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

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\%).

arXiv commentTo appear in IEEE Transactions on Image Processing. Code and model available at https://github.com/wangzheallen/vsad

References in corpus (3)

• Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors
• Learning Contextual Dependencies with Convolutional Hierarchical Recurrent Neural Networks
• Locally-Supervised Deep Hybrid Model for Scene Recognition

Cited by in corpus (8)

• HA-CCN: Hierarchical Attention-based Crowd Counting Network
• Semantic-Aware Scene Recognition
• Learning Effective RGB-D Representations for Scene Recognition
• From Volcano to Toyshop: Adaptive Discriminative Region Discovery for Scene Recognition
• Indoor image representation by high-level semantic features
• Recent Advances in Scene Image Representation and Classification
• What am I allowed to do here?: Online Learning of Context-Specific Norms by Pepper
• EnTri: Ensemble Learning with Tri-level Representations for Explainable Scene Recognition