# LeNo: Adversarial Robust Salient Object Detection Networks with Learnable Noise

arXiv: https://arxiv.org/abs/2210.15392 · HTML: https://mlsanity.com/paper/2210.15392/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 54 references that are in the map.
- First posted on arXiv 27 Oct 2022.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Images](https://mlsanity.com/paper/1412.1897/) (2014)
- [Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks](https://mlsanity.com/paper/1704.01155/) (2017)
- [PraNet: Parallel Reverse Attention Network for Polyp Segmentation](https://mlsanity.com/paper/2006.11392/) (2020)
- [Mitigating Adversarial Effects Through Randomization](https://mlsanity.com/paper/1711.01991/) (2017)
- [Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models](https://mlsanity.com/paper/1805.06605/) (2018)
- [Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser](https://mlsanity.com/paper/1712.02976/) (2017)
- [Toward Convolutional Blind Denoising of Real Photographs](https://mlsanity.com/paper/1807.04686/) (2018)
- [MagNet: a Two-Pronged Defense against Adversarial Examples](https://mlsanity.com/paper/1705.09064/) (2017)
- [EGNet:Edge Guidance Network for Salient Object Detection](https://mlsanity.com/paper/1908.08297/) (2019)
- [Conditional Random Fields as Recurrent Neural Networks](https://mlsanity.com/paper/1502.03240/) (2015)
- [The Secrets of Salient Object Segmentation](https://mlsanity.com/paper/1406.2807/) (2014)
- [Spatially Transformed Adversarial Examples](https://mlsanity.com/paper/1801.02612/) (2018)
- [Visual Saliency Based on Multiscale Deep Features](https://mlsanity.com/paper/1503.08663/) (2015)
- [Generating Natural Adversarial Examples](https://mlsanity.com/paper/1710.11342/) (2017)
- [Stochastic Activation Pruning for Robust Adversarial Defense](https://mlsanity.com/paper/1803.01442/) (2018)
- [Towards Robust Neural Networks via Random Self-ensemble](https://mlsanity.com/paper/1712.00673/) (2017)
- [Generative Adversarial Perturbations](https://mlsanity.com/paper/1712.02328/) (2017)
- [Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks](https://mlsanity.com/paper/1907.06781/) (2019)
- [Suppress and Balance: A Simple Gated Network for Salient Object Detection](https://mlsanity.com/paper/2007.08074/) (2020)
- [EDN: Salient Object Detection via Extremely-Downsampled Network](https://mlsanity.com/paper/2012.13093/) (2020)
- [JCS: An Explainable COVID-19 Diagnosis System by Joint Classification and Segmentation](https://mlsanity.com/paper/2004.07054/) (2020)
- [Accurate RGB-D Salient Object Detection via Collaborative Learning](https://mlsanity.com/paper/2007.11782/) (2020)
- [Learn2Perturb: an End-to-end Feature Perturbation Learning to Improve Adversarial Robustness](https://mlsanity.com/paper/2003.01090/) (2020)
- [MobileSal: Extremely Efficient RGB-D Salient Object Detection](https://mlsanity.com/paper/2012.13095/) (2020)
- [Person Re-identification by Saliency Learning](https://mlsanity.com/paper/1412.1908/) (2014)

## Built on by (most cited first, 4 of 4)

- [Salient Object Detection From Arbitrary Modalities](https://mlsanity.com/paper/2405.03352/) (2024)
- [Deep Fourier-embedded Network for RGB and Thermal Salient Object Detection](https://mlsanity.com/paper/2411.18409/) (2024)
- [Adversarial Attacks Assessment of Salient Object Detection via Symbolic Learning](https://mlsanity.com/paper/2309.05900/) (2023)
- [LFX: Towards Unified Light Field Dense Semantic Segmentation and Salient Object Detection](https://mlsanity.com/paper/2503.00747/) (2025)

## Abstract (arXiv)

Pixel-wise prediction with deep neural network has become an effective paradigm for salient object detection (SOD) and achieved remarkable performance. However, very few SOD models are robust against adversarial attacks which are visually imperceptible for human visual attention. The previous work robust saliency (ROSA) shuffles the pre-segmented superpixels and then refines the coarse saliency map by the densely connected conditional random field (CRF). Different from ROSA that relies on various pre- and post-processings, this paper proposes a light-weight Learnable Noise (LeNo) to defend adversarial attacks for SOD models. LeNo preserves accuracy of SOD models on both adversarial and clean images, as well as inference speed. In general, LeNo consists of a simple shallow noise and noise estimation that embedded in the encoder and decoder of arbitrary SOD networks respectively. Inspired by the center prior of human visual attention mechanism, we initialize the shallow noise with a cross-shaped gaussian distribution for better defense against adversarial attacks. Instead of adding additional network components for post-processing, the proposed noise estimation modifies only one channel of the decoder. With the deeply-supervised noise-decoupled training on state-of-the-art RGB and RGB-D SOD networks, LeNo outperforms previous works not only on adversarial images but also on clean images, which contributes stronger robustness for SOD. Our code is available at https://github.com/ssecv/LeNo.