# Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection

Source: [Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection](<https://www.sota2.com/research/paper/68fa680d1e209131cea19e14>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:28:00.017Z

Authors: Jing Zhang, Jianwen Xie, Nick Barnes

Published: 2020-07-23T18:47:36.000Z

## Abstract

In this paper, we propose a noise-aware encoder-decoder framework to disentangle a clean saliency predictor from noisy training examples, where the noisy labels are generated by unsupervised handcrafted feature-based methods. The proposed model consists of two sub-models parameterized by neural networks: (1) a saliency predictor that maps input images to clean saliency maps, and (2) a noise generator, which is a latent variable model that produces noises from Gaussian latent vectors. The whole model that represents noisy labels is a sum of the two sub-models. The goal of training the model is to estimate the parameters of both sub-models, and simultaneously infer the corresponding latent vector of each noisy label. We propose to train the model by using an alternating back-propagation (ABP) algorithm, which alternates the following two steps: (1) learning back-propagation for estimating the parameters of two sub-models by gradient ascent, and (2) inferential back-propagation for inferring the latent vectors of training noisy examples by Langevin Dynamics. To prevent the network from converging to trivial solutions, we utilize an edge-aware smoothness loss to regularize hidden saliency maps to have similar structures as their corresponding images. Experimental results on several benchmark datasets indicate the effectiveness of the proposed model.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Saliency Detection on DUT-LF](<https://www.sota2.com/research/sota/saliency-detection-on-dut-lf.md>): Saliency Detection; DUT-LF; F-measure: 70.1.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2007.12211>)

[PDF](<https://arxiv.org/pdf/2007.12211.pdf>)