DeepAI AI Chat
Log In Sign Up

Visual Attention: Deep Rare Features

by   Mancas Matei, et al.
University of Mons
Institute of Technology of Cambodia

Human visual system is modeled in engineering field providing feature-engineered methods which detect contrasted/surprising/unusual data into images. This data is "interesting" for humans and leads to numerous applications. Deep learning (DNNs) drastically improved the algorithms efficiency on the main benchmark datasets. However, DNN-based models are counter-intuitive: surprising or unusual data is by definition difficult to learn because of its low occurrence probability. In reality, DNNs models mainly learn top-down features such as faces, text, people, or animals which usually attract human attention, but they have low efficiency in extracting surprising or unusual data in the images. In this paper, we propose a model called DeepRare2019 (DR) which uses the power of DNNs feature extraction and the genericity of feature-engineered algorithms. DR 1) does not need any training, 2) it takes less than a second per image on CPU only and 3) our tests on three very different eye-tracking datasets show that DR is generic and is always in the top-3 models on all datasets and metrics while no other model exhibits such a regularity and genericity. DeepRare2019 code can be found at


page 2

page 3


DeepRare: Generic Unsupervised Visual Attention Models

Human visual system is modeled in engineering field providing feature-en...

BiRA-Net: Bilinear Attention Net for Diabetic Retinopathy Grading

Diabetic retinopathy (DR) is a common retinal disease that leads to blin...

Semi-Supervised Semantic Segmentation Methods for UW-OCTA Diabetic Retinopathy Grade Assessment

People with diabetes are more likely to develop diabetic retinopathy (DR...

Early Detection of Diabetic Retinopathy and Severity Scale Measurement: A Progressive Review Scopes

Early detection of diabetic retinopathy prevents visual loss and blindne...

CANet: Cross-disease Attention Network for Joint Diabetic Retinopathy and Diabetic Macular Edema Grading

Diabetic retinopathy (DR) and diabetic macular edema (DME) are the leadi...

Cross-Field Transformer for Diabetic Retinopathy Grading on Two-feld Fundus Images

Automatic diabetic retinopathy (DR) grading based on fundus photography ...

Cost-Sensitive Regularization for Diabetic Retinopathy Grading from Eye Fundus Images

Assessing the degree of disease severity in biomedical images is a task ...

Code Repositories


Visual Attention : what is salient in an image with DeepRare2019

view repo


Where do people look on images in average? At rare, thus surprising things! Let's compute them automatically

view repo