We describe an object detection system based on mixtures of multiscale deformable part models. Our system is able to represent highly variable object classes and achieves state-of-the-art results in the PASCAL object detection challenges. While deformable part models have become quite popular, their value had not been demonstrated on difficult benchmarks such as the PASCAL datasets. Our system relies on new methods for discriminative training with partially labeled data. We combine a margin-sensitive approach for data-mining hard negative examples with a formalism we call latent SVM. A latent SVM is a reformulation of MI-SVM in terms of latent variables. A latent SVM is semi-convex and the training problem becomes convex once latent information is specified for the positive examples. This leads to an iterative training algorithm that alternates between fixing latent values for positive examples and optimizing the latent SVM objective function.

In this paper, we address the problem of learning an adaptive appearance model for object tracking. In particular, a class of tracking techniques called “tracking by detection” have been shown to give promising results at realtime speeds. These methods train a discriminative classifier in an online manner to separate the object from the background. This classifier bootstraps itself by using the current tracker state to extract positive and negative examples from the current frame. Slight inaccuracies in the tracker can therefore lead to incorrectly labeled training examples, which degrades the classifier and can cause further drift. In this paper we show that using Multiple Instance Learning (MIL) instead of traditional supervised learning avoids these problems, and can therefore lead to a more robust tracker with fewer parameter tweaks. We present a novel online MIL algorithm for object tracking that achieves superior results with real-time performance. 1.

Multiple-instance learning algorithms train classifiers from lightly supervised data, i.e. labeled collections of items, rather than labeled items. We compare the multiple-instance learners mi-SVM and MILES on the task of classifying 10second song clips. These classifiers are trained on tags at the track, album, and artist levels, or granularities, that have been derived from tags at the clip granularity, allowing us to test the effectiveness of the learners at recovering the clip labeling in the training set and predicting the clip labeling for a held-out test set. We find that mi-SVM is better than a control at the recovery task on training clips, with an average classification accuracy as high as 87 % over 43 tags; on test clips, it is comparable to the control with an average classification accuracy of up to 68%. MILES performed adequately on the recovery task, but poorly on the test clips. 1

Abstract. It is common to use domain specific terminology – attributes – to describe the visual appearance of objects. In order to scale the use of these describable visual attributes to a large number of categories, especially those not well studied by psychologists or linguists, it will be necessary to find alternative techniques for identifying attribute vocabularies and for learning to recognize attributes without hand labeled training data. We demonstrate that it is possible to accomplish both these tasks automatically by mining text and image data sampled from the Internet. The proposed approach also characterizes attributes according to their visual representation: global or local, and type: color, texture, or shape. This work focuses on discovering attributes and their visual appearance, and is as agnostic as possible about the textual description. 1

We introduce a framework for actively learning visual categories from a mixture of weakly and strongly labeled image examples. We propose to allow the categorylearner to strategically choose what annotations it receives—based on both the expected reduction in uncertainty as well as the relative costs of obtaining each annotation. We construct a multiple-instance discriminative classifier based on the initial training data. Then all remaining unlabeled and weakly labeled examples are surveyed to actively determine which annotation ought to be requested next. After each request, the current classifier is incrementally updated. Unlike previous work, our approach accounts for the fact that the optimal use of manual annotation may call for a combination of labels at multiple levels of granularity (e.g., a full segmentation on some images and a present/absent flag on others). As a result, it is possible to learn more accurate category models with a lower total expenditure of manual annotation effort. 1

Multi-instance learning and semi-supervised learning are different branches of machine learning. The former attempts to learn from a training set consists of labeled bags each containing many unlabeled instances; the latter tries to exploit abundant unlabeled instances when learning with a small number of labeled examples. In this paper, we establish a bridge between these two branches by showing that multi-instance learning can be viewed as a special case of semi-supervised learning. Based on this recognition, we propose the MissSVM algorithm which addresses multi-instance learning using a special semisupervised support vector machine. Experiments show that solving multi-instance problems from the view of semi-supervised learning is feasible, and the MissSVM algorithm is competitive with state-of-the-art multiinstance learning algorithms. 1.

Abstract. Object detection is one of the key problems in computer vision. In the last decade, discriminative learning approaches have proven effective in detecting rigid objects, achieving very low false positives rates. The field has also seen a resurgence of part-based recognition methods, with impressive results on highly articulated, diverse object categories. In this paper we propose a discriminative learning approach for detection that is inspired by part-based recognition approaches. Our method, Multiple Component Learning (mcl), automatically learns individual component classifiers and combines these into an overall classifier. Unlike previous methods, which rely on either fairly restricted part models or labeled part data, mcl learns powerful component classifiers in a weakly supervised manner, where object labels are provided but part labels are not. The basis of mcl lies in learning a set classifier; we achieve this by combining boosting with weakly supervised learning, specifically the Multiple Instance Learning framework (mil). mcl is general, and we demonstrate results on a range of data from computer audition and computer vision. In particular, mcl outperforms all existing methods on the challenging INRIA pedestrian detection dataset, and unlike methods that are not part-based, mcl is quite robust to occlusions. 1

Abstract. In object recognition in general and in face detection in particular, data alignment is necessary to achieve good classification results with certain statistical learning approaches such as Viola-Jones. Data can be aligned in one of two ways: (1) by separating the data into coherent groups and training separate classifiers for each; (2) by adjusting training samples so they lie in correspondence. If done manually, both procedures are labor intensive and can significantly add to the cost of labeling. In this paper we present a unified boosting framework for simultaneous learning and alignment. We present a novel boosting algorithm for Multiple Pose Learning (mpl), where the goal is to simultaneously split data into groups and train classifiers for each. We also review Multiple Instance Learning (mil), and in particular mil-boost, and describe how to use it to simultaneously train a classifier and bring data into correspondence. We show results on variations of LFW and MNIST, demonstrating the potential of these approaches. 1

Previous studies on multi-instance learning typically treated instances in the bags as independently and identically distributed. The instances in a bag, however, are rarely independent in real tasks, and a better performance can be expected if the instances are treated in an non-i.i.d. way that exploits relations among instances. In this paper, we propose two simple yet effective methods. In the first method, we explicitly map every bag to an undirected graph and design a graph kernel for distinguishing the positive and negative bags. In the second method, we implicitly construct graphs by deriving affinity matrices and propose an efficient graph kernel considering the clique information. The effectiveness of the proposed methods are validated by experiments. 1.

In this paper we demonstrate how deterministic annealing can be applied to different SVM formulations of the multiple-instance learning (MIL) problem. Our results show that we find better local minima compared to the heuristic methods those problems are usually solved with. However this does not always translate into a better test error suggesting an inadequacy of the objective function. Based on this finding we propose a new objective function which together with the deterministic annealing algorithm finds better local minima and achieves better performance on a set of benchmark datasets. Furthermore the results also show how the structure of MIL datasets influence the performance of MIL algorithms and we discuss how future benchmark datasets for the MIL problem should be designed. 1