# SODAWideNet -- Salient Object Detection with an Attention augmented Wide Encoder Decoder network without ImageNet pre-training

arXiv: https://arxiv.org/abs/2311.04828 · HTML: https://mlsanity.com/paper/2311.04828/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 31 references that are in the map.
- First posted on arXiv 8 Nov 2023.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Res2Net: A New Multi-scale Backbone Architecture](https://mlsanity.com/paper/1904.01169/) (2019)
- [U2-Net: Going Deeper with Nested U-Structure for Salient Object Detection](https://mlsanity.com/paper/2005.09007/) (2020)
- [Enhanced-alignment Measure for Binary Foreground Map Evaluation](https://mlsanity.com/paper/1805.10421/) (2018)
- [The Secrets of Salient Object Segmentation](https://mlsanity.com/paper/1406.2807/) (2014)
- [Visual Saliency Based on Multiscale Deep Features](https://mlsanity.com/paper/1503.08663/) (2015)
- [Visual Saliency Transformer](https://mlsanity.com/paper/2104.12099/) (2021)
- [Salient Object Detection via Integrity Learning](https://mlsanity.com/paper/2101.07663/) (2021)
- [Learning to predict crisp boundaries](https://mlsanity.com/paper/1807.10097/) (2018)
- [Highly Efficient Salient Object Detection with 100K Parameters](https://mlsanity.com/paper/2003.05643/) (2020)
- [EDN: Salient Object Detection via Extremely-Downsampled Network](https://mlsanity.com/paper/2012.13093/) (2020)
- [Pyramid Grafting Network for One-Stage High Resolution Saliency Detection](https://mlsanity.com/paper/2204.05041/) (2022)
- [Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction](https://mlsanity.com/paper/2112.13528/) (2021)
- [TRACER: Extreme Attention Guided Salient Object Tracing Network](https://mlsanity.com/paper/2112.07380/) (2021)
- [Recursive Contour Saliency Blending Network for Accurate Salient Object Detection](https://mlsanity.com/paper/2105.13865/) (2021)
- [Progressive Self-Guided Loss for Salient Object Detection](https://mlsanity.com/paper/2101.02412/) (2021)

## Built on by (most cited first, 1 of 1)

- [SODAWideNet++: Combining Attention and Convolutions for Salient Object Detection](https://mlsanity.com/paper/2408.16645/) (2024)

## Abstract (arXiv)

Developing a new Salient Object Detection (SOD) model involves selecting an ImageNet pre-trained backbone and creating novel feature refinement modules to use backbone features. However, adding new components to a pre-trained backbone needs retraining the whole network on the ImageNet dataset, which requires significant time. Hence, we explore developing a neural network from scratch directly trained on SOD without ImageNet pre-training. Such a formulation offers full autonomy to design task-specific components. To that end, we propose SODAWideNet, an encoder-decoder-style network for Salient Object Detection. We deviate from the commonly practiced paradigm of narrow and deep convolutional models to a wide and shallow architecture, resulting in a parameter-efficient deep neural network. To achieve a shallower network, we increase the receptive field from the beginning of the network using a combination of dilated convolutions and self-attention. Therefore, we propose Multi Receptive Field Feature Aggregation Module (MRFFAM) that efficiently obtains discriminative features from farther regions at higher resolutions using dilated convolutions. Next, we propose Multi-Scale Attention (MSA), which creates a feature pyramid and efficiently computes attention across multiple resolutions to extract global features from larger feature maps. Finally, we propose two variants, SODAWideNet-S (3.03M) and SODAWideNet (9.03M), that achieve competitive performance against state-of-the-art models on five datasets.