Self-supervised Learning of Dense Hierarchical Representations for Medical Image Segmentation

• URL: http://arxiv.org/abs/2401.06473v2
• Date: Sun, 26 May 2024 08:17:57 GMT
• Title: Self-supervised Learning of Dense Hierarchical Representations for Medical Image Segmentation
• Authors: Eytan Kats, Jochen G. Hirsch, Mattias P. Heinrich,
• Abstract summary: This paper demonstrates a self-supervised framework for learning voxel-wise coarse-to-fine representations tailored for dense downstream tasks. We devise a training strategy that balances the contributions of features from multiple scales, ensuring that the learned representations capture both coarse and fine-grained details.
• Score: 2.2265038612930663
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: This paper demonstrates a self-supervised framework for learning voxel-wise coarse-to-fine representations tailored for dense downstream tasks. Our approach stems from the observation that existing methods for hierarchical representation learning tend to prioritize global features over local features due to inherent architectural bias. To address this challenge, we devise a training strategy that balances the contributions of features from multiple scales, ensuring that the learned representations capture both coarse and fine-grained details. Our strategy incorporates 3-fold improvements: (1) local data augmentations, (2) a hierarchically balanced architecture, and (3) a hybrid contrastive-restorative loss function. We evaluate our method on CT and MRI data and demonstrate that our new approach particularly beneficial for fine-tuning with limited annotated data and consistently outperforms the baseline counterpart in linear evaluation settings.

Related papers

• Scalable Deep Metric Learning on Attributed Graphs [10.092560681589578]
  We develop a graph embedding method, which is based on extending deep metric and unbiased contrastive learning techniques. Based on a multi-classt loss function, we present two algorithms -- DMT for semi-supervised learning and DMAT-i for the unsupervised case.
  arXiv  Detail & Related papers  (2024-11-20T03:34:31Z)
• ACTRESS: Active Retraining for Semi-supervised Visual Grounding [52.08834188447851]
  A previous study, RefTeacher, makes the first attempt to tackle this task by adopting the teacher-student framework to provide pseudo confidence supervision and attention-based supervision. This approach is incompatible with current state-of-the-art visual grounding models, which follow the Transformer-based pipeline. Our paper proposes the ACTive REtraining approach for Semi-Supervised Visual Grounding, abbreviated as ACTRESS.
  arXiv  Detail & Related papers  (2024-07-03T16:33:31Z)
• Hierarchical Insights: Exploiting Structural Similarities for Reliable 3D Semantic Segmentation [4.480310276450028]
  We propose a training strategy for a 3D LiDAR semantic segmentation model that learns structural relationships between classes through abstraction. This is achieved by implicitly modeling these relationships using a learning rule for hierarchical multi-label classification (HMC) Our detailed analysis demonstrates that this training strategy not only improves the model's confidence calibration but also retains additional information useful for downstream tasks such as fusion, prediction, and planning.
  arXiv  Detail & Related papers  (2024-04-09T08:49:01Z)
• Class Anchor Margin Loss for Content-Based Image Retrieval [97.81742911657497]
  We propose a novel repeller-attractor loss that falls in the metric learning paradigm, yet directly optimize for the L2 metric without the need of generating pairs. We evaluate the proposed objective in the context of few-shot and full-set training on the CBIR task, by using both convolutional and transformer architectures.
  arXiv  Detail & Related papers  (2023-06-01T12:53:10Z)
• Repurposing Knowledge Graph Embeddings for Triple Representation via Weak Supervision [77.34726150561087]
  Current methods learn triple embeddings from scratch without utilizing entity and predicate embeddings from pre-trained models. We develop a method for automatically sampling triples from a knowledge graph and estimating their pairwise similarities from pre-trained embedding models. These pairwise similarity scores are then fed to a Siamese-like neural architecture to fine-tune triple representations.
  arXiv  Detail & Related papers  (2022-08-22T14:07:08Z)
• Modularity Optimization as a Training Criterion for Graph Neural Networks [2.903711704663904]
  We investigate the effect on the quality of learned representations by the incorporation of community structure preservation objectives of networks in the graph convolutional model. Experimental evaluation on two attributed bibilographic networks showed that the incorporation of the community-preserving objective improves semi-supervised node classification accuracy in the sparse label regime.
  arXiv  Detail & Related papers  (2022-06-30T21:32:33Z)
• Imposing Consistency for Optical Flow Estimation [73.53204596544472]
  Imposing consistency through proxy tasks has been shown to enhance data-driven learning. This paper introduces novel and effective consistency strategies for optical flow estimation.
  arXiv  Detail & Related papers  (2022-04-14T22:58:30Z)
• Clustering by Maximizing Mutual Information Across Views [62.21716612888669]
  We propose a novel framework for image clustering that incorporates joint representation learning and clustering. Our method significantly outperforms state-of-the-art single-stage clustering methods across a variety of image datasets.
  arXiv  Detail & Related papers  (2021-07-24T15:36:49Z)
• PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning [109.84770951839289]
  We present PredRNN, a new recurrent network for learning visual dynamics from historical context. We show that our approach obtains highly competitive results on three standard datasets.
  arXiv  Detail & Related papers  (2021-03-17T08:28:30Z)
• Hierarchical Domain-Adapted Feature Learning for Video Saliency Prediction [15.270499225813841]
  We propose a 3D fully convolutional architecture for video saliency prediction. We provide the base hierarchical learning mechanism with two techniques for domain adaptation and domain-specific learning. The results of our experiments show that the proposed model yields state-of-the-art accuracy on supervised saliency prediction.
  arXiv  Detail & Related papers  (2020-10-02T23:00:00Z)
• Progressive Learning and Disentanglement of Hierarchical Representations [10.201945347770643]
  We present a strategy to progressively learn independent hierarchical representations from high- to low-levels of abstractions. We quantitatively demonstrate the ability of the presented model to improve disentanglement in comparison to existing works.
  arXiv  Detail & Related papers  (2020-02-24T21:19:38Z)

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.