We investigate the problem of learning optimal descriptors for a given classification task. Many hand-crafted descriptors have been proposed in the literature for measuring visual similarity. Looking past initial differences, what really distinguishes one descriptor from another is the tradeoff that it achieves between discriminative power and invariance. Since this trade-off must vary from task to task, no single descriptor can be optimal in all situations. Our focus, in this paper, is on learning the optimal tradeoff for classification given a particular training set and prior constraints. The problem is posed in the kernel learning framework. We learn the optimal, domain-specific kernel as a combination of base kernels corresponding to base features which achieve different levels of trade-off (such as no invariance, rotation invariance, scale invariance, affine invariance, etc.) This leads to a convex optimisation problem with a unique global optimum which can be solved for efficiently. The method is shown to achieve state-of-the-art performance on the UIUC textures, Oxford flowers and Caltech 101 datasets. 1.

Abstract not found

Many studies have uncovered evidence that visual cortex contains specialized regions involved in processing faces but not other object classes. Recent electrophysiology studies of cells in several of these specialized regions revealed that at least some of these regions are organized in a hierarchical manner with viewpointspecific cells projecting to downstream viewpoint-invariant identity-specific cells [1]. A separate computational line of reasoning leads to the claim that some transformations of visual inputs that preserve viewed object identity are class-specific. In particular, the 2D images evoked by a face undergoing a 3D rotation are not produced by the same image transformation (2D) that would produce the images evoked by an object of another class undergoing the same 3D rotation. However, within the class of faces, knowledge of the image transformation evoked by 3D rotation can be reliably transferred from previously viewed faces to help identify a novel face at a new viewpoint. We show, through computational simulations, that an architecture which applies this method of gaining invariance to class-specific transformations is effective when restricted to faces and fails spectacularly when applied to other object classes. We argue here that in order to accomplish viewpoint-invariant face identification from a single example view, visual cortex must separate the circuitry involved in discounting 3D rotations of faces from the generic circuitry involved in processing other objects. The resulting model of the ventral stream of visual cortex is consistent with the recent physiology results showing the hierarchical organization of the face processing network. 1

Many places around the world are exposed to tropical cyclones and associated storm surges. In spite of massive efforts, a great number of people die each year as a result of cyclone attacks. To mitigate the damages caused by cyclones, improved cyclone forecasting techniques must be developed. The technique presented here uses artificial neural networks to interpret NOAA-AVHRR satellite images. A multi-layered neural network, resembling the human visual system, was trained to forecast the movement direction of cyclones based on satellite images. The trained network produced correct directional forecast for 98 % of novel test images, thus showing a good generalization capability from training images to novel images. The results indicate that multilayered neural networks could be further developed into an effective tool for cyclone track forecasting using various types of remote sensing data. Future work includes extension of the present network to handle a wide range of cyclones and to take into account supplementary information, such as wind speeds around the cyclone, water temperature, air moisture, and air pressure.

Invariance to various transformations is key to object recognition but existing definitions of invariance are somewhat confusing while discussions of invariance are often confused. In this report, we provide an operational definition of invariance by formally defining perceptual tasks as classification problems. The definition should be appropriate for physiology, psychophysics and computational modeling. For any specific object, invariance can be trivially “learned ” by memorizing a sufficient number of example images of the transformed object. While our formal definition of invariance also covers such cases, this report focuses instead on invariance from very few images and mostly on invariances from one example. Image-plane invariances – such as translation, rotation and scaling – can be computed from a single image for any object. They are called generic since in principle they can be hardwired or learned (during development) for any object. In this perspective, we characterize the invariance range of a class of feedforward architectures for visual recognition that mimic the hierarchical organization of the ventral stream.