This paper presents a method for recognizing scene categories based on approximate global geometric correspondence. This technique works by partitioning the image into increasingly fine sub-regions and computing histograms of local features found inside each sub-region. The resulting “spatial pyramid ” is a simple and computationally efficient extension of an orderless bag-of-features image representation, and it shows significantly improved performance on challenging scene categorization tasks. Specifically, our proposed method exceeds the state of the art on the Caltech-101 database and achieves high accuracy on a large database of fifteen natural scene categories. The spatial pyramid framework also offers insights into the success of several recently proposed image descriptions, including Torralba’s “gist ” and Lowe’s SIFT descriptors. 1.

State-of-the-art image classification methods require an intensive learning/training stage (using SVM, Boosting, etc.) In contrast, non-parametric Nearest-Neighbor (NN) based image classifiers require no training time and have other favorable properties. However, the large performance gap between these two families of approaches rendered NNbased image classifiers useless. We claim that the effectiveness of non-parametric NNbased image classification has been considerably undervalued. We argue that two practices commonly used in image classification methods, have led to the inferior performance of NN-based image classifiers: (i) Quantization of local image descriptors (used to generate “bags-of-words”, codebooks). (ii) Computation of ‘Image-to-Image ’ distance, instead of ‘Image-to-Class ’ distance. We propose a trivial NN-based classifier – NBNN, (Naive-Bayes Nearest-Neighbor), which employs NNdistances in the space of the local image descriptors (and not in the space of images). NBNN computes direct ‘Imageto-Class’ distances without descriptor quantization. We further show that under the Naive-Bayes assumption, the theoretically optimal image classifier can be accurately approximated by NBNN. Although NBNN is extremely simple, efficient, and requires no learning/training phase, its performance ranks among the top leading learning-based image classifiers. Empirical comparisons are shown on several challenging databases (Caltech-101,Caltech-256 and Graz-01). 1.

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

In many recent object recognition systems, feature extraction stages are generally composed of a filter bank, a non-linear transformation, and some sort of feature pooling layer. Most systems use only one stage of feature extraction in which the filters are hard-wired, or two stages where the filters in one or both stages are learned in supervised or unsupervised mode. This paper addresses three questions: 1. How does the non-linearities that follow the filter banks influence the recognition accuracy? 2. does learning the filter banks in an unsupervised or supervised manner improve the performance over random filters or hardwired filters? 3. Is there any advantage to using an architecture with two stages of feature extraction, rather than one? We show that using non-linearities that include rectification and local contrast normalization is the single most important ingredient for good accuracy on object recognition benchmarks. We show that two stages of feature extraction yield better accuracy than one. Most surprisingly, we show that a two-stage system with random filters can yield almost 63 % recognition rate on Caltech-101, provided that the proper non-linearities and pooling layers are used. Finally, we show that with supervised refinement, the system achieves state-of-the-art performance on NORB dataset (5.6%) and unsupervised pre-training followed by supervised refinement produces good accuracy on Caltech-101 (> 65%), and the lowest known error rate on the undistorted, unprocessed MNIST dataset (0.53%). 1.

In numerous domains it is useful to represent a single example by the set of the local features or parts that comprise it. However, this representation poses a challenge to many conventional machine learning techniques, since sets may vary in cardinality and elements lack a meaningful ordering. Kernel methods can learn complex functions, but a kernel over unordered set inputs must somehow solve for correspondences—generally a computationally expensive task that becomes impractical for large set sizes. We present a new fast kernel function called the pyramid match that measures partial match similarity in time linear in the number of features. The pyramid match maps unordered feature sets to multi-resolution histograms and computes a weighted histogram intersection in order to find implicit correspondences based on the finest resolution histogram cell where a matched pair first appears. We show the pyramid match yields a Mercer kernel, and we prove bounds on its error relative to the optimal partial matching cost. We demonstrate our algorithm on both classification and regression tasks, including object recognition, 3-D human pose inference, and time of publication estimation for documents, and we show that the proposed method is accurate and significantly more efficient than current approaches.

We introduce an exemplar model that can learn and generate a region of interest around class instances in a training set, given only a set of images containing the visual class. The model is scale and translation invariant. In the training phase, image regions that optimize an objective function are automatically located in the training images, without requiring any user annotation such as bounding boxes. The objective function measures visual similarity between training image pairs, using the spatial distribution of both appearance patches and edges. The optimization is initialized using discriminative features. The model enables the detection (localization) of multiple instances of the object class in test images, and can be used as a precursor to training other visual models that require bounding box annotation. The detection performance of the model is assessed on the PASCAL Visual Object Classes Challenge 2006 test set. For a number of object classes the performance far exceeds the current state of the art of fully supervised methods. 1.

Progress in understanding the brain mechanisms underlying vision requires the construction of computational models that not only emulate the brain’s anatomy and physiology, but ultimately match its performance on visual tasks. In recent years, ‘‘natural’ ’ images have become popular in the study of vision and have been used to show apparently impressive progress in building such models. Here, we challenge the use of uncontrolled ‘‘natural’ ’ images in guiding that progress. In particular, we show that a simple V1-like model—a neuroscientist’s ‘‘null’ ’ model, which should perform poorly at real-world visual object recognition tasks—outperforms state-of-the-art object recognition systems (biologically inspired and otherwise) on a standard, ostensibly natural image recognition test. As a counterpoint, we designed a ‘‘simpler’ ’ recognition test to better span the real-world variation in object pose, position, and scale, and we show that this test correctly exposes the inadequacy of the V1-like model. Taken together, these results demonstrate that tests based on uncontrolled natural images can be seriously misleading, potentially guiding progress in the wrong direction. Instead, we reexamine what it means for images to be natural and argue for a renewed focus on the core problem of object recognition—real-world image variation.

We introduce a method that enables scalable image search for learned metrics. Given pairwise similarity and dissimilarity constraints between some images, we learn a Mahalanobis distance function that captures the images’ underlying relationships well. To allow sub-linear time similarity search under the learned metric, we show how to encode the learned metric parameterization into randomized locality-sensitive hash functions. We further formulate an indirect solution that enables metric learning and hashing for vector spaces whose high dimensionality make it infeasible to learn an explicit weighting over the feature dimensions. We demonstrate the approach applied to a variety of image datasets. Our learned metrics improve accuracy relative to commonly-used metric baselines, while our hashing construction enables efficient indexing with learned distances and very large databases.

We demonstrate a method for identifying images containing categories of animals. The images we classify depict animals in a wide range of aspects, configurations and appearances. In addition, the images typically portray multiple species that differ in appearance (e.g. ukari’s, vervet monkeys, spider monkeys, rhesus monkeys, etc.). Our method is accurate despite this variation and relies on four simple cues: text, color, shape and texture. Visual cues are evaluated by a voting method that compares local image phenomena with a number of visual exemplars for the category. The visual exemplars are obtained using a clustering method applied to text on web pages. The only supervision required involves identifying which clusters of exemplars refer to which sense of a term (for example, “monkey” can refer to an animal or a bandmember). Because our method is applied to web pages with free text, the word cue is extremely noisy. We show unequivocal evidence that visual information improves performance for our task. Our method allows us to produce large, accurate and challenging visual datasets mostly automatically.

“Bag of words ” models have enjoyed much attention and achieved good performances in recent studies of object categorization. In most of these works, local patches are modeled as basic building blocks of an image, analogous to words in text documents. In most previous works using the “bag of words ” models (e.g. [4, 20, 7]), the local patches are assumed to be independent with each other. In this paper, we relax the independence assumption and model explicitly the inter-dependency of the local regions. Similarly to previous work, we represent images as a collection of patches, each of which belongs to a latent “theme ” that is shared across images as well as categories. We learn the theme distributions and patch distributions over the themes in a hierarchical structure [22]. In particular, we introduce a linkage structure over the latent themes to encode the dependencies of the patches. This structure enforces the semantic connections among the patches by facilitating better clustering of the themes. As a result, our models for object categories tend to be more discriminative than the ones obtained under the independent patch assumption. We show highly competitive categorization results on both the Caltech 4 and Caltech 101 object category datasets. By examining the distributions of the latent themes for each object category, we construct an object taxonomy using the 101 object classes from the Caltech 101 datasets. 1.