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

TL;DR

This paper introduces a noise-aware encoder-decoder framework that disentangles clean saliency maps from noisy labels generated by unsupervised methods, using an alternating back-propagation algorithm for training.

Contribution

It proposes a novel noise-aware model with a unique training algorithm to improve saliency detection from noisy labels, enhancing robustness and accuracy.

Findings

Effective in disentangling clean saliency from noisy labels

Improves saliency detection accuracy on benchmark datasets

Uses alternating back-propagation for stable training

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.