Contextual Encoder-Decoder Network for Visual Saliency Prediction
This work addresses the problem of predicting human visual attention for applications like robotics, though it appears incremental as it builds on existing CNN approaches with specific architectural modifications.
The paper tackles visual saliency prediction by proposing a contextual encoder-decoder network that captures multi-scale features and global scene information, achieving competitive results on multiple benchmarks while using a lightweight backbone suitable for resource-constrained applications.
Predicting salient regions in natural images requires the detection of objects that are present in a scene. To develop robust representations for this challenging task, high-level visual features at multiple spatial scales must be extracted and augmented with contextual information. However, existing models aimed at explaining human fixation maps do not incorporate such a mechanism explicitly. Here we propose an approach based on a convolutional neural network pre-trained on a large-scale image classification task. The architecture forms an encoder-decoder structure and includes a module with multiple convolutional layers at different dilation rates to capture multi-scale features in parallel. Moreover, we combine the resulting representations with global scene information for accurately predicting visual saliency. Our model achieves competitive and consistent results across multiple evaluation metrics on two public saliency benchmarks and we demonstrate the effectiveness of the suggested approach on five datasets and selected examples. Compared to state of the art approaches, the network is based on a lightweight image classification backbone and hence presents a suitable choice for applications with limited computational resources, such as (virtual) robotic systems, to estimate human fixations across complex natural scenes.