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

Boshko Koloski; Marjan Stoimchev; Jurica Levatić; Dragi Kocev; Sašo Džeroski

cs.CVMar 31, 2026

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

Authors: Boshko Koloski, Marjan Stoimchev, Jurica Levatić, Dragi Kocev, Sašo Džeroski

Organizations: Jožef Stefan Institute, Ljubljana, Slovenia · Jožef Stefan International Postgraduate School, Ljubljana, Slovenia

Abstract

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).

Figures & tables

Figure 1: MAPLE architecture overview. The framework processes an input image with a ViT encoder that uses hierarchy-specific class tokens. A GCN refines these token embeddings by propagating information along the label taxonomy. Finally, visual features and refined semantic embeddings are fused via adaptive gating to produce level-aware classifications.

Dataset	$l_{1}$	$l_{2}$	$l_{3}$	Leaf	MLC	$\Delta$ (%)
	MAPLE
AID	95.31	94.32	84.83	87.25	84.21	+3.6
DFC-15	99.62	98.33	98.37	98.71	98.65	+0.1
MLRSNet	98.23	97.88	96.77	96.71	96.17	+0.6

Table 1: Hierarchical vs. flat classification (AU

\overline{\text{PRC}}

%). MAPLE outperforms the flat baseline at all hierarchy levels (

l_{1}

–

l_{3}

) and leaf nodes.

Method	4-shot	8-shot	12-shot	16-shot
AID
MLC	0.286±0.018	0.334±0.012	0.341±0.025	0.310±0.009
MAPLE	0.357±0.021	0.371±0.017	0.396±0.039	0.440±0.046
$\Delta$ (%)	+25.0	+11.1	+16.1	+41.9
DFC-15
MLC	0.541±0.044	0.541±0.012	0.790±0.008	0.807±0.021

Table 2: Few-shot performance (AU

\overline{\text{PRC}}

) with K-shot training per class.

\mu\pm\sigma

over 3 runs.

\Delta

shows MAPLE’s improvement over the MLC baseline.

Method	AID	DFC-15	MLRSNet
C-HMCNN [ 11 ]	0.764	0.962	0.792
HiMulConE [ 7 ]	0.770	0.970	0.865
HMI [ 23 ]	0.647	0.923	0.437
MAPLE (Ours)	0.872	0.987	0.967

Table 3: Comparison with state-of-the-art HMLC methods on leaf-level AU

\overline{\text{PRC}}

(

\uparrow

). Best in bold , second-best underlined .

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Figure 2: Examples of constructed label hierarchies for (a) the AID dataset, derived from the CORINE Land Cover (CLC) nomenclature, and (b) the MuRed dataset, with abbreviations in leaf labels corresponding to ICD-10 codes of disease names.

	$N$	$N_{train}$	$N_{test}$	$\|\mathcal{L}\|$
Dataset				$1$	$2$	$3$	$4$	$5$	$6$	${\ell}$
AID	3,000	2,400	600	4	9	15	7	-	-	17
DFC-15	3,341	2,672	669	3	7	7	-	-	-	8
MLRSNet	109,151	87,336	21,815	7	15	22	60	-	-	60
MuRed	2,208	1,764	444	4	8	17	5	-	-	20
HPA	31,072	24,837	6,235	6	28	-	-	-	-	28

Appendix

Table 4: Summary of the datasets used in this study.

N

denotes the total number of images in each dataset, while

N_{train}

and

N_{test}

represent the number of images in the training and test sets, respectively.

|\mathcal{L}|

indicates the number of unique labels at each hierarchical level, where

{\ell}

corresponds to the deepest (leaf) level.

Figure 3: Representative examples from the nine datasets used in our evaluation, showing sample images alongside their corresponding hierarchical label structures. The datasets span three domains: remote sensing (AID, DFC-15, MLRSNet), medical imaging (MuRed, HPA, PadChest), and fine-grained visual categorization (OxfordPets-37, Stanford Cars, ETHEC). Each hierarchy displays the multi-level taxonomic organization from coarse-grained categories at Level 1 to fine-grained leaf labels.

Remote Sensing Datasets
Dataset		MAPLE*	MAPLE	Flat Baseline	$\boldsymbol{\Delta^{*}}$ (%)	$\boldsymbol{\Delta}$ (%)
AID	$l_{1}$	95.31	94.11	-	-	-
	$l_{2}$	94.32	93.10	-	-	-
	$l_{3}$	84.83	82.50	-	-	-
	Leaf	87.25	86.66	84.21	+3.61	+2.91
DFC-15	$l_{1}$	99.62	99.51	-	-	-

Appendix

Table 5: Complete performance comparison across hierarchical levels using AU

\overline{\textrm{PRC}}

(%). This table extends Table 1 from the main paper with results across all nine datasets and all hierarchical levels.

l_{i}

denotes the

i

-th hierarchical level. MAPLE* uses semantic initialization while MAPLE uses random initialization.

\Delta^{*}

and

\Delta

show relative improvements over flat baseline.

Figure 5: Few-shot learning performance comparison between MAPLE (in green ) and flat MLC baseline (in red ) across representative datasets. Results show AU

\overline{\textrm{PRC}}

performance (

\mu\pm\sigma

across three experimental repeats) for varying numbers of shots per category (

K\in\{4,8,12,16\}

). MAPLE consistently outperforms the baseline, with particularly pronounced benefits in low-data regimes.

	Per Image (ms)
Model	$8$	$16$	$32$	$64$	GFLOPs	Params (M)
Flat Baseline	3.02	2.96	2.62	2.55	33.54	86.57
MAPLE	3.18	3.01	2.65	2.61	33.77	88.84
Overhead (%)	+5.3	+1.7	+1.1	+2.4	+0.7	+2.6

Appendix

Table 6: Computational efficiency comparison on AID dataset.

Figure 6: Evolution of node embeddings throughout MAPLE training stages visualized using UMAP dimensionality reduction on the AID dataset. (a) Initial embeddings show random spatial distribution. (b) Learned embeddings after hierarchical semantic initialization demonstrate clear semantic clustering. (c) GNN embeddings after graph neural network refinement exhibit enhanced separation between semantic groups. (d) Visual-fused embeddings after multimodal fusion achieve sophisticated organization, integrating both visual and semantic information while respecting hierarchical structure.

Dataset	Baseline	MAPLE	Improvement (%)	Absolute Reduction
AID	107	94	12.1	13
MuRed	77	76	1.3	1
Oxford Pets	41	12	70.7	29

Appendix

Table 7: Leaf-level confusion reduction across datasets. MAPLE consistently reduces confusion instances compared to baseline models, with particularly strong improvements on Oxford Pets (70.7% reduction) and AID (12.1% reduction). Lower values indicate better performance.

Figure 7: Leaf-level confusion matrix comparison for AID dataset. Left: baseline model confusions, Center: MAPLE confusions, Right: difference matrix (MAPLE $-$ Baseline). Blue cells indicate reduced confusions (improvements), red cells indicate increased confusions. MAPLE achieves a 12.1% reduction in total leaf-level confusions, with notable improvements in semantically challenging pairs such as trees $\rightarrow$ water and buildings $\rightarrow$ bare-soil.

Figure 8: Performance comparison of different GNN architectures across datasets.

Figure 9: Comparison of embedding initialization strategies.

Hierarchical Classification

Hierarchical classification uses relationships among labels to predict categories at multiple levels, from broad groups to fine-grained classes.

See all 89 papers

HELM: Hierarchical and Explicit Label Modeling with Graph Learning for Multi-Label Image Classification
Mar 12, 2026Marjan Stoimchev, Boshko Koloski, Jurica Levatić +2Multi-Label Classification Remote Sensing Image Understanding
Jožef Stefan Institute, Ljubljana, Slovenia · Jožef Stefan International Postgraduate School, Ljubljana, Slovenia
Semantics-Aware Hierarchical Consensus Learning for Remote Sensing Image Classification
Oct 6, 2025Giulio Weikmann, Gianmarco Perantoni, Lorenzo BruzzoneHierarchical Classification Remote Sensing
Department of Information Engineering and Computer Science, University of Trento, 38123 Trento, Italy
Beyond Flat Labels: Level-Restricted Contrastive Learning for Hierarchical Fine-Grained Vision Classification
Jun 20, 2026Zhiyuan Tao, Srikumar Sastry, Matthew J Thompson +9Hierarchical Classification Contrastive Learning
The Ohio State University · Washington University in St. Louis · Neuromatch +1

Mar 12, 2026J/K move · Enter open · S save

HELM: Hierarchical and Explicit Label Modeling with Graph Learning for Multi-Label Image Classification

Marjan Stoimchev, Boshko Koloski, Jurica Levatić, Dragi Kocev+1

Jožef Stefan Institute, Ljubljana, Slovenia · Jožef Stefan International Postgraduate School, Ljubljana, Slovenia

Multi-Label Classification Remote Sensing Image Understanding Hierarchical Representation Learning

Open paper AskPDF arXiv

Hierarchical multi-label classification (HMLC) is essential for modeling complex label dependencies in remote sensing. Existing methods, however, struggle with multi-path hierarchies where instances belong to multiple branches, and they rarely exploit unlabeled data. We introduce HELM (Hierarchical and Explicit Label Modeling), a novel framework that overcomes these limitations. HELM: (i) uses hierarchy-specific class tokens within a Vision Transformer to capture nuanced label interactions; (ii) employs graph convolutional networks to explicitly encode the hierarchical structure and generate hierarchy-aware embeddings; and (iii) integrates a self-supervised branch to effectively leverage unlabeled imagery. We perform a comprehensive evaluation on four remote sensing image (RSI) datasets (UCM, AID, DFC-15, MLRSNet). HELM achieves state-of-the-art performance, consistently outperforming strong baselines in both supervised and semi-supervised settings, demonstrating particular strength in low-label scenarios.

Abstract

Hierarchical Classification

Explore similar work

HELM: Hierarchical and Explicit Label Modeling with Graph Learning for Multi-Label Image Classification

Semantics-Aware Hierarchical Consensus Learning for Remote Sensing Image Classification

Beyond Flat Labels: Level-Restricted Contrastive Learning for Hierarchical Fine-Grained Vision Classification