Related papers: Soft-Label Anonymous Gastric X-ray Image Distillat…
Histological analysis of tissue samples is one of the most widely used methods for disease diagnosis. After taking a sample from a patient, it goes through a lengthy and laborious preparation, which stains the tissue to visualize different…
Recent advancements in self-supervised learning have reduced the gap between supervised and unsupervised representation learning. However, most self-supervised and deep clustering techniques rely heavily on data augmentation, rendering them…
In recent years, the research landscape of machine learning in medical imaging has changed drastically from supervised to semi-, weakly- or unsupervised methods. This is mainly due to the fact that ground-truth labels are time-consuming and…
Semantic segmentation is a challenging computer vision task demanding a significant amount of pixel-level annotated data. Producing such data is a time-consuming and costly process, especially for domains with a scarcity of experts, such as…
This paper proposes a novel pseudo-labeling method for medical image segmentation that can perform learning on ``individual images'' to select effective pseudo-labels. We introduce Positive and Unlabeled Learning (PU learning), which uses…
Learning from noisy data has become essential for adapting deep learning models to real-world applications. Traditional methods often involve first evaluating the noise and then applying strategies such as discarding noisy samples,…
Automated labeling of chest X-ray reports is essential for enabling downstream tasks such as training image-based diagnostic models, population health studies, and clinical decision support. However, the high variability, complexity, and…
Foundation Models (FMs) have demonstrated strong generalization across diverse vision tasks. However, their deployment in federated settings is hindered by high computational demands, substantial communication overhead, and significant…
Medical image classification is a challenging task due to the scarcity of labeled samples and class imbalance caused by the high variance in disease prevalence. Semi-supervised learning (SSL) methods can mitigate these challenges by…
Segmenting tumors in histological images is vital for cancer diagnosis. While fully supervised models excel with pixel-level annotations, creating such annotations is labor-intensive and costly. Accurate histopathology image segmentation…
Deep learning holds immense promise for transforming medical image analysis, yet its clinical generalization remains profoundly limited. A major barrier is data heterogeneity. This is particularly true in Magnetic Resonance Imaging, where…
The increased growth in the use of transmission of multimedia medical contents over unsecured and open networks provides insecurity for confidential patient information over these networks. Digital encryption of medical images before…
Dataset distillation aims to encapsulate the rich information contained in dataset into a compact distilled dataset but it faces performance degradation as the image-per-class (IPC) setting or image resolution grows larger. Recent…
We present a conceptually simple self-supervised method for saliency detection. Our method generates and uses pseudo-ground truth labels for training. The generated pseudo-GT labels don't require any kind of human annotations (e.g.,…
Dataset distillation aims to synthesize a compact subset of the original data, enabling models trained on it to achieve performance comparable to those trained on the original large dataset. Existing distribution-matching methods are…
Knowledge distillation is typically conducted by training a small model (the student) to mimic a large and cumbersome model (the teacher). The idea is to compress the knowledge from the teacher by using its output probabilities as…
Knowledge distillation has been widely used to produce portable and efficient neural networks which can be well applied on edge devices for computer vision tasks. However, almost all top-performing knowledge distillation methods need to…
Recent advancements in camera-based 3D object detection have introduced cross-modal knowledge distillation to bridge the performance gap with LiDAR 3D detectors, leveraging the precise geometric information in LiDAR point clouds. However,…
Model compression and knowledge distillation have been successfully applied for cross-architecture and cross-domain transfer learning. However, a key requirement is that training examples are in correspondence across the domains. We show…
Current weakly supervised object localization and segmentation rely on class-discriminative visualization techniques to generate pseudo-labels for pixel-level training. Such visualization methods, including class activation mapping (CAM)…