Learning from Pixel-Level Noisy Label : A New Perspective for Light Field Saliency Detection

TL;DR

This paper presents a novel framework for light field saliency detection that learns from pixel-level noisy labels by jointly optimizing feature fusion and scene correlation, effectively handling label noise and achieving state-of-the-art results.

Contribution

It introduces a unified approach combining pixel forgetting guided fusion and cross scene noise penalty to improve saliency detection from noisy labels.

Findings

Achieves saliency prediction comparable to fully supervised methods.

Effectively identifies and mitigates noisy labels during training.

Demonstrates superior performance on multiple benchmark datasets.

Abstract

Saliency detection with light field images is becoming attractive given the abundant cues available, however, this comes at the expense of large-scale pixel level annotated data which is expensive to generate. In this paper, we propose to learn light field saliency from pixel-level noisy labels obtained from unsupervised hand crafted featured based saliency methods. Given this goal, a natural question is: can we efficiently incorporate the relationships among light field cues while identifying clean labels in a unified framework? We address this question by formulating the learning as a joint optimization of intra light field features fusion stream and inter scenes correlation stream to generate the predictions. Specially, we first introduce a pixel forgetting guided fusion module to mutually enhance the light field features and exploit pixel consistency across iterations to identify noisy pixels. Next, we introduce a cross scene noise penalty loss for better reflecting latent structures of training data and enabling the learning to be invariant to noise. Extensive experiments on multiple benchmark datasets demonstrate the superiority of our framework showing that it learns saliency prediction comparable to state-of-the-art fully supervised light field saliency methods. Our code is available at https://github.com/OLobbCode/NoiseLF.