# CLASS: Cross-Level Attention and Supervision for Salient Objects Detection

arXiv: https://arxiv.org/abs/2009.10916 · HTML: https://mlsanity.com/paper/2009.10916/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Sep 2020.

## Built on by (most cited first, 7 of 7)

- [Federated Learning with Label Distribution Skew via Logits Calibration](https://mlsanity.com/paper/2209.00189/) (2022)
- [CoSformer: Detecting Co-Salient Object with Transformers](https://mlsanity.com/paper/2104.14729/) (2021)
- [Highly Efficient Natural Image Matting](https://mlsanity.com/paper/2110.12748/) (2021)
- [Scene Matters: Model-based Deep Video Compression](https://mlsanity.com/paper/2303.04557/) (2023)
- [Towards Stable Co-saliency Detection and Object Co-segmentation](https://mlsanity.com/paper/2209.12138/) (2022)
- [Attention Guided Network for Salient Object Detection in Optical Remote Sensing Images](https://mlsanity.com/paper/2207.01755/) (2022)
- [Context-Guided Semantic Alignment for Feature Fusion Networks](https://mlsanity.com/paper/2606.14005/) (2026)

## Abstract (arXiv)

Salient object detection (SOD) is a fundamental computer vision task. Recently, with the revival of deep neural networks, SOD has made great progresses. However, there still exist two thorny issues that cannot be well addressed by existing methods, indistinguishable regions and complex structures. To address these two issues, in this paper we propose a novel deep network for accurate SOD, named CLASS. First, in order to leverage the different advantages of low-level and high-level features, we propose a novel non-local cross-level attention (CLA), which can capture the long-range feature dependencies to enhance the distinction of complete salient object. Second, a novel cross-level supervision (CLS) is designed to learn complementary context for complex structures through pixel-level, region-level and object-level. Then the fine structures and boundaries of salient objects can be well restored. In experiments, with the proposed CLA and CLS, our CLASS net. consistently outperforms 13 state-of-the-art methods on five datasets.