# End-to-End Instance Segmentation with Recurrent Attention

arXiv: https://arxiv.org/abs/1605.09410 · HTML: https://mlsanity.com/paper/1605.09410/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 May 2016.

## Built on by (most cited first, 4 of 4)

- [Object Detection with Transformers: A Review](https://mlsanity.com/paper/2306.04670/) (2023)
- [ARMBench: An Object-centric Benchmark Dataset for Robotic Manipulation](https://mlsanity.com/paper/2303.16382/) (2023)
- [Understanding the computational demands underlying visual reasoning](https://mlsanity.com/paper/2108.03603/) (2021)
- [PhD Thesis: Exploring the role of (self-)attention in cognitive and computer vision architecture](https://mlsanity.com/paper/2306.14650/) (2023)

## Abstract (arXiv)

While convolutional neural networks have gained impressive success recently in solving structured prediction problems such as semantic segmentation, it remains a challenge to differentiate individual object instances in the scene. Instance segmentation is very important in a variety of applications, such as autonomous driving, image captioning, and visual question answering. Techniques that combine large graphical models with low-level vision have been proposed to address this problem; however, we propose an end-to-end recurrent neural network (RNN) architecture with an attention mechanism to model a human-like counting process, and produce detailed instance segmentations. The network is jointly trained to sequentially produce regions of interest as well as a dominant object segmentation within each region. The proposed model achieves competitive results on the CVPPP, KITTI, and Cityscapes datasets.