SalFBNet: Learning Pseudo-Saliency Distribution via Feedback Convolutional Networks

TL;DR

SalFBNet introduces a feedback convolutional framework for saliency detection that leverages pseudo-saliency data and a novel loss to improve feature learning, achieving competitive results with fewer parameters.

Contribution

The paper proposes a feedback-recursive CNN architecture for saliency detection, creates a large pseudo-saliency dataset, and introduces a new loss function to enhance feature discrimination.

Findings

Achieves competitive performance on saliency benchmarks.

Uses fewer parameters than existing models.

Effectively learns from pseudo-ground-truth data.

Abstract

Feed-forward only convolutional neural networks (CNNs) may ignore intrinsic relationships and potential benefits of feedback connections in vision tasks such as saliency detection, despite their significant representation capabilities. In this work, we propose a feedback-recursive convolutional framework (SalFBNet) for saliency detection. The proposed feedback model can learn abundant contextual representations by bridging a recursive pathway from higher-level feature blocks to low-level layer. Moreover, we create a large-scale Pseudo-Saliency dataset to alleviate the problem of data deficiency in saliency detection. We first use the proposed feedback model to learn saliency distribution from pseudo-ground-truth. Afterwards, we fine-tune the feedback model on existing eye-fixation datasets. Furthermore, we present a novel Selective Fixation and Non-Fixation Error (sFNE) loss to make proposed feedback model better learn distinguishable eye-fixation-based features. Extensive experimental results show that our SalFBNet with fewer parameters achieves competitive results on the public saliency detection benchmarks, which demonstrate the effectiveness of proposed feedback model and Pseudo-Saliency data. Source codes and Pseudo-Saliency dataset can be found at https://github.com/gqding/SalFBNet