paper-with-me

홈 › Papers

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

2020-07-24 · Carola Figueroa-Flores, Bogdan Raducanu, David Berga, Joost Van de Weijer

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).

📄 PDF Abstract BibTeX arXiv:2007.12562

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationFine-Grained Image ClassificationGeneral Classificationimage-classificationImage ClassificationObject RecognitionSaliency Prediction

Similar Papers 제목 키워드 기반

Few-Shot Learning via Saliency-guided Hallucination of Samples

2019-04-06 · CVPR 2019 6 · Hongguang Zhang, Jing Zhang, Piotr Koniusz

Learning new concepts from a few of samples is a standard challenge in computer vision. The main directions to improve the learning ability of few-shot training models include (i) a robust similarity learning and (ii) ge…

Few-Shot LearningHallucination

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

2021-10-11 · Lin Cheng, Pengfei Fang, Yanjie Liang, Liao Zhang 외

The explanation for deep neural networks has drawn extensive attention in the deep learning community over the past few years. In this work, we study the visual saliency, a.k.a. visual explanation, to interpret convoluti…

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

2018-08-01 · Carola Figueroa Flores, Abel Gonzalez-García, Joost Van de Weijer, Bogdan Raducanu

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 …

Object Recognition

Top-Down Saliency Detection Driven by Visual Classification

2017-09-15 · Francesca Murabito, Concetto Spampinato, Simone Palazzo, Konstantin Pogorelov 외

This paper presents an approach for top-down saliency detection guided by visual classification tasks. We first learn how to compute visual saliency when a specific visual task has to be accomplished, as opposed to most …

ClassificationGeneral ClassificationSaliency Detection

SSiT: Saliency-guided Self-supervised Image Transformer for Diabetic Retinopathy Grading

2022-10-20 · Yijin Huang, Junyan Lyu, Pujin Cheng, Roger Tam 외

Self-supervised Learning (SSL) has been widely applied to learn image representations through exploiting unlabeled images. However, it has not been fully explored in the medical image analysis field. In this work, Salien…

Contrastive LearningDiabetic Retinopathy GradingMedical Image AnalysisSelf-Supervised Learning