Weakly Supervised PatchNets: Describing and Aggregating Local Patches for Scene Recognition

TL;DR

This paper introduces PatchNet, a weakly supervised patch-level model, and VSAD, a hybrid global image representation, achieving state-of-the-art scene recognition results by combining CNN features with descriptor encoding.

Contribution

It presents a novel weakly supervised patch-level network and a hybrid representation for scene recognition, improving accuracy over existing methods.

Findings

Achieved 86.2% accuracy on MIT Indoor67

Achieved 73.0% accuracy on SUN397

Outperformed previous state-of-the-art methods

Abstract

Traditional feature encoding scheme (e.g., Fisher vector) with local descriptors (e.g., SIFT) and recent convolutional neural networks (CNNs) are two classes of successful methods for image recognition. In this paper, we propose a hybrid representation, which leverages the discriminative capacity of CNNs and the simplicity of descriptor encoding schema for image recognition, with a focus on scene recognition. To this end, we make three main contributions from the following aspects. First, we propose a patch-level and end-to-end architecture to model the appearance of local patches, called {\em PatchNet}. PatchNet is essentially a customized network trained in a weakly supervised manner, which uses the image-level supervision to guide the patch-level feature extraction. Second, we present a hybrid visual representation, called {\em VSAD}, by utilizing the robust feature representations of PatchNet to describe local patches and exploiting the semantic probabilities of PatchNet to aggregate these local patches into a global representation. Third, based on the proposed VSAD representation, we propose a new state-of-the-art scene recognition approach, which achieves an excellent performance on two standard benchmarks: MIT Indoor67 (86.2\%) and SUN397 (73.0\%).