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

Abstract

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. % The vast 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.

Published in Pattern Recognition journal

References in corpus (10)

• Prototypical Networks for Few-shot Learning
• Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer
• DeepSaliency: Multi-Task Deep Neural Network Model for Salient Object Detection
• Residual Attention Network for Image Classification
• Exploiting inter-image similarity and ensemble of extreme learners for fixation prediction using deep features
• Compact Bilinear Pooling
• Deep Layer Aggregation
• OpenSalicon: An Open Source Implementation of the Salicon Saliency Model
• Borrowing Treasures from the Wealthy: Deep Transfer Learning through Selective Joint Fine-tuning
• Low-rank Bilinear Pooling for Fine-Grained Classification

Cited by in corpus (7)

• Insect pest image detection and recognition based on bio-inspired methods
• CAGNet: Content-Aware Guidance for Salient Object Detection
• Contrast-weighted Dictionary Learning Based Saliency Detection for Remote Sensing Images
• Deep Fourier-embedded Network for RGB and Thermal Salient Object Detection
• Saliency for free: Saliency prediction as a side-effect of object recognition
• Deep Object Co-segmentation via Spatial-Semantic Network Modulation
• Relating Blindsight and AI: A Review