paper-with-me

홈 › Papers

Enhanced Masked Image Modeling to Avoid Model Collapse on Multi-modal MRI Datasets

2024-07-15 · Linxuan Han, Sa Xiao, Zimeng Li, Haidong Li, Xiuchao Zhao, Yeqing Han, Fumin Guo, Xin Zhou

Multi-modal magnetic resonance imaging (MRI) provides information of lesions for computer-aided diagnosis from different views. Deep learning algorithms are suitable for identifying specific anatomical structures, segmenting lesions, and classifying diseases. Manual labels are limited due to the high expense, which hinders further improvement of accuracy. Self-supervised learning, particularly masked image modeling (MIM), has shown promise in utilizing unlabeled data. However, we spot model collapse when applying MIM to multi-modal MRI datasets. The performance of downstream tasks does not see any improvement following the collapsed model. To solve model collapse, we analyze and address it in two types: complete collapse and dimensional collapse. We find complete collapse occurs because the collapsed loss value in multi-modal MRI datasets falls below the normally converged loss value. Based on this, the hybrid mask pattern (HMP) masking strategy is introduced to elevate the collapsed loss above the normally converged loss value and avoid complete collapse. Additionally, we reveal that dimensional collapse stems from insufficient feature uniformity in MIM. We mitigate dimensional collapse by introducing the pyramid barlow twins (PBT) module as an explicit regularization method. Overall, we construct the enhanced MIM (E-MIM) with HMP and PBT module to avoid model collapse multi-modal MRI. Experiments are conducted on three multi-modal MRI datasets to validate the effectiveness of our approach in preventing both types of model collapse. By preventing model collapse, the training of the model becomes more stable, resulting in a decent improvement in performance for segmentation and classification tasks. The code is available at https://github.com/LinxuanHan/E-MIM.

📄 PDF Abstract BibTeX arXiv:2407.10377

Code (2)

linxuanhan/e-mim 공식 구현 pytorch
linxuanhan/m2-mae 공식 구현 pytorch

Tasks

MRI segmentationSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

MIM 설명 없음
Barlow Twins Barlow Twins is a self-supervised learning method that applies redundancy-reduction — a principle first proposed in neuroscience — to self supervised learning. The objective…

Similar Papers 제목 키워드 기반

Siamese Image Modeling for Self-Supervised Vision Representation Learning

2022-06-02 · CVPR 2023 1 · Chenxin Tao, Xizhou Zhu, Weijie Su, Gao Huang 외

Self-supervised learning (SSL) has delivered superior performance on a variety of downstream vision tasks. Two main-stream SSL frameworks have been proposed, i.e., Instance Discrimination (ID) and Masked Image Modeling (…

Representation LearningSelf-Supervised LearningSemantic SegmentationSensitivity

Enhancing JEPAs with Spatial Conditioning: Robust and Efficient Representation Learning

2024-10-14 · Etai Littwin, Vimal Thilak, Anand Gopalakrishnan

Image-based Joint-Embedding Predictive Architecture (IJEPA) offers an attractive alternative to Masked Autoencoder (MAE) for representation learning using the Masked Image Modeling framework. IJEPA drives representations…

image-classificationImage ClassificationRepresentation Learning

PFML: Self-Supervised Learning of Time-Series Data Without Representation Collapse

2024-11-15 · Einari Vaaras, Manu Airaksinen, Okko Räsänen

Self-supervised learning (SSL) is a data-driven learning approach that utilizes the innate structure of the data to guide the learning process. In contrast to supervised learning, which depends on external labels, SSL ut…

Contrastive LearningEEGEmotion RecognitionSelf-Supervised Learning+1

The Collapse of Patches

2025-11-27 · Wei Guo, Shunqi Mao, Zhuonan Liang, Heng Wang 외 arxiv

Observing certain patches in an image reduces the uncertainty of others. Their realization lowers the distribution entropy of each remaining patch feature, analogous to collapsing a particle's wave function in quantum me…

Image ClassificationImage Generation

Towards Efficient General Feature Prediction in Masked Skeleton Modeling

2025-09-03 · Shengkai Sun, Zefan Zhang, Jianfeng Dong, Zhiyong Cheng 외 arxiv

Recent advances in the masked autoencoder (MAE) paradigm have significantly propelled self-supervised skeleton-based action recognition. However, most existing approaches limit reconstruction targets to raw joint coordin…

Computational EfficiencyAction Recognition