Every Error has Its Magnitude: Asymmetric Mistake Severity Training for Multiclass Multiple Instance Learning

• URL: http://arxiv.org/abs/2603.13682v1
• Date: Sat, 14 Mar 2026 01:36:12 GMT
• Title: Every Error has Its Magnitude: Asymmetric Mistake Severity Training for Multiclass Multiple Instance Learning
• Abstract summary: Multiple Instance Learning (MIL) has emerged as a promising paradigm for Whole Slide Image (WSI) diagnosis.<n>We propose a mistake-severity-aware training strategy that organizes diagnostic classes into a hierarchical structure.<n>We show that our approach significantly mitigates critical errors in MIL diagnosis compared to existing methods.
• Score: 7.643169473987673
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Multiple Instance Learning (MIL) has emerged as a promising paradigm for Whole Slide Image (WSI) diagnosis, offering effective learning with limited annotations. However, existing MIL frameworks overlook diagnostic priorities and fail to differentiate the severity of misclassifications in multiclass, leaving clinically critical errors unaddressed. We propose a mistake-severity-aware training strategy that organizes diagnostic classes into a hierarchical structure, with each level optimized using a severity-weighted cross-entropy loss that penalizes high-severity misclassifications more strongly. Additionally, hierarchical consistency is enforced through probabilistic alignment, a semantic feature remix applied to the instance bag to robustly train class priority and accommodate clinical cases involving multiple symptoms. An asymmetric Mikel's Wheel-based metric is also introduced to quantify the severity of errors specific to medical fields. Experiments on challenging public and real-world in-house datasets demonstrate that our approach significantly mitigates critical errors in MIL diagnosis compared to existing methods. We present additional experimental results on natural domain data to demonstrate the generalizability of our proposed method beyond medical contexts.

Related papers

• Clinical Cognition Alignment for Gastrointestinal Diagnosis with Multimodal LLMs [63.535652574541764]
  Multimodal Large Language Models (MLLMs) have demonstrated remarkable potential in medical image analysis.<n>Their application in gastrointestinal endoscopy is currently hindered by two critical limitations.<n>We propose a novel Clinical-Cognitive-Aligned (CogAlign) framework to address these challenges.
  arXiv  Detail & Related papers  (2026-03-21T07:47:37Z)
• Diagnose Like A REAL Pathologist: An Uncertainty-Focused Approach for Trustworthy Multi-Resolution Multiple Instance Learning [5.073978768018109]
  Multiple Instance Learning (MIL) has received heightened research focus as a viable solution for AI-centric diagnostic aid.<n>We propose Uncertainty-Focused Calibrated MIL (UFC-MIL), which more closely mimics the pathologists' examination behaviors.<n> UFC-MIL shows superior performance in model calibration while achieving classification accuracy comparable to that of state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-11-09T16:02:13Z)
• CLIMD: A Curriculum Learning Framework for Imbalanced Multimodal Diagnosis [21.001994821490644]
  We propose a Curriculum Learning framework for Imbalanced Multimodal Diagnosis (CLIMD)<n>Specifically, we first design multimodal curriculum measurer that combines intra-modal confidence and inter-modal complementarity, to enable the model to focus on key samples.<n>As a plug-and-play CL framework, CLIMD can be easily integrated into other models, offering a promising path for improving multimodal disease diagnosis accuracy.
  arXiv  Detail & Related papers  (2025-08-03T05:25:12Z)
• Priority-Aware Clinical Pathology Hierarchy Training for Multiple Instance Learning [5.119970053489523]
  We propose a new method that addresses priority issues using two hierarchies: vertical inter-hierarchy and horizontal intra-hierarchy.<n>The proposed method aligns MIL predictions across each hierarchical level and employs an implicit feature re-usability during training to facilitate clinically more serious classes within the same level.<n>Experiments with real-world patient data show that the proposed method effectively reduces misdiagnosis and prioritizes more important symptoms in multiclass scenarios.
  arXiv  Detail & Related papers  (2025-07-28T02:09:29Z)
• CLIP Meets Diffusion: A Synergistic Approach to Anomaly Detection [49.11819337853632]
  Anomaly detection is a complex problem due to the ambiguity in defining anomalies, the diversity of anomaly types, and the scarcity of training data.<n>We propose CLIPfusion, a method that leverages both discriminative and generative foundation models.<n>We believe that our method underscores the effectiveness of multi-modal and multi-model fusion in tackling the multifaceted challenges of anomaly detection.
  arXiv  Detail & Related papers  (2025-06-13T13:30:15Z)
• Error Classification of Large Language Models on Math Word Problems: A Dynamically Adaptive Framework [79.40678802098026]
  Math Word Problems serve as a crucial benchmark for evaluating Large Language Models' reasoning abilities.<n>Current error classification methods rely on static and predefined categories.<n>We propose Error-Aware Prompting (EAP) that incorporates common error patterns as explicit guidance.
  arXiv  Detail & Related papers  (2025-01-26T16:17:57Z)
• Fine-grained Abnormality Prompt Learning for Zero-shot Anomaly Detection [109.72772150095646]
  FAPrompt is a novel framework designed to learn Fine-grained Abnormality Prompts for accurate ZSAD.<n>Experiments on 19 real-world datasets, covering both industrial defects and medical anomalies, demonstrate that FAPrompt substantially outperforms state-of-the-art methods in both image- and pixel-level ZSAD tasks.
  arXiv  Detail & Related papers  (2024-10-14T08:41:31Z)
• Position: From Correlation to Causation: Max-Pooling-Based Multi-Instance Learning Leads to More Robust Whole Slide Image Classification [51.95824566163554]
  We argue that well-trained max-pooling-based MIL models can make predictions based on causal factors and avoid relying on spurious correlations.<n>We propose a simple yet effective max-pooling-based MIL method (FocusMIL) that outperforms existing mainstream attention-based methods on two datasets.
  arXiv  Detail & Related papers  (2024-08-18T12:15:22Z)
• TVDiag: A Task-oriented and View-invariant Failure Diagnosis Framework with Multimodal Data [11.373761837547852]
  Microservice-based systems often suffer from reliability issues due to their intricate interactions and expanding scale.<n>Traditional failure diagnosis methods that use single-modal data can hardly cover all failure scenarios due to the restricted information.<n>We propose textitTVDiag, a multimodal failure diagnosis framework for locating culprit microservice instances and identifying their failure types.
  arXiv  Detail & Related papers  (2024-07-29T05:26:57Z)
• Improving Multiple Sclerosis Lesion Segmentation Across Clinical Sites: A Federated Learning Approach with Noise-Resilient Training [75.40980802817349]
  Deep learning models have shown promise for automatically segmenting MS lesions, but the scarcity of accurately annotated data hinders progress in this area. We introduce a Decoupled Hard Label Correction (DHLC) strategy that considers the imbalanced distribution and fuzzy boundaries of MS lesions. We also introduce a Centrally Enhanced Label Correction (CELC) strategy, which leverages the aggregated central model as a correction teacher for all sites.
  arXiv  Detail & Related papers  (2023-08-31T00:36:10Z)
• Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection [37.99031842449251]
  Video anomaly detection under weak supervision presents significant challenges. We present a weakly supervised anomaly detection framework that focuses on efficient context modeling and enhanced semantic discriminability. Our approach significantly improves the detection accuracy of certain anomaly sub-classes, underscoring its practical value and efficacy.
  arXiv  Detail & Related papers  (2023-06-26T06:45:16Z)
• MaxMatch: Semi-Supervised Learning with Worst-Case Consistency [149.03760479533855]
  We propose a worst-case consistency regularization technique for semi-supervised learning (SSL) We present a generalization bound for SSL consisting of the empirical loss terms observed on labeled and unlabeled training data separately. Motivated by this bound, we derive an SSL objective that minimizes the largest inconsistency between an original unlabeled sample and its multiple augmented variants.
  arXiv  Detail & Related papers  (2022-09-26T12:04:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.