“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

A stellar spectral flux library of wide spectral coverage and an example of its application are presented. The new library consists of 131 flux-calibrated spectra, encompassing all normal spectral types and luminosity classes at solar abundance, and metal-weak and metal-rich F-K dwarf and G-K giant components. Each library spectrum was formed by combining data from several sources overlapping in wavelength coverage. The SIMBAD database, measured colors, and line strengths were used to check that each input component has closely similar stellar type. The library has complete spectral coverage from 1150 to 10620 Afor all components and to 25000 Afor about half of them, mainly later types of solar abundance. Missing spectral coverage in the infrared currently consists of a smooth energy distribution formed from standard colors for the relevant types. The library is designed to permit inclusion of additional digital spectra, particularly of non-solar abundance stars in the infrared, as they become available. The library spectra are each given as Fl versus l, from 1150 to 25000 Ain steps of 5 A ˚. A program to combine the library spectra in the ratios appropriate to a selected isochrone is described and an example of a spectral component signature of a composite population of solar age and metallicity is illustrated. The library spectra and associated tables are available as text files by remote electronic access.

VizieR Online Data Catalog: A Stellar Spectral Flux Library: 1150 - 25000 A (Pickles 1998)

We introduce a novel Deep Network architecture that implements the full feature point handling pipeline, that is, detection, orientation estimation, and feature description. While previous works have successfully tackled each one of these problems individually, we show how to learn to do all three in a unified manner while preserving end-to-end differentiability. We then demonstrate that our Deep pipeline outperforms state-of-the-art methods on a number of benchmark datasets, without the need of retraining.

/pdf/lift-learned-invariant-feature-transform-7420sriqk4.pdf

LIFT: Learned Invariant Feature Transform

Deep learning has revolutionalized image-level tasks such as classification, but patch-level tasks, such as correspondence, still rely on hand-crafted features, e.g. SIFT. In this paper we use Convolutional Neural Networks (CNNs) to learn discriminant patch representations and in particular train a Siamese network with pairs of (non-)corresponding patches. We deal with the large number of potential pairs with the combination of a stochastic sampling of the training set and an aggressive mining strategy biased towards patches that are hard to classify. By using the L2 distance during both training and testing we develop 128-D descriptors whose euclidean distances reflect patch similarity, and which can be used as a drop-in replacement for any task involving SIFT. We demonstrate consistent performance gains over the state of the art, and generalize well against scaling and rotation, perspective transformation, non-rigid deformation, and illumination changes. Our descriptors are efficient to compute and amenable to modern GPUs, and are publicly available.

/pdf/discriminative-learning-of-deep-convolutional-feature-point-qbh8u316j4.pdf

Discriminative Learning of Deep Convolutional Feature Point Descriptors

The research focus of designing local patch descriptors has gradually shifted from handcrafted ones (e.g., SIFT) to learned ones. In this paper, we propose to learn high performance descriptor in Euclidean space via the Convolutional Neural Network (CNN). Our method is distinctive in four aspects: (i) We propose a progressive sampling strategy which enables the network to access billions of training samples in a few epochs. (ii) Derived from the basic concept of local patch matching problem, we empha-size the relative distance between descriptors. (iii) Extra supervision is imposed on the intermediate feature maps. (iv) Compactness of the descriptor is taken into account. The proposed network is named as L2-Net since the output descriptor can be matched in Euclidean space by L2 distance. L2-Net achieves state-of-the-art performance on the Brown datasets [16], Oxford dataset [18] and the newly proposed Hpatches dataset [11]. The good generalization ability shown by experiments indicates that L2-Net can serve as a direct substitution of the existing handcrafted descriptors. The pre-trained L2-Net is publicly available.

/pdf/l2-net-deep-learning-of-discriminative-patch-descriptor-in-4srwxvgl7s.pdf

L2-Net: Deep Learning of Discriminative Patch Descriptor in Euclidean Space

This paper presents a novel method for feature description based on intensity order. Specifically, a Local Intensity Order Pattern(LIOP) is proposed to encode the local ordinal information of each pixel and the overall ordinal information is used to divide the local patch into subregions which are used for accumulating the LIOPs respectively. Therefore, both local and overall intensity ordinal information of the local patch are captured by the proposed LIOP descriptor so as to make it a highly discriminative descriptor. It is shown that the proposed descriptor is not only invariant to monotonic intensity changes and image rotation but also robust to many other geometric and photometric transformations such as viewpoint change, image blur and JEPG compression. The proposed descriptor has been evaluated on the standard Oxford dataset and four additional image pairs with complex illumination changes. The experimental results show that the proposed descriptor obtains a significant improvement over the existing state-of-the-art descriptors.

/pdf/local-intensity-order-pattern-for-feature-description-4lqsb1tnpp.pdf

Local Intensity Order Pattern for feature description

MSLD: A robust descriptor for line matching

Traffic sign recognition plays an important role in driver assistant systems and intelligent autonomous vehicles. Its real-time performance is highly desirable in addition to its recognition performance. This paper aims to deal with real-time traffic sign recognition, i.e., localizing what type of traffic sign appears in which area of an input image at a fast processing time. To achieve this goal, we first propose an extremely fast detection module, which is 20 times faster than the existing best detection module. Our detection module is based on traffic sign proposal extraction and classification built upon a color probability model and a color HOG. Then, we harvest from a convolutional neural network to further classify the detected signs into their subclasses within each superclass. Experimental results on both German and Chinese roads show that both our detection and classification methods achieve comparable performance with the state-of-the-art methods, with significantly improved computational efficiency.

Towards Real-Time Traffic Sign Detection and Classification

This paper proposes a novel method for interest region description which pools local features based on their intensity orders in multiple support regions. Pooling by intensity orders is not only invariant to rotation and monotonic intensity changes, but also encodes ordinal information into a descriptor. Two kinds of local features are used in this paper, one based on gradients and the other on intensities; hence, two descriptors are obtained: the Multisupport Region Order-Based Gradient Histogram (MROGH) and the Multisupport Region Rotation and Intensity Monotonic Invariant Descriptor (MRRID). Thanks to the intensity order pooling scheme, the two descriptors are rotation invariant without estimating a reference orientation, which appears to be a major error source for most of the existing methods, such as Scale Invariant Feature Transform (SIFT), SURF, and DAISY. Promising experimental results on image matching and object recognition demonstrate the effectiveness of the proposed descriptors compared to state-of-the-art descriptors.

http://vision.ia.ac.cn/Students/bfan/BinFan-TPAMI2012-PrePrint.pdf

Fuchao Wu

Papers

L2-Net: Deep Learning of Discriminative Patch Descriptor in Euclidean Space

Local Intensity Order Pattern for feature description

MSLD: A robust descriptor for line matching

Towards Real-Time Traffic Sign Detection and Classification

Rotationally Invariant Descriptors Using Intensity Order Pooling