net. Unlike skip connections and previous encoder-decoder methods, we first learn a coarse feature map after the encoder stage in a feedforward pass, and then refine this feature map in a top-down strategy during the decoder stage utilizing features at successively lower layers. Therefore, the deconvolutional process is conducted stepwise, which is guided by Deeply-Supervision Net providing the integrated direct supervision. The above proposed technologies lead to a more precise and clearer prediction. Our proposed algorithm achieved the state-of-the-art on the BSDS500 dataset (ODS F-score of 0.788), the PASCAL VOC2012 dataset (ODS F-score of 0.588), and and the NYU Depth dataset (ODS F-score of 0.735).

arXiv:1608.04267

Detecting Dominant Vanishing Points in Natural Scenes with Application to Composition-Sensitive Image Retrieval

Linear perspective is widely used in landscape photography to create the impression of depth on a 2D photo. Automated understanding of linear perspective in landscape photography has several real-world applications, including aesthetics assessment, image retrieval, and on-site feedback for photo composition, yet adequate automated understanding has been elusive. We address this problem by detecting the dominant vanishing point and the associated line structures in a photo. However, natural landscape scenes pose great technical challenges because often the inadequate number of strong edges converging to the dominant vanishing point is inadequate. To overcome this difficulty, we propose a novel vanishing point detection method that exploits global structures in the scene via contour detection. We show that our method significantly outperforms state-of-the-art methods on a public ground truth landscape image dataset that we have created. Based on the detection results, we further demonstrate how our approach to linear perspective understanding provides on-site guidance to amateur photographers on their work through a novel viewpoint-specific image retrieval system.

arXiv:1707.03710

Contour and Centreline Tracking of Vessels from Angiograms using the Classical Image Processing Techniques

This article deals with the problem of vessel edge and centerline detection using classical image processing techniques due to their simpleness and easiness to be implemented. The method is divided into four steps: the vessel enhancement which implies a non-linear filtering proposed by Frangi, the thresholding using Otsu method and the contour detection using the Canny edge detector due to its good performances for the small vessels and the morphological skeletonisation. The algorithms are tested on real data collected from a cardiac catheterism laboratory and it is accurate for images with good spatial resolution (512*512). The output image can be used for further processing in order to find the vessel length or its radius.

arXiv:1706.00598

Dynamic Steerable Blocks in Deep Residual Networks

Filters in convolutional networks are typically parameterized in a pixel basis, that does not take prior knowledge about the visual world into account. We investigate the generalized notion of frames designed with image properties in mind, as alternatives to this parametrization. We show that frame-based ResNets and Densenets can improve performance on Cifar-10+ consistently, while having additional pleasant properties like steerability. By exploiting these transformation properties explicitly, we arrive at dynamic steerable blocks. They are an extension of residual blocks, that are able to seamlessly transform filters under pre-defined transformations, conditioned on the input at training and inference time. Dynamic steerable blocks learn the degree of invariance from data and locally adapt filters, allowing them to apply a different geometrical variant of the same filter to each location of the feature map. When evaluated on the Berkeley Segmentation contour detection dataset, our approach outperforms all competing approaches that do not utilize pre-training. Our results highlight the benefits of image-based regularization to deep networks.

arXiv:1708.07281

Recent Advances in the Applications of Convolutional Neural Networks to Medical Image Contour Detection

The fast growing deep learning technologies have become the main solution of many machine learning problems for medical image analysis. Deep convolution neural networks (CNNs), as one of the most important branch of the deep learning family, have been widely investigated for various computer-aided diagnosis tasks including long-term problems and continuously emerging new problems. Image contour detection is a fundamental but challenging task that has been studied for more than four decades. Recently, we have witnessed the significantly improved performance of contour detection thanks to the development of CNNs. Beyond purusing performance in existing natural image benchmarks, contour detection plays a particularly important role in medical image analysis. Segmenting various objects from radiology images or pathology images requires accurate detection of contours. However, some problems, such as discontinuity and shape constraints, are insufficiently studied in CNNs. It is necessary to clarify the challenges to encourage further exploration. The performance of CNN based contour detection relies on the state-of-the-art CNN architectures. Careful investigation of their design principles and motivations is critical and beneficial to contour detection. In this paper, we first review recent development of medical image contour detection and point out the current confronting challenges and problems. We discuss the development of general CNNs and their applications in image contours (or edges) detection. We compare those methods in detail, clarify their strengthens and weaknesses. Then we review their recent applications in medical image analysis and point out limitations, with the goal to light some potential directions in medical image analysis. We expect the paper to cover comprehensive technical ingredients of advanced CNNs to enrich the study in the medical image domain.

arXiv:1709.01813

Towards Automated Cadastral Boundary Delineation from UAV Data

Unmanned aerial vehicles (UAV) are evolving as an alternative tool to acquire land tenure data. UAVs can capture geospatial data at high quality and resolution in a cost-effective, transparent and flexible manner, from which visible land parcel boundaries, i.e., cadastral boundaries are delineable. This delineation is to no extent automated, even though physical objects automatically retrievable through image analysis methods mark a large portion of cadastral boundaries. This study proposes (i) a workflow that automatically extracts candidate cadastral boundaries from UAV orthoimages and (ii) a tool for their semi-automatic processing to delineate final cadastral boundaries. The workflow consists of two state-of-the-art computer vision methods, namely gPb contour detection and SLIC superpixels that are transferred to remote sensing in this study. The tool combines the two methods, allows a semi-automatic final delineation and is implemented as a publicly available QGIS plugin. The approach does not yet aim to provide a comparable alternative to manual cadastral mapping procedures. However, the methodological development of the tool towards this goal is developed in this paper. A study with 13 volunteers investigates the design and implementation of the approach and gathers initial qualitative as well as quantitate results. The study revealed points for improvement, which are prioritized based on the study results and which will be addressed in future work.

arXiv:1801.00524

Learning Deep Structured Multi-Scale Features using Attention-Gated CRFs for Contour Prediction

Recent works have shown that exploiting multi-scale representations deeply learned via convolutional neural networks (CNN) is of tremendous importance for accurate contour detection. This paper presents a novel approach for predicting contours which advances the state of the art in two fundamental aspects, i.e. multi-scale feature generation and fusion. Different from previous works directly consider- ing multi-scale feature maps obtained from the inner layers of a primary CNN architecture, we introduce a hierarchical deep model which produces more rich and complementary representations. Furthermore, to refine and robustly fuse the representations learned at different scales, the novel Attention-Gated Conditional Random Fields (AG-CRFs) are proposed. The experiments ran on two publicly available datasets (BSDS500 and NYUDv2) demonstrate the effectiveness of the latent AG-CRF model and of the overall hierarchical framework.

arXiv:1803.04620

Image Segmentation and Processing for Efficient Parking Space Analysis

In this paper, we develop a method to detect vacant parking spaces in an environment with unclear segments and contours with the help of MATLAB image processing capabilities. Due to the anomalies present in the parking spaces, such as uneven illumination, distorted slot lines and overlapping of cars. The present-day conventional algorithms have difficulties processing the image for accurate results. The algorithm proposed uses a combination of image pre-processing and false contour detection techniques to improve the detection efficiency. The proposed method also eliminates the need to employ individual sensors to detect a car, instead uses real-time static images to consider a group of slots together, instead of the usual single slot method. This greatly decreases the expenses required to design an efficient parking system. We compare the performance of our algorithm to that of other techniques. These comparisons show that the proposed algorithm can detect the vacancies in the parking spots while ignoring the false data and other distortions.

arXiv:1802.03248

Piecewise Flat Embedding for Image Segmentation

We introduce a new multi-dimensional nonlinear embedding -- Piecewise Flat Embedding (PFE) -- for image segmentation. Based on the theory of sparse signal recovery, piecewise flat embedding with diverse channels attempts to recover a piecewise constant image representation with sparse region boundaries and sparse cluster value scattering. The resultant piecewise flat embedding exhibits interesting properties such as suppressing slowly varying signals, and offers an image representation with higher region identifiability which is desirable for image segmentation or high-level semantic analysis tasks. We formulate our embedding as a variant of the Laplacian Eigenmap embedding with an $L_{1,p} (0<p\leq1)$ regularization term to promote sparse solutions. First, we devise a two-stage numerical algorithm based on Bregman iterations to compute $L_{1,1}$-regularized piecewise flat embeddings. We further generalize this algorithm through iterative reweighting to solve the general $L_{1,p}$-regularized problem. To demonstrate its efficacy, we integrate PFE into two existing image segmentation frameworks, segmentation based on clustering and hierarchical segmentation based on contour detection. Experiments on four major benchmark datasets, BSDS500, MSRC, Stanford Background Dataset, and PASCAL Context, show that segmentation algorithms incorporating our embedding achieve significantly improved results.

arXiv:1612.00343

Global Minimum for a Finsler Elastica Minimal Path Approach

In this paper, we propose a novel curvature-penalized minimal path model via an orientation-lifted Finsler metric and the Euler elastica curve. The original minimal path model computes the globally minimal geodesic by solving an Eikonal partial differential equation (PDE). Essentially, this first-order model is unable to penalize curvature which is related to the path rigidity property in the classical active contour models. To solve this problem, we present an Eikonal PDE-based Finsler elastica minimal path approach to address the curvature-penalized geodesic energy minimization problem. We were successful at adding the curvature penalization to the classical geodesic energy. The basic idea of this work is to interpret the Euler elastica bending energy via a novel Finsler elastica metric that embeds a curvature penalty. This metric is non-Riemannian, anisotropic and asymmetric, and is defined over an orientation-lifted space by adding to the image domain the orientation as an extra space dimension. Based on this orientation lifting, the proposed minimal path model can benefit from both the curvature and orientation of the paths. Thanks to the fast marching method, the global minimum of the curvature-penalized geodesic energy can be computed efficiently. We introduce two anisotropic image data-driven speed functions that are computed by steerable filters. Based on these orientation-dependent speed functions, we can apply the proposed Finsler elastica minimal path model to the applications of closed contour detection, perceptual grouping and tubular structure extraction. Numerical experiments on both synthetic and real images show that these applications of the proposed model indeed obtain promising results.

arXiv:1805.08315공식 코드 · Papers with Code

Learning long-range spatial dependencies with horizontal gated-recurrent units

Progress in deep learning has spawned great successes in many engineering applications. As a prime example, convolutional neural networks, a type of feedforward neural networks, are now approaching -- and sometimes even surpassing -- human accuracy on a variety of visual recognition tasks. Here, however, we show that these neural networks and their recent extensions struggle in recognition tasks where co-dependent visual features must be detected over long spatial ranges. We introduce the horizontal gated-recurrent unit (hGRU) to learn intrinsic horizontal connections -- both within and across feature columns. We demonstrate that a single hGRU layer matches or outperforms all tested feedforward hierarchical baselines including state-of-the-art architectures which have orders of magnitude more free parameters. We further discuss the biological plausibility of the hGRU in comparison to anatomical data from the visual cortex as well as human behavioral data on a classic contour detection task.