# DNA: Deeply-supervised Nonlinear Aggregation for Salient Object Detection

arXiv: https://arxiv.org/abs/1903.12476 · HTML: https://mlsanity.com/paper/1903.12476/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Mar 2019.

## Built on by (most cited first, 17 of 17)

- [P2T: Pyramid Pooling Transformer for Scene Understanding](https://mlsanity.com/paper/2106.12011/) (2021)
- [Every Annotation Counts: Multi-label Deep Supervision for Medical Image Segmentation](https://mlsanity.com/paper/2104.13243/) (2021)
- [Vision Transformers with Hierarchical Attention](https://mlsanity.com/paper/2106.03180/) (2021)
- [Global-and-Local Collaborative Learning for Co-Salient Object Detection](https://mlsanity.com/paper/2204.08917/) (2022)
- [Adjacent Context Coordination Network for Salient Object Detection in Optical Remote Sensing Images](https://mlsanity.com/paper/2203.13664/) (2022)
- [Salient Objects in Clutter](https://mlsanity.com/paper/2105.03053/) (2021)
- [A Comprehensive Review on Deep Supervision: Theories and Applications](https://mlsanity.com/paper/2207.02376/) (2022)
- [Boosting Salient Object Detection with Transformer-based Asymmetric Bilateral U-Net](https://mlsanity.com/paper/2108.07851/) (2021)
- [United Domain Cognition Network for Salient Object Detection in Optical Remote Sensing Images](https://mlsanity.com/paper/2411.06703/) (2024)
- [Middle-level Fusion for Lightweight RGB-D Salient Object Detection](https://mlsanity.com/paper/2104.11543/) (2021)
- [Assisted Refinement Network Based on Channel Information Interaction for Camouflaged and Salient Object Detection](https://mlsanity.com/paper/2512.11369/) (2025)
- [KD-SCFNet: Towards More Accurate and Efficient Salient Object Detection via Knowledge Distillation](https://mlsanity.com/paper/2208.02178/) (2022)
- [GAPNet: A Lightweight Framework for Image and Video Salient Object Detection via Granularity-Aware Paradigm](https://mlsanity.com/paper/2508.07585/) (2025)
- [Class-Agnostic Segmentation Loss and Its Application to Salient Object Detection and Segmentation](https://mlsanity.com/paper/2108.04226/) (2021)
- [Parameter Aware Mamba Model for Multi-task Dense Prediction](https://mlsanity.com/paper/2511.14503/) (2025)
- [A Cascaded Information Interaction Network for Precise Image Segmentation](https://mlsanity.com/paper/2601.00562/) (2026)
- [MIMONet: Multi-scale Input and Multi-scale Output Network for Salient Object Detection](https://mlsanity.com/paper/2608.25733/) (2026)

## Abstract (arXiv)

Recent progress on salient object detection mainly aims at exploiting how to effectively integrate multi-scale convolutional features in convolutional neural networks (CNNs). Many popular methods impose deep supervision to perform side-output predictions that are linearly aggregated for final saliency prediction. In this paper, we theoretically and experimentally demonstrate that linear aggregation of side-output predictions is suboptimal, and it only makes limited use of the side-output information obtained by deep supervision. To solve this problem, we propose Deeply-supervised Nonlinear Aggregation (DNA) for better leveraging the complementary information of various side-outputs. Compared with existing methods, it i) aggregates side-output features rather than predictions, and ii) adopts nonlinear instead of linear transformations. Experiments demonstrate that DNA can successfully break through the bottleneck of current linear approaches. Specifically, the proposed saliency detector, a modified U-Net architecture with DNA, performs favorably against state-of-the-art methods on various datasets and evaluation metrics without bells and whistles.