Andrea Vedaldi

Understanding deep image representations by inverting them

Image representations, from SIFT and Bag of Visual Words to Convolutional Neural Networks (CNNs), are a crucial component of almost any image understanding system. Nevertheless,...

Class segmentation and object localization with superpixel neighborhoods

We propose a method to identify and localize object classes in images. Instead of operating at the pixel level, we advocate the use of superpixels as the basic unit of a class s...

Quick Shift and Kernel Methods for Mode Seeking

Speeding up Convolutional Neural Networks with Low Rank Expansions

The focus of this paper is speeding up the application of convolutional neural networks. While delivering impressive results across a range of computer vision and machine learni...

Speeding up Convolutional Neural Networks with Low Rank Expansions

The focus of this paper is speeding up the evaluation of convolutional neural networks. While delivering impressive results across a range of computer vision and machine learnin...