# F3Net: Fusion, Feedback and Focus for Salient Object Detection

arXiv: https://arxiv.org/abs/1911.11445 · HTML: https://mlsanity.com/paper/1911.11445/

## Key facts

- Cited by 176 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2019.

## Built on by (most cited first, 30 of 176)

- [VAPO: Efficient and Reliable Reinforcement Learning for Advanced Reasoning Tasks](https://mlsanity.com/paper/2504.05118/) (2025)
- [Concealed Object Detection](https://mlsanity.com/paper/2102.10274/) (2021)
- [Simultaneously Localize, Segment and Rank the Camouflaged Objects](https://mlsanity.com/paper/2103.04011/) (2021)
- [Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers](https://mlsanity.com/paper/2108.06932/) (2021)
- [Camouflaged Object Segmentation with Distraction Mining](https://mlsanity.com/paper/2104.10475/) (2021)
- [Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection](https://mlsanity.com/paper/2203.02688/) (2022)
- [Salient Object Detection via Integrity Learning](https://mlsanity.com/paper/2101.07663/) (2021)
- [Uncertainty-aware Joint Salient Object and Camouflaged Object Detection](https://mlsanity.com/paper/2104.02628/) (2021)
- [Highly Accurate Dichotomous Image Segmentation](https://mlsanity.com/paper/2203.03041/) (2022)
- [Shallow Attention Network for Polyp Segmentation](https://mlsanity.com/paper/2108.00882/) (2021)
- [Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers](https://mlsanity.com/paper/2303.14816/) (2023)
- [Full-Duplex Strategy for Video Object Segmentation](https://mlsanity.com/paper/2108.03151/) (2021)
- [High-resolution Iterative Feedback Network for Camouflaged Object Detection](https://mlsanity.com/paper/2203.11624/) (2022)
- [Automatic Polyp Segmentation via Multi-scale Subtraction Network](https://mlsanity.com/paper/2108.05082/) (2021)
- [Specificity-preserving RGB-D Saliency Detection](https://mlsanity.com/paper/2108.08162/) (2021)
- [Deep Gradient Learning for Efficient Camouflaged Object Detection](https://mlsanity.com/paper/2205.12853/) (2022)
- [Pyramid Grafting Network for One-Stage High Resolution Saliency Detection](https://mlsanity.com/paper/2204.05041/) (2022)
- [Implicit Motion Handling for Video Camouflaged Object Detection](https://mlsanity.com/paper/2203.07363/) (2022)
- [Learning Generative Vision Transformer with Energy-Based Latent Space for Saliency Prediction](https://mlsanity.com/paper/2112.13528/) (2021)
- [RGB-D Saliency Detection via Cascaded Mutual Information Minimization](https://mlsanity.com/paper/2109.07246/) (2021)
- [SeeABLE: Soft Discrepancies and Bounded Contrastive Learning for Exposing Deepfakes](https://mlsanity.com/paper/2211.11296/) (2022)
- [CAVER: Cross-Modal View-Mixed Transformer for Bi-Modal Salient Object Detection](https://mlsanity.com/paper/2112.02363/) (2021)
- [TriTransNet: RGB-D Salient Object Detection with a Triplet Transformer Embedding Network](https://mlsanity.com/paper/2108.03990/) (2021)
- [Weakly-Supervised Camouflaged Object Detection with Scribble Annotations](https://mlsanity.com/paper/2207.14083/) (2022)
- [Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network](https://mlsanity.com/paper/2111.03216/) (2021)
- [Feature Aggregation and Propagation Network for Camouflaged Object Detection](https://mlsanity.com/paper/2212.00990/) (2022)
- [Multimodal Variational Auto-encoder based Audio-Visual Segmentation](https://mlsanity.com/paper/2310.08303/) (2023)
- [Frequency Perception Network for Camouflaged Object Detection](https://mlsanity.com/paper/2308.08924/) (2023)
- [Revisiting Image Pyramid Structure for High Resolution Salient Object Detection](https://mlsanity.com/paper/2209.09475/) (2022)
- [Disentangled High Quality Salient Object Detection](https://mlsanity.com/paper/2108.03551/) (2021)

## Abstract (arXiv)

Most of existing salient object detection models have achieved great progress by aggregating multi-level features extracted from convolutional neural networks. However, because of the different receptive fields of different convolutional layers, there exists big differences between features generated by these layers. Common feature fusion strategies (addition or concatenation) ignore these differences and may cause suboptimal solutions. In this paper, we propose the F3Net to solve above problem, which mainly consists of cross feature module (CFM) and cascaded feedback decoder (CFD) trained by minimizing a new pixel position aware loss (PPA). Specifically, CFM aims to selectively aggregate multi-level features. Different from addition and concatenation, CFM adaptively selects complementary components from input features before fusion, which can effectively avoid introducing too much redundant information that may destroy the original features. Besides, CFD adopts a multi-stage feedback mechanism, where features closed to supervision will be introduced to the output of previous layers to supplement them and eliminate the differences between features. These refined features will go through multiple similar iterations before generating the final saliency maps. Furthermore, different from binary cross entropy, the proposed PPA loss doesn't treat pixels equally, which can synthesize the local structure information of a pixel to guide the network to focus more on local details. Hard pixels from boundaries or error-prone parts will be given more attention to emphasize their importance. F3Net is able to segment salient object regions accurately and provide clear local details. Comprehensive experiments on five benchmark datasets demonstrate that F3Net outperforms state-of-the-art approaches on six evaluation metrics.