# Rethinking Learnable Tree Filter for Generic Feature Transform

arXiv: https://arxiv.org/abs/2012.03482 · HTML: https://mlsanity.com/paper/2012.03482/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2020.

## Built on by (most cited first, 10 of 10)

- [Personalize Segment Anything Model with One Shot](https://mlsanity.com/paper/2305.03048/) (2023)
- [GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction](https://mlsanity.com/paper/2305.18752/) (2023)
- [OTA: Optimal Transport Assignment for Object Detection](https://mlsanity.com/paper/2103.14259/) (2021)
- [Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation](https://mlsanity.com/paper/2203.10739/) (2022)
- [Meta-Adapter: An Online Few-shot Learner for Vision-Language Model](https://mlsanity.com/paper/2311.03774/) (2023)
- [DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection](https://mlsanity.com/paper/2207.10909/) (2022)
- [Dynamic Grained Encoder for Vision Transformers](https://mlsanity.com/paper/2301.03831/) (2023)
- [BoxSnake: Polygonal Instance Segmentation with Box Supervision](https://mlsanity.com/paper/2303.11630/) (2023)
- [Label-efficient Segmentation via Affinity Propagation](https://mlsanity.com/paper/2310.10533/) (2023)
- [Robust Self-Supervised Cross-Modal Super-Resolution against Real-World Misaligned Observations](https://mlsanity.com/paper/2602.18822/) (2026)

## Abstract (arXiv)

The Learnable Tree Filter presents a remarkable approach to model structure-preserving relations for semantic segmentation. Nevertheless, the intrinsic geometric constraint forces it to focus on the regions with close spatial distance, hindering the effective long-range interactions. To relax the geometric constraint, we give the analysis by reformulating it as a Markov Random Field and introduce a learnable unary term. Besides, we propose a learnable spanning tree algorithm to replace the original non-differentiable one, which further improves the flexibility and robustness. With the above improvements, our method can better capture long-range dependencies and preserve structural details with linear complexity, which is extended to several vision tasks for more generic feature transform. Extensive experiments on object detection/instance segmentation demonstrate the consistent improvements over the original version. For semantic segmentation, we achieve leading performance (82.1% mIoU) on the Cityscapes benchmark without bells-and-whistles. Code is available at https://github.com/StevenGrove/LearnableTreeFilterV2.