Multiple instance learning: A survey of problem characteristics and applications

We propose a method for the weakly supervised detection of objects in paintings. At training time, only image-level annotations are needed. This, combined with the efficiency of our multiple-instance learning method, enables one to learn new classes on-the-fly from globally annotated databases, avoiding the tedious task of manually marking objects. We show on several databases that dropping the instance-level annotations only yields mild performance losses. We also introduce a new database, IconArt, on which we perform detection experiments on classes that could not be learned on photographs, such as Jesus Child or Saint Sebastian. To the best of our knowledge, these are the first experiments dealing with the automatic (and in our case weakly supervised) detection of iconographic elements in paintings. We believe that such a method is of great benefit for helping art historians to explore large digital databases.

show abstract

“…Several approximations of the involved non-convex problem have been proposed, see e.g. [22] or the recent survey [7].…”

Section: Related Workmentioning

confidence: 99%

Weakly Supervised Object Detection in Artworks

Gonthier

Gousseau

Ladjal

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Often σ is taken to be of sigmoidal shape, like the logistic function in Equation (13) used in logistic regression. This function squeezes the real line onto the interval [0, 1], resembling a 12 Together with the underlying theory, SVMs caused all the furore in the late 1990s and early 2000s. To many, the development of the SVM may still be one of the prime achievements of the mathematical field of statistical learning theory that started with Vapnik and Chervonenkis in the early 1970s.…”

Section: Neural Networkmentioning

confidence: 89%

Supervised Classification: Quite a Brief Overview

Loog

2018

Machine Learning Techniques for Space Weather

View full text Add to dashboard Cite

The original problem of supervised classification considers the task of automatically assigning objects to their respective classes on the basis of numerical measurements derived from these objects. Classifiers are the tools that implement the actual functional mapping from these measurements-also called features or inputs-to the so-called class label-or output. The fields of pattern recognition and machine learning study ways of constructing such classifiers. The main idea behind supervised methods is that of learning from examples: given a number of example input-output relations, to what extent can the general mapping be learned that takes any new and unseen feature vector to its correct class? This chapter provides a basic introduction to the underlying ideas of how to come to a supervised classification problem. In addition, it provides an overview of some specific classification techniques, delves into the issues of object representation and classifier evaluation, and (very) briefly covers some variations on the basic supervised classification task that may also be of interest to the practitioner.

show abstract

“…Multiple instance learning (MIL) [7,33] methods have been used for learning weakly supervised tasks such as object localization (WSOL) [25,8,53,41]. In a standard MIL framework, instance labels in each positive bag are treated as hidden variables with the constraint that at least one of them should be positive.…”

Section: Related Workmentioning

confidence: 99%

Learning to Find Common Objects Across Few Image Collections

Shaban

Rahimi

Bansal

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Given a collection of bags where each bag is a set of images, our goal is to select one image from each bag such that the selected images are from the same object class. We model the selection as an energy minimization problem with unary and pairwise potential functions. Inspired by recent few-shot learning algorithms, we propose an approach to learn the potential functions directly from the data. Furthermore, we propose a fast greedy inference algorithm for energy minimization. We evaluate our approach on few-shot common object recognition as well as object co-localization tasks. Our experiments show that learning the pairwise and unary terms greatly improves the performance of the model over several well-known methods for these tasks. The proposed greedy optimization algorithm achieves performance comparable to state-of-the-art structured inference algorithms while being ∼10 times faster.

show abstract

Multiple instance learning: A survey of problem characteristics and applications

Cited by 542 publications

References 146 publications

Weakly Supervised Object Detection in Artworks

Weakly Supervised Object Detection in Artworks

Supervised Classification: Quite a Brief Overview

Learning to Find Common Objects Across Few Image Collections

Contact Info

Product

Resources

About