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

arXiv: https://arxiv.org/abs/2007.12211 · HTML: https://mlsanity.com/paper/2007.12211/

## Key facts

- Cited by 29 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jul 2020.

## Built on by (most cited first, 29 of 29)

- [Salient Object Detection via Integrity Learning](https://mlsanity.com/paper/2101.07663/) (2021)
- [Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction](https://mlsanity.com/paper/2112.13528/) (2021)
- [Disentangled High Quality Salient Object Detection](https://mlsanity.com/paper/2108.03551/) (2021)
- [Texture-guided Saliency Distilling for Unsupervised Salient Object Detection](https://mlsanity.com/paper/2207.05921/) (2022)
- [Salient Objects in Clutter](https://mlsanity.com/paper/2105.03053/) (2021)
- [Generative Transformer for Accurate and Reliable Salient Object Detection](https://mlsanity.com/paper/2104.10127/) (2021)
- [Unsupervised Domain Adaptive Salient Object Detection Through Uncertainty-Aware Pseudo-Label Learning](https://mlsanity.com/paper/2202.13170/) (2022)
- [Learning from Pixel-Level Label Noise: A New Perspective for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.14242/) (2021)
- [Synthetic Data Supervised Salient Object Detection](https://mlsanity.com/paper/2210.13835/) (2022)
- [Learning to Detect Instance-level Salient Objects Using Complementary Image Labels](https://mlsanity.com/paper/2111.10137/) (2021)
- [Weakly-supervised Contrastive Learning for Unsupervised Object Discovery](https://mlsanity.com/paper/2307.03376/) (2023)
- [Mutual Information Regularization for Weakly-supervised RGB-D Salient Object Detection](https://mlsanity.com/paper/2306.03630/) (2023)
- [Energy-Based Generative Cooperative Saliency Prediction](https://mlsanity.com/paper/2106.13389/) (2021)
- [A Tale of Two Latent Flows: Learning Latent Space Normalizing Flow with Short-run Langevin Flow for Approximate Inference](https://mlsanity.com/paper/2301.09300/) (2023)
- [3SD: Self-Supervised Saliency Detection With No Labels](https://mlsanity.com/paper/2203.04478/) (2022)
- [Learning from Pixel-Level Noisy Label : A New Perspective for Light Field Saliency Detection](https://mlsanity.com/paper/2204.13456/) (2022)
- [Unified Unsupervised Salient Object Detection via Knowledge Transfer](https://mlsanity.com/paper/2404.14759/) (2024)
- [An Energy-Based Prior for Generative Saliency](https://mlsanity.com/paper/2204.08803/) (2022)
- [Model Calibration in Dense Classification with Adaptive Label Perturbation](https://mlsanity.com/paper/2307.13539/) (2023)
- [Langevin Autoencoders for Learning Deep Latent Variable Models](https://mlsanity.com/paper/2209.07036/) (2022)
- [Pixel is All You Need: Adversarial Trajectory-Ensemble Active Learning for Salient Object Detection](https://mlsanity.com/paper/2212.06493/) (2022)
- [Likelihood-Based Generative Radiance Field with Latent Space Energy-Based Model for 3D-Aware Disentangled Image Representation](https://mlsanity.com/paper/2304.07918/) (2023)
- [Towards End-to-End Unsupervised Saliency Detection with Self-Supervised Top-Down Context](https://mlsanity.com/paper/2310.09533/) (2023)
- [Salient Object Detection via Bounding-box Supervision](https://mlsanity.com/paper/2205.05245/) (2022)
- [A Visual Representation-guided Framework with Global Affinity for Weakly Supervised Salient Object Detection](https://mlsanity.com/paper/2302.10697/) (2023)
- [Noise-Aware Video Saliency Prediction](https://mlsanity.com/paper/2104.08038/) (2021)
- [STANLEY: Stochastic Gradient Anisotropic Langevin Dynamics for Learning Energy-Based Models](https://mlsanity.com/paper/2310.12667/) (2023)
- [Split-Fuse-Transport: Annotation-Free Saliency via Dual Clustering and Optimal Transport Alignment](https://mlsanity.com/paper/2510.17484/) (2025)
- [Can Frozen Hyperspherical Features Guide the Selection of Pseudo Masks?](https://mlsanity.com/paper/2609.30080/) (2026)

## Abstract (arXiv)

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.