mlsanityData to 14 Oct 2026

AME-CAM: Attentive Multiple-Exit CAM for Weakly Supervised Segmentation on MRI Brain Tumor

arXiv 2306.14505 ↗First posted 26 Jun 2023cs.CV cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Magnetic resonance imaging (MRI) is commonly used for brain tumor segmentation, which is critical for patient evaluation and treatment planning. To reduce the labor and expertise required for labeling, weakly-supervised semantic segmentation (WSSS) methods with class activation mapping (CAM) have been proposed. However, existing CAM methods suffer from low resolution due to strided convolution and pooling layers, resulting in inaccurate predictions. In this study, we propose a novel CAM method, Attentive Multiple-Exit CAM (AME-CAM), that extracts activation maps from multiple resolutions to hierarchically aggregate and improve prediction accuracy. We evaluate our method on the BraTS 2021 dataset and show that it outperforms state-of-the-art methods.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 18 of its 29 references that are in the map. First posted on arXiv 26 Jun 2023.

Builds on

18 of 29 references.

References · 18

  1. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  2. 2020Supervised Contrastive Learningcited by 2,829
  3. 2019Score-CAM: Score-Weighted Visual Explanations for Convolutional Neural Networkscited by 582
  4. 2018Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challengecited by 511
  5. 2020Self-supervised Equivariant Attention Mechanism for Weakly Supervised Semantic Segmentationcited by 300
  6. 2017Dilated Residual Networkscited by 294
  7. 2022Diffusion Models for Medical Anomaly Detectioncited by 232
  8. 2021Optimized U-Net for Brain Tumor Segmentationcited by 40
  9. 2019A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domainscited by 33
  10. 2021F-CAM: Full Resolution Class Activation Maps via Guided Parametric Upscalingcited by 26
  11. 2022Transformer based multiple instance learning for weakly supervised histopathology image segmentationcited by 26
  12. 2021ASC-Net : Adversarial-based Selective Network for Unsupervised Anomaly Segmentationcited by 15
6 more
  1. 2021LFI-CAM: Learning Feature Importance for Better Visual Explanationcited by 13
  2. 2022Poly-CAM: High resolution class activation map for convolutional neural networkscited by 10
  3. 2022Representative Image Feature Extraction via Contrastive Learning Pretraining for Chest X-ray Report Generationcited by 8
  4. 2020Medical Image Segmentation via Unsupervised Convolutional Neural Networkcited by 6
  5. 2020Do Noises Bother Human and Neural Networks In the Same Way? A Medical Image Analysis Perspectivecited by 3
  6. 2021"One-Shot" Reduction of Additive Artifacts in Medical Imagescited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 4; 2026: 2.

8 papers.

  1. 2024Enhancing Weakly Supervised 3D Medical Image Segmentation through Probabilistic-aware Learningcited by 2
  2. 2024ToNNO: Tomographic Reconstruction of a Neural Network's Output for Weakly Supervised Segmentation of 3D Medical Imagescited by 1
  3. 2026Weakly Supervised Teacher-Student Framework with Progressive Pseudo-mask Refinement for Gland Segmentationcited by 1
  4. 2025Unsupervised Out-of-Distribution Detection in Medical Imaging Using Multi-Exit Class Activation Maps and Feature Maskingcited by 0
  5. 2025Contrastive Learning with Diffusion Features for Weakly Supervised Medical Image Segmentationcited by 0
  6. 2025RASALoRE: Region Aware Spatial Attention with Location-based Random Embeddings for Weakly Supervised Anomaly Detection in Brain MRI Scanscited by 0
  7. 2025Hybrid Transformer-Mamba for Weakly Supervised Volumetric Medical Segmentationcited by 0
  8. 2026MOSAIC: Modality-agnostic Spectral Alignment for Federated Image-level Weakly Supervised Tumor Segmentation under Client-specific Missing Modalitiescited by 0