Saliency for Fine-grained Object Recognition in Domains with Scarce Training Data

by   Carola Figueroa Flores, et al.

This paper investigates the role of saliency to improve the classification accuracy of a Convolutional Neural Network (CNN) for the case when scarce training data is available. Our approach consists in adding a saliency branch to an existing CNN architecture which is used to modulate the standard bottom-up visual features from the original image input, acting as an attentional mechanism that guides the feature extraction process. The main aim of the proposed approach is to enable the effective training of a fine-grained recognition model with limited training samples and to improve the performance on the task, thereby alleviating the need to annotate large dataset. majority of saliency methods are evaluated on their ability to generate saliency maps, and not on their functionality in a complete vision pipeline. Our proposed pipeline allows to evaluate saliency methods for the high-level task of object recognition. We perform extensive experiments on various fine-grained datasets (Flowers, Birds, Cars, and Dogs) under different conditions and show that saliency can considerably improve the network's performance, especially for the case of scarce training data. Furthermore, our experiments show that saliency methods that obtain improved saliency maps (as measured by traditional saliency benchmarks) also translate to saliency methods that yield improved performance gains when applied in an object recognition pipeline.


page 14

page 19

page 20


Hallucinating Saliency Maps for Fine-Grained Image Classification for Limited Data Domains

Most of the saliency methods are evaluated on their ability to generate ...

DISC: Deep Image Saliency Computing via Progressive Representation Learning

Salient object detection increasingly receives attention as an important...

Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet

Recent results suggest that state-of-the-art saliency models perform far...

Boosting Object Recognition in Point Clouds by Saliency Detection

Object recognition in 3D point clouds is a challenging task, mainly when...

Unsupervised Foveal Vision Neural Networks with Top-Down Attention

Deep learning architectures are an extremely powerful tool for recognizi...

TSG: Target-Selective Gradient Backprop for Probing CNN Visual Saliency

The explanation for deep neural networks has drawn extensive attention i...

DeepGaze II: Reading fixations from deep features trained on object recognition

Here we present DeepGaze II, a model that predicts where people look in ...

Please sign up or login with your details

Forgot password? Click here to reset