Exploiting Example Structure In Multiple Instance Learning

Exploiting Example Structure in Multiple Instance Learning

Kernels For Structured Data

This book provides a unique treatment of an important area of machine learning and answers the question of how kernel methods can be applied to structured data. Kernel methods are a class of state-of-the-art learning algorithms that exhibit excellent learning results in several application domains. Originally, kernel methods were developed with data in mind that can easily be embedded in a Euclidean vector space. Much real-world data does not have this property but is inherently structured. An example of such data, often consulted in the book, is the (2D) graph structure of molecules formed by their atoms and bonds. The book guides the reader from the basics of kernel methods to advanced algorithms and kernel design for structured data. It is thus useful for readers who seek an entry point into the field as well as experienced researchers.

Person Re-Identification with Limited Supervision

Person re-identification is the problem of associating observations of targets in different non-overlapping cameras. Most of the existing learning-based methods have resulted in improved performance on standard re-identification benchmarks, but at the cost of time-consuming and tediously labeled data. Motivated by this, learning person re-identification models with limited to no supervision has drawn a great deal of attention in recent years. In this book, we provide an overview of some of the literature in person re-identification, and then move on to focus on some specific problems in the context of person re-identification with limited supervision in multi-camera environments. We expect this to lead to interesting problems for researchers to consider in the future, beyond the conventional fully supervised setup that has been the framework for a lot of work in person re-identification. Chapter 1 starts with an overview of the problems in person re-identification and the major research directions. We provide an overview of the prior works that align most closely with the limited supervision theme of this book. Chapter 2 demonstrates how global camera network constraints in the form of consistency can be utilized for improving the accuracy of camera pair-wise person re-identification models and also selecting a minimal subset of image pairs for labeling without compromising accuracy. Chapter 3 presents two methods that hold the potential for developing highly scalable systems for video person re-identification with limited supervision. In the one-shot setting where only one tracklet per identity is labeled, the objective is to utilize this small labeled set along with a larger unlabeled set of tracklets to obtain a re-identification model. Another setting is completely unsupervised without requiring any identity labels. The temporal consistency in the videos allows us to infer about matching objects across the cameras with higher confidence, even withlimited to no supervision. Chapter 4 investigates person re-identification in dynamic camera networks. Specifically, we consider a novel problem that has received very little attention in the community but is critically important for many applications where a new camera is added to an existing group observing a set of targets. We propose two possible solutions for on-boarding new camera(s) dynamically to an existing network using transfer learning with limited additional supervision. Finally, Chapter 5 concludes the book by highlighting the major directions for future research.