Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet

Abstract

Recent results suggest that state-of-the-art saliency models perform far from optimal in predicting fixations. This lack in performance has been attributed to an inability to model the influence of high-level image features such as objects. Recent seminal advances in applying deep neural networks to tasks like object recognition suggests that they are able to capture this kind of structure. However, the enormous amount of training data necessary to train these networks makes them difficult to apply directly to saliency prediction. We present a novel way of reusing existing neural networks that have been pretrained on the task of object recognition in models of fixation prediction. Using the well-known network of Krizhevsky et al. (2012), we come up with a new saliency model that significantly outperforms all state-of-the-art models on the MIT Saliency Benchmark. We show that the structure of this network allows new insights in the psychophysics of fixation selection and potentially their neural implementation. To train our network, we build on recent work on the modeling of saliency as point processes.

References in corpus (3)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Caffe: Convolutional Architecture for Fast Feature Embedding
• Going Deeper with Convolutions

Cited by in corpus (11)

• Learning Visual Importance for Graphic Designs and Data Visualizations
• Bio-Inspired Representation Learning for Visual Attention Prediction
• A Deep Spatial Contextual Long-term Recurrent Convolutional Network for Saliency Detection
• A Dilated Inception Network for Visual Saliency Prediction
• Improving Video Compression With Deep Visual-Attention Models
• DeepFeat: A Bottom Up and Top Down Saliency Model Based on Deep Features of Convolutional Neural Nets
• SalSum: Saliency-based Video Summarization using Generative Adversarial Networks
• SalGaze: Personalizing Gaze Estimation Using Visual Saliency
• Few-Shot Abstract Visual Reasoning With Spectral Features
• Believe It or Not, We Know What You Are Looking at!
• Saliency Prediction with External Knowledge