# MAPLE: Multi-Path Adaptive Propagation with Level-Aware Embeddings for Hierarchical Multi-Label Image Classification

arXiv: https://arxiv.org/abs/2603.29784 · HTML: https://mlsanity.com/paper/2603.29784/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 39 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Builds on (most cited first, 24 of 24)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [HuggingFace's Transformers: State-of-the-art Natural Language Processing](https://mlsanity.com/paper/1910.03771/) (2019)
- [MPNet: Masked and Permuted Pre-training for Language Understanding](https://mlsanity.com/paper/2004.09297/) (2020)
- [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017)
- [NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models](https://mlsanity.com/paper/2405.17428/) (2024)
- [Multi-Label Image Recognition with Graph Convolutional Networks](https://mlsanity.com/paper/1904.03582/) (2019)
- [PadChest: A large chest x-ray image dataset with multi-label annotated reports](https://mlsanity.com/paper/1901.07441/) (2019)
- [A Survey on Deep Semi-supervised Learning](https://mlsanity.com/paper/2103.00550/) (2021)
- [BigEarthNet: A Large-Scale Benchmark Archive For Remote Sensing Image Understanding](https://mlsanity.com/paper/1902.06148/) (2019)
- [Self-supervised Learning in Remote Sensing: A Review](https://mlsanity.com/paper/2206.13188/) (2022)
- [Coherent Hierarchical Multi-Label Classification Networks](https://mlsanity.com/paper/2010.10151/) (2020)
- [MLRSNet: A Multi-label High Spatial Resolution Remote Sensing Dataset for Semantic Scene Understanding](https://mlsanity.com/paper/2010.00243/) (2020)
- [Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework](https://mlsanity.com/paper/2204.13207/) (2022)
- [Hierarchical Image Classification using Entailment Cone Embeddings](https://mlsanity.com/paper/2004.03459/) (2020)
- [B-CNN: Branch Convolutional Neural Network for Hierarchical Classification](https://mlsanity.com/paper/1709.09890/) (2017)
- [Label Relation Graphs Enhanced Hierarchical Residual Network for Hierarchical Multi-Granularity Classification](https://mlsanity.com/paper/2201.03194/) (2022)
- [Relation Network for Multi-label Aerial Image Classification](https://mlsanity.com/paper/1907.07274/) (2019)
- [HGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical Understanding](https://mlsanity.com/paper/2311.14064/) (2023)
- [Multi-Label Retinal Disease Classification using Transformers](https://mlsanity.com/paper/2207.02335/) (2022)
- [Recurrently Exploring Class-wise Attention in A Hybrid Convolutional and Bidirectional LSTM Network for Multi-label Aerial Image Classification](https://mlsanity.com/paper/1807.11245/) (2018)
- [LLM Embeddings for Deep Learning on Tabular Data](https://mlsanity.com/paper/2502.11596/) (2025)

## Abstract (arXiv)

Hierarchical multi-label classification (HMLC) is essential for modeling structured label dependencies in remote sensing. Yet existing approaches struggle in multi-path settings, where images may activate multiple taxonomic branches, leading to underuse of hierarchical information. We propose MAPLE (Multi-Path Adaptive Propagation with Level-Aware Embeddings), a framework that integrates (i) hierarchical semantic initialization from graph-aware textual descriptions, (ii) graph-based structure encoding via graph convolutional networks (GCNs), and (iii) adaptive multi-modal fusion that dynamically balances semantic priors and visual evidence. An adaptive level-aware objective automatically selects appropriate losses per hierarchy level. Evaluations on CORINE-aligned remote sensing datasets (AID, DFC-15, and MLRSNet) show consistent improvements of up to +42% in few-shot regimes while adding only 2.6% parameter overhead, demonstrating that MAPLE effectively and efficiently models hierarchical semantics for Earth observation (EO).