# Learnable Tree Filter for Structure-preserving Feature Transform

arXiv: https://arxiv.org/abs/1909.12513 · HTML: https://mlsanity.com/paper/1909.12513/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Sep 2019.

## Built on by (most cited first, 25 of 25)

- [GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction](https://mlsanity.com/paper/2305.18752/) (2023)
- [TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization](https://mlsanity.com/paper/2103.14862/) (2021)
- [Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2106.04054/) (2021)
- [Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation](https://mlsanity.com/paper/2203.10739/) (2022)
- [Unveiling the Potential of Structure Preserving for Weakly Supervised Object Localization](https://mlsanity.com/paper/2103.04523/) (2021)
- [Box-supervised Instance Segmentation with Level Set Evolution](https://mlsanity.com/paper/2207.09055/) (2022)
- [Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision](https://mlsanity.com/paper/2108.07682/) (2021)
- [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)
- [Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution](https://mlsanity.com/paper/2212.01579/) (2022)
- [LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation](https://mlsanity.com/paper/2304.11379/) (2023)
- [Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation](https://mlsanity.com/paper/2207.10892/) (2022)
- [GrootVL: Tree Topology is All You Need in State Space Model](https://mlsanity.com/paper/2406.02395/) (2024)
- [BoxSnake: Polygonal Instance Segmentation with Box Supervision](https://mlsanity.com/paper/2303.11630/) (2023)
- [Contrastive Multi-Task Dense Prediction](https://mlsanity.com/paper/2307.07934/) (2023)
- [Label-efficient Segmentation via Affinity Propagation](https://mlsanity.com/paper/2310.10533/) (2023)
- [Dynamic Feature Regularized Loss for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2108.01296/) (2021)
- [Unifying and Personalizing Weakly-supervised Federated Medical Image Segmentation via Adaptive Representation and Aggregation](https://mlsanity.com/paper/2304.05635/) (2023)
- [Segment Anything Across Shots: A Method and Benchmark](https://mlsanity.com/paper/2511.13715/) (2025)
- [Diversified Dynamic Routing for Vision Tasks](https://mlsanity.com/paper/2209.13071/) (2022)
- [Unsupervised Instance Segmentation with Superpixels](https://mlsanity.com/paper/2509.05352/) (2025)
- [Robust Self-Supervised Cross-Modal Super-Resolution against Real-World Misaligned Observations](https://mlsanity.com/paper/2602.18822/) (2026)
- [SAPNet++: Evolving Point-Prompted Instance Segmentation with Semantic and Spatial Awareness](https://mlsanity.com/paper/2602.21762/) (2026)
- [LIE: LiDAR-only HD Map Construction with Intensity Enhancement via Online Knowledge Distillation](https://mlsanity.com/paper/2605.01478/) (2026)

## Abstract (arXiv)

Learning discriminative global features plays a vital role in semantic segmentation. And most of the existing methods adopt stacks of local convolutions or non-local blocks to capture long-range context. However, due to the absence of spatial structure preservation, these operators ignore the object details when enlarging receptive fields. In this paper, we propose the learnable tree filter to form a generic tree filtering module that leverages the structural property of minimal spanning tree to model long-range dependencies while preserving the details. Furthermore, we propose a highly efficient linear-time algorithm to reduce resource consumption. Thus, the designed modules can be plugged into existing deep neural networks conveniently. To this end, tree filtering modules are embedded to formulate a unified framework for semantic segmentation. We conduct extensive ablation studies to elaborate on the effectiveness and efficiency of the proposed method. Specifically, it attains better performance with much less overhead compared with the classic PSP block and Non-local operation under the same backbone. Our approach is proved to achieve consistent improvements on several benchmarks without bells-and-whistles. Code and models are available at https://github.com/StevenGrove/TreeFilter-Torch.