AI summary

This paper introduces Adaptive Deconvolutional Networks, a hierarchical model learning image decompositions through alternating convolutional sparse coding and max-pooling layers, achieving state-of-the-art results on Caltech-101 and Caltech-256 datasets by capturing multi-scale image structures.

Abstract

We present a hierarchical model that learns image decompositions via alternating layers of convolutional sparse coding and max pooling. When trained on natural images, the layers of our model capture image information in a variety of forms: low-level edges, mid-level edge junctions, high-level object parts and complete objects. To build our model we rely on a novel inference scheme that ensures each layer reconstructs the input, rather than just the output of the layer directly beneath, as is common with existing hierarchical approaches. This makes it possible to learn multiple layers of representation and we show models with 4 layers, trained on images from the Caltech-101 and 256 datasets. Features extracted from these models, in combination with a standard classifier, outperform SIFT and representations from other feature learning approaches.