# Bottom-up Instance Segmentation using Deep Higher-Order CRFs

arXiv: https://arxiv.org/abs/1609.02583 · HTML: https://mlsanity.com/paper/1609.02583/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Sep 2016.

## Built on by (most cited first, 8 of 8)

- [AISFormer: Amodal Instance Segmentation with Transformer](https://mlsanity.com/paper/2210.06323/) (2022)
- [ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts](https://mlsanity.com/paper/2301.12276/) (2023)
- [ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation](https://mlsanity.com/paper/2306.17319/) (2023)
- [Learning Equivariant Segmentation with Instance-Unique Querying](https://mlsanity.com/paper/2210.00911/) (2022)
- [supervised adptive threshold network for instance segmentation](https://mlsanity.com/paper/2106.03450/) (2021)
- [CarcassFormer: An End-to-end Transformer-based Framework for Simultaneous Localization, Segmentation and Classification of Poultry Carcass Defect](https://mlsanity.com/paper/2404.11429/) (2024)
- [Ideal Observer for Segmentation of Dead Leaves Images](https://mlsanity.com/paper/2512.05539/) (2025)
- [ZMIS-SAM: Segment Anything Model Enhanced with Wavelet Transform for Zooplankton Microscopy Image Instance Segmentation](https://mlsanity.com/paper/2607.27585/) (2026)

## Abstract (arXiv)

Traditional Scene Understanding problems such as Object Detection and Semantic Segmentation have made breakthroughs in recent years due to the adoption of deep learning. However, the former task is not able to localise objects at a pixel level, and the latter task has no notion of different instances of objects of the same class. We focus on the task of Instance Segmentation which recognises and localises objects down to a pixel level. Our model is based on a deep neural network trained for semantic segmentation. This network incorporates a Conditional Random Field with end-to-end trainable higher order potentials based on object detector outputs. This allows us to reason about instances from an initial, category-level semantic segmentation. Our simple method effectively leverages the great progress recently made in semantic segmentation and object detection. The accurate instance-level segmentations that our network produces is reflected by the considerable improvements obtained over previous work.