Deep Saliency with Encoded Low level Distance Map and High Level Features

TL;DR

This paper proposes a deep learning framework that combines high level features from VGG-net with handcrafted low level distance maps, improving saliency detection performance beyond existing methods.

Contribution

It introduces a novel approach that integrates handcrafted low level features with high level deep features within a unified deep learning model for saliency detection.

Findings

Enhanced saliency detection accuracy over state-of-the-art methods

Effective encoding of low level distance maps using CNN

Complementary benefits of combining low and high level features

Abstract

Recent advances in saliency detection have utilized deep learning to obtain high level features to detect salient regions in a scene. These advances have demonstrated superior results over previous works that utilize hand-crafted low level features for saliency detection. In this paper, we demonstrate that hand-crafted features can provide complementary information to enhance performance of saliency detection that utilizes only high level features. Our method utilizes both high level and low level features for saliency detection under a unified deep learning framework. The high level features are extracted using the VGG-net, and the low level features are compared with other parts of an image to form a low level distance map. The low level distance map is then encoded using a convolutional neural network(CNN) with multiple 1X1 convolutional and ReLU layers. We concatenate the encoded low level distance map and the high level features, and connect them to a fully connected neural network classifier to evaluate the saliency of a query region. Our experiments show that our method can further improve the performance of state-of-the-art deep learning-based saliency detection methods.