# Semantic Segmentation with Reverse Attention

arXiv: https://arxiv.org/abs/1707.06426 · HTML: https://mlsanity.com/paper/1707.06426/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jul 2017.

## Built on by (most cited first, 12 of 12)

- [Camouflaged Object Segmentation with Distraction Mining](https://mlsanity.com/paper/2104.10475/) (2021)
- [Fast Camouflaged Object Detection via Edge-based Reversible Re-calibration Network](https://mlsanity.com/paper/2111.03216/) (2021)
- [Visual Attention Methods in Deep Learning: An In-Depth Survey](https://mlsanity.com/paper/2204.07756/) (2022)
- [No Need For Real Anomaly: MLLM Empowered Zero-Shot Video Anomaly Detection](https://mlsanity.com/paper/2602.19248/) (2026)
- [Multi-Scale Grouped Prototypes for Interpretable Semantic Segmentation](https://mlsanity.com/paper/2409.09497/) (2024)
- [CTG-Net: An Efficient Cascaded Framework Driven by Terminal Guidance Mechanism for Dilated Pancreatic Duct Segmentation](https://mlsanity.com/paper/2303.02944/) (2023)
- [Don't worry about mistakes! Glass Segmentation Network via Mistake Correction](https://mlsanity.com/paper/2304.10825/) (2023)
- [Ultrasonic Image's Annotation Removal: A Self-supervised Noise2Noise Approach](https://mlsanity.com/paper/2307.04133/) (2023)
- [Advancing Medical Image Segmentation: Morphology-Driven Learning with Diffusion Transformer](https://mlsanity.com/paper/2408.00347/) (2024)
- [Interpretable Open-Vocabulary Referring Object Detection with Reverse Contrast Attention](https://mlsanity.com/paper/2507.19891/) (2025)
- [Automated Peripancreatic Vessel Segmentation and Labeling Based on Iterative Trunk Growth and Weakly Supervised Mechanism](https://mlsanity.com/paper/2303.02967/) (2023)
- [Uplifting Range-View-based 3D Semantic Segmentation in Real-Time with Multi-Sensor Fusion](https://mlsanity.com/paper/2407.09697/) (2024)

## Abstract (arXiv)

Recent development in fully convolutional neural network enables efficient end-to-end learning of semantic segmentation. Traditionally, the convolutional classifiers are taught to learn the representative semantic features of labeled semantic objects. In this work, we propose a reverse attention network (RAN) architecture that trains the network to capture the opposite concept (i.e., what are not associated with a target class) as well. The RAN is a three-branch network that performs the direct, reverse and reverse-attention learning processes simultaneously. Extensive experiments are conducted to show the effectiveness of the RAN in semantic segmentation. Being built upon the DeepLabv2-LargeFOV, the RAN achieves the state-of-the-art mIoU score (48.1%) for the challenging PASCAL-Context dataset. Significant performance improvements are also observed for the PASCAL-VOC, Person-Part, NYUDv2 and ADE20K datasets.