Harvesting Discriminative Meta Objects with Deep CNN Features for Scene Classification

10/06/2015
by   Ruobing Wu, et al.
1

Recent work on scene classification still makes use of generic CNN features in a rudimentary manner. In this ICCV 2015 paper, we present a novel pipeline built upon deep CNN features to harvest discriminative visual objects and parts for scene classification. We first use a region proposal technique to generate a set of high-quality patches potentially containing objects, and apply a pre-trained CNN to extract generic deep features from these patches. Then we perform both unsupervised and weakly supervised learning to screen these patches and discover discriminative ones representing category-specific objects and parts. We further apply discriminative clustering enhanced with local CNN fine-tuning to aggregate similar objects and parts into groups, called meta objects. A scene image representation is constructed by pooling the feature response maps of all the learned meta objects at multiple spatial scales. We have confirmed that the scene image representation obtained using this new pipeline is capable of delivering state-of-the-art performance on two popular scene benchmark datasets, MIT Indoor 67 MITIndoor67 and Sun397 Sun397

READ FULL TEXT

page 3

page 5

research
05/14/2012

Unsupervised Discovery of Mid-Level Discriminative Patches

The goal of this paper is to discover a set of discriminative patches wh...
research
07/23/2018

From Volcano to Toyshop: Adaptive Discriminative Region Discovery for Scene Recognition

As deep learning approaches to scene recognition emerge, they have conti...
research
11/01/2019

Centroid-Based Scene Classification (CBSC): Using Deep Features and Clustering for RGB-D Indoor Scene Classification

This paper contributes a novel method for RGB-D indoor scene classificat...
research
09/01/2016

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

Traditional feature encoding scheme (e.g., Fisher vector) with local des...
research
12/09/2019

Patch Aggregator for Scene Text Script Identification

Script identification in the wild is of great importance in a multi-ling...
research
03/18/2023

Extracting Class Activation Maps from Non-Discriminative Features as well

Extracting class activation maps (CAM) from a classification model often...
research
08/18/2019

Scene Classification in Indoor Environments for Robots using Context Based Word Embeddings

Scene Classification has been addressed with numerous techniques in comp...

Please sign up or login with your details

Forgot password? Click here to reset