# Iterative Instance Segmentation

arXiv: https://arxiv.org/abs/1511.08498 · HTML: https://mlsanity.com/paper/1511.08498/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2015.

## Built on by (most cited first, 19 of 19)

- [Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers](https://mlsanity.com/paper/2103.12340/) (2021)
- [Look Closer to Segment Better: Boundary Patch Refinement for Instance Segmentation](https://mlsanity.com/paper/2104.05239/) (2021)
- [Progressive Semantic Segmentation](https://mlsanity.com/paper/2104.03778/) (2021)
- [Instance-wise Occlusion and Depth Orders in Natural Scenes](https://mlsanity.com/paper/2111.14562/) (2021)
- [Topologically-Aware Deformation Fields for Single-View 3D Reconstruction](https://mlsanity.com/paper/2205.06267/) (2022)
- [A Unified Efficient Pyramid Transformer for Semantic Segmentation](https://mlsanity.com/paper/2107.14209/) (2021)
- [Discovering 3D Parts from Image Collections](https://mlsanity.com/paper/2107.13629/) (2021)
- [Towards the Unseen: Iterative Text Recognition by Distilling from Errors](https://mlsanity.com/paper/2107.12081/) (2021)
- [LiDARFormer: A Unified Transformer-based Multi-task Network for LiDAR Perception](https://mlsanity.com/paper/2303.12194/) (2023)
- [LidarMultiNet: Unifying LiDAR Semantic Segmentation, 3D Object Detection, and Panoptic Segmentation in a Single Multi-task Network](https://mlsanity.com/paper/2206.11428/) (2022)
- [SegMix: Co-occurrence Driven Mixup for Semantic Segmentation and Adversarial Robustness](https://mlsanity.com/paper/2108.09929/) (2021)
- [Diversified Multiscale Graph Learning with Graph Self-Correction](https://mlsanity.com/paper/2103.09754/) (2021)
- [Compact and Optimal Deep Learning with Recurrent Parameter Generators](https://mlsanity.com/paper/2107.07110/) (2021)
- [Occlusion-Aware Instance Segmentation via BiLayer Network Architectures](https://mlsanity.com/paper/2208.04438/) (2022)
- [Diverse Single Image Generation with Controllable Global Structure](https://mlsanity.com/paper/2102.04780/) (2021)
- [Sequential Ensembling for Semantic Segmentation](https://mlsanity.com/paper/2210.05387/) (2022)
- [OVeNet: Offset Vector Network for Semantic Segmentation](https://mlsanity.com/paper/2303.14516/) (2023)
- [Do Neural Networks for Segmentation Understand Insideness?](https://mlsanity.com/paper/2201.10664/) (2022)
- [Dense Point-to-Mask Optimization with Reinforced Point Selection for Crowd Instance Segmentation](https://mlsanity.com/paper/2604.01742/) (2026)

## Abstract (arXiv)

Existing methods for pixel-wise labelling tasks generally disregard the underlying structure of labellings, often leading to predictions that are visually implausible. While incorporating structure into the model should improve prediction quality, doing so is challenging - manually specifying the form of structural constraints may be impractical and inference often becomes intractable even if structural constraints are given. We sidestep this problem by reducing structured prediction to a sequence of unconstrained prediction problems and demonstrate that this approach is capable of automatically discovering priors on shape, contiguity of region predictions and smoothness of region contours from data without any a priori specification. On the instance segmentation task, this method outperforms the state-of-the-art, achieving a mean APr of 63.6% at 50% overlap and 43.3% at 70% overlap.