The PASCAL Visual Object Classes Challenge

MUCKE aims to mine a large volume of images, to structure them conceptually and to use this conceptual structuring in order to improve large-scale image retrieval. The last decade witnessed important progress concerning low-level image representations. However, there are a number problems which need to be solved in order to unleash the full potential of image mining in applications. The central problem with low-level representations is the mismatch between them and the human interpretation of image content. This problem can be instantiated, for instance, by the incapability of existing descriptors to capture spatial relationships between the concepts represented or by their incapability to convey an explanation of why two images are similar in a content-based image retrieval framework. We start by assessing existing local descriptors for image classification and by proposing to use co-occurrence matrices to better capture spatial relationships in images. The main focus in MUCKE is on cleaning large scale Web image corpora and on proposing image representations which are closer to the human interpretation of images. Consequently, we introduce methods which tackle these two problems and compare results to state of the art methods. Note: some aspects of this deliverable are withheld at this time as they are pending review. Please contact the authors for a preview.

http://ieeexplore.ieee.org/iel2/4524/12820/00592460.pdf

Image Processing

Recent advancements in perception for autonomous driving are driven by deep learning. In order to achieve robust and accurate scene understanding, autonomous vehicles are usually equipped with different sensors (e.g. cameras, LiDARs, Radars), and multiple sensing modalities can be fused to exploit their complementary properties. In this context, many methods have been proposed for deep multi-modal perception problems. However, there is no general guideline for network architecture design, and questions of “what to fuse”, “when to fuse”, and “how to fuse” remain open. This review paper attempts to systematically summarize methodologies and discuss challenges for deep multi-modal object detection and semantic segmentation in autonomous driving. To this end, we first provide an overview of on-board sensors on test vehicles, open datasets, and background information for object detection and semantic segmentation in autonomous driving research. We then summarize the fusion methodologies and discuss challenges and open questions. In the appendix, we provide tables that summarize topics and methods. We also provide an interactive online platform to navigate each reference: https://boschresearch.github.io/multimodalperception/ .

Deep Multi-Modal Object Detection and Semantic Segmentation for Autonomous Driving: Datasets, Methods, and Challenges

The need for appropriate ways to measure the distance or similarity between data is ubiquitous in machine learning, pattern recognition and data mining, but handcrafting such good metrics for specific problems is generally difficult. This has led to the emergence of metric learning, which aims at automatically learning a metric from data and has attracted a lot of interest in machine learning and related fields for the past ten years. This survey paper proposes a systematic review of the metric learning literature, highlighting the pros and cons of each approach. We pay particular attention to Mahalanobis distance metric learning, a well-studied and successful framework, but additionally present a wide range of methods that have recently emerged as powerful alternatives, including nonlinear metric learning, similarity learning and local metric learning. Recent trends and extensions, such as semi-supervised metric learning, metric learning for histogram data and the derivation of generalization guarantees, are also covered. Finally, this survey addresses metric learning for structured data, in particular edit distance learning, and attempts to give an overview of the remaining challenges in metric learning for the years to come.

A Survey on Metric Learning for Feature Vectors and Structured Data

Medical image analysis

The success of deep learning has been a catalyst to solving increasingly complex machine-learning problems, which often involve multiple data modalities. We review recent advances in deep multimodal learning and highlight the state-of the art, as well as gaps and challenges in this active research field. We first classify deep multimodal learning architectures and then discuss methods to fuse learned multimodal representations in deep-learning architectures. We highlight two areas of research&#x02013;regularization strategies and methods that learn or optimize multimodal fusion structures&#x02013;as exciting areas for future work.

Deep Multimodal Learning: A Survey on Recent Advances and Trends

Automatic white matter lesion segmentation using an adaptive outlier detection method.

In recent years, the machine learning community has witnessed a tremendous growth in the development of kernel-based learning algorithms. However, the performance of this class of algorithms greatly depends on the choice of the kernel function. Kernel function implicitly represents the inner product between a pair of points of a dataset in a higher dimensional space. This inner product amounts to the similarity between points and provides a solid foundation for nonlinear analysis in kernel-based learning algorithms. The most important challenge in kernel-based learning is the selection of an appropriate kernel for a given dataset. To remedy this problem, algorithms to learn the kernel have recently been proposed. These methods formulate a learning algorithm that finds an optimal kernel for a given dataset. In this paper, we present an overview of these algorithms and provide a comparison of various approaches to find an optimal kernel. Furthermore, a list of pivotal issues that lead to efficient design of such algorithms will be presented.

/pdf/a-survey-of-the-state-of-the-art-in-learning-the-kernels-3juuylh0l5.pdf

A survey of the state of the art in learning the kernels

We present a deep learning approach to the ISIC 2017 Skin Lesion Classification Challenge using a multi-scale convolutional neural network. Our approach utilizes an Inception-v3 network pre-trained on the ImageNet dataset, which is fine-tuned for skin lesion classification using two different scales of input images.

Skin Lesion Classification Using Deep Multi-scale Convolutional Neural Networks.

In this paper, a new dynamic clustering approach based on the Harmony Search algorithm (HS) called DCHS is proposed. In this algorithm, the capability of standard HS is modified to automatically evolve the appropriate number of clusters as well as the locations of cluster centers. By incorporating the concept of variable length in each harmony memory vector, DCHS is able to encode variable numbers of candidate cluster centers at each iteration. The PBMF cluster validity index is used as an objective function to validate the clustering result obtained from each harmony memory vector. The proposed approach has been applied onto well known natural images and experimental results show that DCHS is able to find the appropriate number of clusters and locations of cluster centers. This approach has also been compared with other metaheuristic dynamic clustering techniques and has shown to be very promising.

Dhanesh Ramachandram

Papers

Deep Multimodal Learning: A Survey on Recent Advances and Trends

Automatic white matter lesion segmentation using an adaptive outlier detection method.

A survey of the state of the art in learning the kernels

Skin Lesion Classification Using Deep Multi-scale Convolutional Neural Networks.

Dynamic fuzzy clustering using Harmony Search with application to image segmentation