# SelvaBox: A high-resolution dataset for tropical tree crown detection

arXiv: https://arxiv.org/abs/2507.00170 · HTML: https://mlsanity.com/paper/2507.00170/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 105 references that are in the map.
- First posted on arXiv 30 Jun 2025.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Masked-attention Mask Transformer for Universal Image Segmentation](https://mlsanity.com/paper/2112.01527/) (2021)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022)
- [DN-DETR: Accelerate DETR Training by Introducing Query DeNoising](https://mlsanity.com/paper/2203.01305/) (2022)
- [Soft-NMS -- Improving Object Detection With One Line of Code](https://mlsanity.com/paper/1704.04503/) (2017)
- [Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation](https://mlsanity.com/paper/2206.02777/) (2022)
- [Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning](https://mlsanity.com/paper/2212.14532/) (2022)
- [DETRs with Collaborative Hybrid Assignments Training](https://mlsanity.com/paper/2211.12860/) (2022)
- [A high-resolution canopy height model of the Earth](https://mlsanity.com/paper/2204.08322/) (2022)
- [Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on Aerial Lidar](https://mlsanity.com/paper/2304.07213/) (2023)
- [Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network](https://mlsanity.com/paper/2003.09085/) (2020)
- [FoMo: Multi-Modal, Multi-Scale and Multi-Task Remote Sensing Foundation Models for Forest Monitoring](https://mlsanity.com/paper/2312.10114/) (2023)
- [Application-Driven Innovation in Machine Learning](https://mlsanity.com/paper/2403.17381/) (2024)
- [FOR-instance: a UAV laser scanning benchmark dataset for semantic and instance segmentation of individual trees](https://mlsanity.com/paper/2309.01279/) (2023)
- [SegmentAnyTree: A sensor and platform agnostic deep learning model for tree segmentation using laser scanning data](https://mlsanity.com/paper/2401.15739/) (2024)
- [ReforesTree: A Dataset for Estimating Tropical Forest Carbon Stock with Deep Learning and Aerial Imagery](https://mlsanity.com/paper/2201.11192/) (2022)
- [OpenForest: A data catalogue for machine learning in forest monitoring](https://mlsanity.com/paper/2311.00277/) (2023)
- [TreeLearn: A deep learning method for segmenting individual trees from ground-based LiDAR forest point clouds](https://mlsanity.com/paper/2309.08471/) (2023)
- [OAM-TCD: A globally diverse dataset of high-resolution tree cover maps](https://mlsanity.com/paper/2407.11743/) (2024)
- [Benchmarking tree species classification from proximally-sensed laser scanning data: introducing the FOR-species20K dataset](https://mlsanity.com/paper/2408.06507/) (2024)
- [PureForest: A Large-Scale Aerial Lidar and Aerial Imagery Dataset for Tree Species Classification in Monospecific Forests](https://mlsanity.com/paper/2404.12064/) (2024)

## Built on by (most cited first, 5 of 5)

- [SelvaMask: Segmenting Trees in Tropical Forests and Beyond](https://mlsanity.com/paper/2602.02426/) (2026)
- [Estimating Individual Tree Height and Species from UAV Imagery](https://mlsanity.com/paper/2603.23669/) (2026)
- [Understanding Representation Gaps Across Scales in Tropical Tree Species Classification from Drone Imagery](https://mlsanity.com/paper/2604.23019/) (2026)
- [ResAF-Net: An Anchor-Free Attention-Based Network for Tree Detection and Agricultural Mapping in Palestine](https://mlsanity.com/paper/2604.23653/) (2026)
- [Latent Commonality Expectation-Maximisation for Box-supervised Tree Crown Instance Segmentation](https://mlsanity.com/paper/2609.26549/) (2026)

## Abstract (arXiv)

Detecting individual tree crowns in tropical forests is essential to study these complex and crucial ecosystems impacted by human interventions and climate change. However, tropical crowns vary widely in size, structure, and pattern and are largely overlapping and intertwined, requiring advanced remote sensing methods applied to high-resolution imagery. Despite growing interest in tropical tree crown detection, annotated datasets remain scarce, hindering robust model development. We introduce SelvaBox, the largest open-access dataset for tropical tree crown detection in high-resolution drone imagery. It spans three countries and contains more than 83,000 manually labeled crowns - an order of magnitude larger than all previous tropical forest datasets combined. Extensive benchmarks on SelvaBox reveal two key findings: (1) higher-resolution inputs consistently boost detection accuracy; and (2) models trained exclusively on SelvaBox achieve competitive zero-shot detection performance on unseen tropical tree crown datasets, matching or exceeding competing methods. Furthermore, jointly training on SelvaBox and three other datasets at resolutions from 3 to 10 cm per pixel within a unified multi-resolution pipeline yields a detector ranking first or second across all evaluated datasets. Our dataset, code, and pre-trained weights are made public.