# Instance-Level Segmentation for Autonomous Driving with Deep Densely Connected MRFs

arXiv: https://arxiv.org/abs/1512.06735 · HTML: https://mlsanity.com/paper/1512.06735/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Dec 2015.

## Built on by (most cited first, 30 of 32)

- [Associating Objects with Transformers for Video Object Segmentation](https://mlsanity.com/paper/2106.02638/) (2021)
- [LVOS: A Benchmark for Long-term Video Object Segmentation](https://mlsanity.com/paper/2211.10181/) (2022)
- [OneTracker: Unifying Visual Object Tracking with Foundation Models and Efficient Tuning](https://mlsanity.com/paper/2403.09634/) (2024)
- [Frequency-aware Feature Fusion for Dense Image Prediction](https://mlsanity.com/paper/2408.12879/) (2024)
- [LVOS: A Benchmark for Large-scale Long-term Video Object Segmentation](https://mlsanity.com/paper/2404.19326/) (2024)
- [Instance-wise Occlusion and Depth Orders in Natural Scenes](https://mlsanity.com/paper/2111.14562/) (2021)
- [Towards Universal Modal Tracking with Online Dense Temporal Token Learning](https://mlsanity.com/paper/2507.20177/) (2025)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [An Empirical Study on the Robustness of the Segment Anything Model (SAM)](https://mlsanity.com/paper/2305.06422/) (2023)
- [Global Spectral Filter Memory Network for Video Object Segmentation](https://mlsanity.com/paper/2210.05567/) (2022)
- [Event-assisted Low-Light Video Object Segmentation](https://mlsanity.com/paper/2404.01945/) (2024)
- [ARMBench: An Object-centric Benchmark Dataset for Robotic Manipulation](https://mlsanity.com/paper/2303.16382/) (2023)
- [Camouflaged Instance Segmentation In-The-Wild: Dataset, Method, and Benchmark Suite](https://mlsanity.com/paper/2103.17123/) (2021)
- [Adversarial Attacks on Video Object Segmentation with Hard Region Discovery](https://mlsanity.com/paper/2309.13857/) (2023)
- [VideoClick: Video Object Segmentation with a Single Click](https://mlsanity.com/paper/2101.06545/) (2021)
- [Unsupervised domain adaptation for clinician pose estimation and instance segmentation in the operating room](https://mlsanity.com/paper/2108.11801/) (2021)
- [Test-time Adaptation vs. Training-time Generalization: A Case Study in Human Instance Segmentation using Keypoints Estimation](https://mlsanity.com/paper/2212.06242/) (2022)
- [S^4M: Boosting Semi-Supervised Instance Segmentation with SAM](https://mlsanity.com/paper/2504.05301/) (2025)
- [Pixel-level Certified Explanations via Randomized Smoothing](https://mlsanity.com/paper/2506.15499/) (2025)
- [Unsupervised Domain Adaptation for Semantic Segmentation via Low-level Edge Information Transfer](https://mlsanity.com/paper/2109.08912/) (2021)
- [Adaptive Hierarchical Certification for Segmentation using Randomized Smoothing](https://mlsanity.com/paper/2402.08400/) (2024)
- [ENInst: Enhancing Weakly-supervised Low-shot Instance Segmentation](https://mlsanity.com/paper/2302.09765/) (2023)
- [Salient Object Detection in Traffic Scene through the TSOD10K Dataset](https://mlsanity.com/paper/2503.16910/) (2025)
- [PAT: Pseudo-Adversarial Training For Detecting Adversarial Videos](https://mlsanity.com/paper/2109.05695/) (2021)
- [2nd Place Solution for MOSE Track in CVPR 2024 PVUW workshop: Complex Video Object Segmentation](https://mlsanity.com/paper/2406.08192/) (2024)
- [Progressive Scaling Visual Object Tracking](https://mlsanity.com/paper/2505.19990/) (2025)
- [RXFOOD: Plug-in RGB-X Fusion for Object of Interest Detection](https://mlsanity.com/paper/2306.12621/) (2023)
- [Joint Modeling of Feature, Correspondence, and a Compressed Memory for Video Object Segmentation](https://mlsanity.com/paper/2308.13505/) (2023)
- [Online Continual Domain Adaptation for Semantic Image Segmentation Using Internal Representations](https://mlsanity.com/paper/2401.01035/) (2024)
- [Lifelong Learning Using a Dynamically Growing Tree of Sub-networks for Domain Generalization in Video Object Segmentation](https://mlsanity.com/paper/2405.19525/) (2024)

## Abstract (arXiv)

Our aim is to provide a pixel-wise instance-level labeling of a monocular image in the context of autonomous driving. We build on recent work [Zhang et al., ICCV15] that trained a convolutional neural net to predict instance labeling in local image patches, extracted exhaustively in a stride from an image. A simple Markov random field model using several heuristics was then proposed in [Zhang et al., ICCV15] to derive a globally consistent instance labeling of the image. In this paper, we formulate the global labeling problem with a novel densely connected Markov random field and show how to encode various intuitive potentials in a way that is amenable to efficient mean field inference [Kr"ahenb"uhl et al., NIPS11]. Our potentials encode the compatibility between the global labeling and the patch-level predictions, contrast-sensitive smoothness as well as the fact that separate regions form different instances. Our experiments on the challenging KITTI benchmark [Geiger et al., CVPR12] demonstrate that our method achieves a significant performance boost over the baseline [Zhang et al., ICCV15].