We seek to build a large collection of images with ground truth labels to be used for object detection and recognition research. Such data is useful for supervised learning and quantitative evaluation. To achieve this, we developed a web-based tool that allows easy image annotation and instant sharing of such annotations. Using this annotation tool, we have collected a large dataset that spans many object categories, often containing multiple instances over a wide variety of images. We quantify the contents of the dataset and compare against existing state of the art datasets used for object recognition and detection. Also, we show how to extend the dataset to automatically enhance object labels with WordNet, discover object parts, recover a depth ordering of objects in a scene, and increase the number of labels using minimal user supervision and images from the web.

We present an unsupervised method for learning a hierarchy of sparse feature detectors that are invariant to small shifts and distortions. The resulting feature extractor consists of multiple convolution filters, followed by a pointwise sigmoid non-linearity, and a feature-pooling layer that computes the max of each filter output within adjacent windows. A second level of larger and more invariant features is obtained by training the same algorithm on patches of features from the first level. Training a supervised classifier on these features yields 0.64 % error on MNIST, and 54 % average recognition rate on Caltech 101

This exploratory paper quests for a stochastic and context sensitive grammar of images. The grammar should achieve the following four objectives and thus serves as a unified framework of representation, learning, and recognition for a large number of object categories. (i) The grammar represents both the hierarchical decompositions from scenes, to objects, parts, primitives and pixels by terminal and non-terminal nodes and the contexts for spatial and functional relations by horizontal links between the nodes. It formulates each object category as the set of all possible valid configurations produced by the grammar. (ii) The grammar is embodied in a simple And–Or graph representation where each Or-node points to alternative sub-configurations and an And-node is decomposed into a number of components. This representation supports recursive top-down/bottom-up procedures for image parsing under the Bayesian framework and make it convenient to scale

We present methods for training high quality object detectors very quickly. The core contribution is a pair of fast training algorithms for piece-wise linear classifiers, which can approximate arbitrary additive models. The classifiers are trained in a max-margin framework and significantly outperform linear classifiers on a variety of vision datasets. We report experimental results quantifying training time and accuracy on image classification tasks and pedestrian detection, including detection results better than the best previous on the INRIA dataset with faster training. 1.

Abstract not found

Internet offers a vast amount of multi-modal and heterogeneous information mainly in the form of textual and visual data. Most of the current web-based visual object classification methods only utilize one of these data streams. As we will show in this paper, combining these modalities in a proper way often provides better results not attainable by relying on only one of these data streams. However, up to our knowledge, there is no publicly available dataset for benchmarking algorithms which use textual and visual data simultaneously. Therefore, in this work, we present an annotated multi-modal dataset, named TVGraz, which currently contains 10 visual object categories. The visual appearance of the objects in the dataset is challenging and offers a less biased benchmark. In order to facilitate the usage of this dataset in vision community, we additionally provide a preprocessed text data by using VIPS (VIsion-based Page Segmentation) method. We use a Multiple Kernel Learning (MKL) method to combine the textual and visual features in a proper way and show improved classification and ranking results with respect to the using only one of the data streams. 1

Recognizing the many objects that comprise our visual world is a difficult task. Confounding factors, such as intra-class object variation, clutter, pose, lighting, dealing with never-before seen objects, scale, and lack of visual experience often fool existing recognition systems. In this thesis, we explore three issues that address a few of these factors: the importance of labeled image databases for recognition, the ability to discover object categories from simply looking at many images, and the use of large labeled image databases to efficiently detect objects embedded in scenes. For each of the issues above, we will need to cope with large collections of images. We begin by introducing LabelMe, a large labeled image database collected from users via a web annotation tool. The users of the annotation tool provided information about the identity, location, and extent of objects in images. Through this effort, we have collected about 160,000 images and 200,000 object labels to date. We