Deep Convolutional Features for Image Based Retrieval and Scene Categorization

Abstract

Several recent approaches showed how the representations learned by Convolutional Neural Networks can be repurposed for novel tasks. Most commonly it has been shown that the activation features of the last fully connected layers (fc7 or fc6) of the network, followed by a linear classifier outperform the state-of-the-art on several recognition challenge datasets. Instead of recognition, this paper focuses on the image retrieval problem and proposes a examines alternative pooling strategies derived for CNN features. The presented scheme uses the features maps from an earlier layer 5 of the CNN architecture, which has been shown to preserve coarse spatial information and is semantically meaningful. We examine several pooling strategies and demonstrate superior performance on the image retrieval task (INRIA Holidays) at the fraction of the computational cost, while using a relatively small memory requirements. In addition to retrieval, we see similar efficiency gains on the SUN397 scene categorization dataset, demonstrating wide applicability of this simple strategy. We also introduce and evaluate a novel GeoPlaces5K dataset from different geographical locations in the world for image retrieval that stresses more dramatic changes in appearance and viewpoint.

References in corpus (7)

• Caffe: Convolutional Architecture for Fast Feature Embedding
• Going Deeper with Convolutions
• Fully Convolutional Networks for Semantic Segmentation
• Object Detectors Emerge in Deep Scene CNNs
• Return of the Devil in the Details: Delving Deep into Convolutional Nets
• CNN Features off-the-shelf: an Astounding Baseline for Recognition
• Factors of Transferability for a Generic ConvNet Representation

Cited by in corpus (6)

• Good Practice in CNN Feature Transfer
• Exploiting Deep Features for Remote Sensing Image Retrieval: A Systematic Investigation
• An Out-of-the-box Full-network Embedding for Convolutional Neural Networks
• Full-Network Embedding in a Multimodal Embedding Pipeline
• MILDNet: A Lightweight Single Scaled Deep Ranking Architecture
• Building Graph Representations of Deep Vector Embeddings