Related papers: Style Curriculum Learning for Robust Medical Image…
The volume estimation of brain regions from MRI data is a key problem in many clinical applications, where the acquisition of data at high spatial resolution is desirable. While parallel MRI and constrained image reconstruction algorithms…
Image clustering is one of the crucial techniques in multimedia analytics and knowledge discovery. Recently, the Deep clustering method (DC), characterized by its ability to perform feature learning and cluster assignment jointly, surpasses…
Traditional domain generalization methods often rely on domain alignment to reduce inter-domain distribution differences and learn domain-invariant representations. However, domain shifts are inherently difficult to eliminate, which limits…
Achieving robustness against adversarial input perturbation is an important and intriguing problem in machine learning. In the area of semantic image segmentation, a number of adversarial training approaches have been proposed as a defense…
Remote sensing semantic segmentation must address both what the ground objects are within an image and where they are located. Consequently, segmentation models must ensure not only the semantic correctness of large-scale patches…
Semi-supervised learning has made significant strides in the medical domain since it alleviates the heavy burden of collecting abundant pixel-wise annotated data for semantic segmentation tasks. Existing semi-supervised approaches enhance…
In medical image segmentation tasks, the scarcity of labeled training data poses a significant challenge when training deep neural networks. When using U-Net-style architectures, it is common practice to address this problem by pretraining…
The rapid development of deep learning has made a great progress in image segmentation, one of the fundamental tasks of computer vision. However, the current segmentation algorithms mostly rely on the availability of pixel-level…
With the development of deep convolutional neural networks, medical image segmentation has achieved a series of breakthroughs in recent years. However, the high-performance convolutional neural networks always mean numerous parameters and…
Despite the recent success of deep learning methods at achieving new state-of-the-art accuracy for medical image segmentation, some major limitations are still restricting their deployment into clinics. One major limitation of deep…
Masked Image Modeling (MIM) has emerged as a powerful self-supervised learning paradigm for visual representation learning, enabling models to acquire rich visual representations by predicting masked portions of images from their visible…
We share our recent findings in an attempt to train a universal segmentation network for various cell types and imaging modalities. Our method was built on the generalized U-Net architecture, which allows the evaluation of each component…
Supervised deep learning for semantic segmentation has achieved excellent results in accurately identifying anatomical and pathological structures in medical images. However, it often requires large annotated training datasets, which limits…
Segmentation uncertainty models predict a distribution over plausible segmentations for a given input, which they learn from the annotator variation in the training set. However, in practice these annotations can differ systematically in…
The reliability of segmentation models in the medical domain depends on the model's robustness to perturbations in the input space. Robustness is a particular challenge in medical imaging exhibiting various sources of image noise,…
Semantic segmentation is a fundamental computer vision task with a vast number of applications. State of the art methods increasingly rely on deep learning models, known to incorrectly estimate uncertainty and being overconfident in…
To segment 4K or 6K ultra high-resolution images needs extra computation consideration in image segmentation. Common strategies, such as down-sampling, patch cropping, and cascade model, cannot address well the balance issue between…
Standard supervised learning breaks down under data distribution shift. However, the principle of independent causal mechanisms (ICM, Peters et al. (2017)) can turn this weakness into an opportunity: one can take advantage of distribution…
The visual models pretrained on large-scale benchmarks encode general knowledge and prove effective in building more powerful representations for downstream tasks. Most existing approaches follow the fine-tuning paradigm, either by…
The performance of machine learning models can significantly degrade under distribution shifts of the data. We propose a new method for classification which can improve robustness to distribution shifts, by combining expert knowledge about…