DeepAI AI Chat
Log In Sign Up

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

by   Carola Figueroa Flores, et al.

Most of the saliency methods are evaluated on their ability to generate saliency maps, and not on their functionality in a complete vision pipeline, like for instance, image classification. In the current paper, we propose an approach which does not require explicit saliency maps to improve image classification, but they are learned implicitely, during the training of an end-to-end image classification task. We show that our approach obtains similar results as the case when the saliency maps are provided explicitely. Combining RGB data with saliency maps represents a significant advantage for object recognition, especially for the case when training data is limited. We validate our method on several datasets for fine-grained classification tasks (Flowers, Birds and Cars). In addition, we show that our saliency estimation method, which is trained without any saliency groundtruth data, obtains competitive results on real image saliency benchmark (Toronto), and outperforms deep saliency models with synthetic images (SID4VAM).


page 3

page 7


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

This paper investigates the role of saliency to improve the classificati...

Saliency for free: Saliency prediction as a side-effect of object recognition

Saliency is the perceptual capacity of our visual system to focus our at...

Influence of Image Classification Accuracy on Saliency Map Estimation

Saliency map estimation in computer vision aims to estimate the location...

Top-Down Saliency Detection Driven by Visual Classification

This paper presents an approach for top-down saliency detection guided b...

ITSELF: Iterative Saliency Estimation fLexible Framework

Saliency object detection estimates the objects that most stand out in a...

Learning to Zoom: a Saliency-Based Sampling Layer for Neural Networks

We introduce a saliency-based distortion layer for convolutional neural ...

Interpretable Image Classification with Differentiable Prototypes Assignment

We introduce ProtoPool, an interpretable image classification model with...