Bio-Inspired Representation Learning for Visual Attention Prediction

Abstract

Visual Attention Prediction (VAP) is a significant and imperative issue in the field of computer vision. Most of existing VAP methods are based on deep learning. However, they do not fully take advantage of the low-level contrast features while generating the visual attention map. In this paper, a novel VAP method is proposed to generate visual attention map via bioinspired representation learning. The bio-inspired representation learning combines both low-level contrast and high-level semantic features simultaneously, which are developed by the fact that human eye is sensitive to the patches with high contrast and objects with high semantics. The proposed method is composed of three main steps: 1) feature extraction, 2) bio-inspired representation learning and 3) visual attention map generation. Firstly, the high-level semantic feature is extracted from the refined VGG16, while the low-level contrast feature is extracted by the proposed contrast feature extraction block in a deep network. Secondly, during bio-inspired representation learning, both the extracted low-level contrast and high-level semantic features are combined by the designed densely connected block, which is proposed to concatenate various features scale by scale. Finally, the weightedfusion layer is exploited to generate the ultimate visual attention map based on the obtained representations after bio-inspired representation learning. Extensive experiments are performed to demonstrate the effectiveness of the proposed method.

Privacy-Preserving Cloud Computing: Ecosystem, Life Cycle, Layered Architecture and Future Roadmap

“…In [370], bio-inspired representation learning is said to combine low-level contrast and high-level semantic features in order to generate a visual attention map. As outlined in [371], a neural network can be used to train Bio-inspired features.…”

Turning the Hunted into the Hunter via Threat Hunting: Life Cycle, Ecosystem, Challenges and the Great Promise of AI

“…Implementing biological system processes into computing systems may have many advantages [223]. In [224] Visual attention prediction (VAP) was explained as an important challenge for computer vision. A new approach to VAP is proposed in [224] that combines low-level features and high-level semantics similar to a human eye for visual mapping.…”

“…In [224] Visual attention prediction (VAP) was explained as an important challenge for computer vision. A new approach to VAP is proposed in [224] that combines low-level features and high-level semantics similar to a human eye for visual mapping. The article [224] explains that the new VAP method performs stronger than the other current methods.…”

Semantics-Consistent Representation Learning for Remote Sensing Image-Voice Retrieval

“…The parameter θ I in the image encoding network is initialized by VGG16 network pre-trained on the ImageNet [45]. The parameters θ V in the voice encoding network, Θ I and Θ V in the semantics-consistent representation step are randomly initialized by truncated normal distribution [46]. In each training iteration, the optimizing process can be divided into five main steps.…”

“…The proposed method is optimized utilizing a RMSProp optimizer [46], in which the weight decay is set as 0.0005 and momentum is set to 0.9. The learning rate is set as 0.0004.…”