DeepRare: Generic Unsupervised Visual Attention Models
This addresses the challenge of generic unsupervised visual attention for applications in image analysis, though it is incremental as an evolution of a previous version.
The paper tackles the problem of DNN-based visual attention models being inefficient at detecting surprising or unusual data in images, proposing DeepRare2021 (DR21) which combines DNN feature extraction with feature-engineered algorithms, resulting in a model that is always within the top models on four diverse eye-tracking datasets without needing training.
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, DNN-based 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 new visual attention model called DeepRare2021 (DR21) which uses the power of DNNs feature extraction and the genericity of feature-engineered algorithms. This algorithm is an evolution of a previous version called DeepRare2019 (DR19) based on a common framework. DR21 1) does not need any training and uses the default ImageNet training, 2) is fast even on CPU, 3) is tested on four very different eye-tracking datasets showing that the DR21 is generic and is always in the within the top models on all datasets and metrics while no other model exhibits such a regularity and genericity. Finally DR21 4) is tested with several network architectures such as VGG16 (V16), VGG19 (V19) and MobileNetV2 (MN2) and 5) it provides explanation and transparency on which parts of the image are the most surprising at different levels despite the use of a DNN-based feature extractor. DeepRare2021 code can be found at https://github.com/numediart/VisualAttention-RareFamil}.