arXiv subjects

Takanori Takebe

Publications and source records attributed to Takanori Takebe.

3 recordsLinked to original sources

arXiv2025

SimLabel: Similarity-Weighted Iterative Framework for Multi-annotator Learning with Missing Annotations

Multi-annotator learning (MAL) aims to model annotator-specific labeling patterns. However, existing methods face a critical challenge: they simply skip updating annotator-specific model parameters when encountering missing labels, i.e., a common scenario in real-world crowdsourced datasets where each annotator labels only small subsets of samples. This leads to inefficient data utilization and overfitting risks. To this end, we propose a novel similarity-weighted semi-supervised learning framework (SimLabel) that leverages inter-annotator similarities to generate weighted soft labels for missing annotations, enabling the utilization of unannotated samples rather than skipping them entirely. We further introduce a confidence-based iterative refinement mechanism that combines maximum probability with entropy-based uncertainty to prioritize predicted high-quality pseudo-labels to impute missing labels, jointly enhancing similarity estimation and model performance over time. For evaluation, we contribute a new multimodal multi-annotator dataset, AMER2, with high and more variable missing rates, reflecting real-world annotation sparsity and enabling evaluation across different sparsity levels.

cs.MM↗

arXiv2025

QuMAB: Query-based Multi-Annotator Behavior Modeling with Reliability under Sparse Labels

Multi-annotator learning traditionally aggregates diverse annotations to approximate a single ground truth, treating disagreements as noise. However, this paradigm faces fundamental challenges: subjective tasks often lack absolute ground truth, and sparse annotation coverage makes aggregation statistically unreliable. We introduce a paradigm shift from sample-wise aggregation to annotator-wise behavior modeling. By treating annotator disagreements as valuable information rather than noise, modeling annotator-specific behavior patterns can reconstruct unlabeled data to reduce annotation cost, enhance aggregation reliability, and explain annotator decision behavior. To this end, we propose QuMAB (Query-based Multi-Annotator Behavior Pattern Learning), which uses light-weight queries to model individual annotators while capturing inter-annotator correlations as implicit regularization, preventing overfitting to sparse individual data while maintaining individualization and improving generalization, with a visualization of annotator focus regions offering an explainable analysis of behavior understanding. We contribute two large-scale datasets with dense per-annotator labels: STREET (4,300 labels/annotator) and AMER (average 3,118 labels/annotator), the first multimodal multi-annotator dataset. Extensive experiments demonstrate the superiority of our QuMAB in modeling individual annotators' behavior patterns, their utility for consensus prediction, and applicability under sparse annotations.

cs.MM↗

arXiv2025

QuMATL: Query-based Multi-annotator Tendency Learning

Different annotators often assign different labels to the same sample due to backgrounds or preferences, and such labeling patterns are referred to as tendency. In multi-annotator scenarios, we introduce a novel task called Multi-annotator Tendency Learning (MATL), which aims to capture each annotator tendency. Unlike traditional tasks that prioritize consensus-oriented learning, which averages out annotator differences and leads to tendency information loss, MATL emphasizes learning each annotator tendency, better preserves tendency information. To this end, we propose an efficient baseline method, Query-based Multi-annotator Tendency Learning (QuMATL), which uses lightweight query to represent each annotator for tendency modeling. It saves the costs of building separate conventional models for each annotator, leverages shared learnable queries to capture inter-annotator correlations as an additional hidden supervisory signal to enhance modeling performance. Meanwhile, we provide a new metric, Difference of Inter-annotator Consistency (DIC), to evaluate how effectively models preserve annotators tendency information. Additionally, we contribute two large-scale datasets, STREET and AMER, providing averages of 4300 and 3118 per-annotator labels, respectively. Extensive experiments verified the effectiveness of our QuMATL.

cs.MM↗