Deep Attributes from Context-Aware Regional Neural Codes

09/08/2015
by   Jianwei Luo, et al.
0

Recently, many researches employ middle-layer output of convolutional neural network models (CNN) as features for different visual recognition tasks. Although promising results have been achieved in some empirical studies, such type of representations still suffer from the well-known issue of semantic gap. This paper proposes so-called deep attribute framework to alleviate this issue from three aspects. First, we introduce object region proposals as intermedia to represent target images, and extract features from region proposals. Second, we study aggregating features from different CNN layers for all region proposals. The aggregation yields a holistic yet compact representation of input images. Results show that cross-region max-pooling of soft-max layer output outperform all other layers. As soft-max layer directly corresponds to semantic concepts, this representation is named "deep attributes". Third, we observe that only a small portion of generated regions by object proposals algorithm are correlated to classification target. Therefore, we introduce context-aware region refining algorithm to pick out contextual regions and build context-aware classifiers. We apply the proposed deep attributes framework for various vision tasks. Extensive experiments are conducted on standard benchmarks for three visual recognition tasks, i.e., image classification, fine-grained recognition and visual instance retrieval. Results show that deep attribute approaches achieve state-of-the-art results, and outperforms existing peer methods with a significant margin, even though some benchmarks have little overlap of concepts with the pre-trained CNN models.

READ FULL TEXT

page 4

page 9

research
06/15/2019

Visual Context-aware Convolution Filters for Transformation-invariant Neural Network

We propose a novel visual context-aware filter generation module which i...
research
01/17/2021

Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification

Deep convolutional neural networks (CNNs) have shown a strong ability in...
research
03/03/2017

Context Aware Query Image Representation for Particular Object Retrieval

The current models of image representation based on Convolutional Neural...
research
05/14/2018

Deep Attentional Structured Representation Learning for Visual Recognition

Structured representations, such as Bags of Words, VLAD and Fisher Vecto...
research
09/14/2016

ContextLocNet: Context-Aware Deep Network Models for Weakly Supervised Localization

We aim to localize objects in images using image-level supervision only....
research
12/19/2018

CNN based Multi-Instance Multi-Task Learning for Syndrome Differentiation of Diabetic Patients

Syndrome differentiation in Traditional Chinese Medicine (TCM) is the pr...
research
11/13/2012

Deep Attribute Networks

Obtaining compact and discriminative features is one of the major challe...

Please sign up or login with your details

Forgot password? Click here to reset