Related papers: Parameter-Free Spectral Kernel Learning
This paper studies semi-supervised learning of semantic segmentation, which assumes that only a small portion of training images are labeled and the others remain unlabeled. The unlabeled images are usually assigned pseudo labels to be used…
In this paper, we present a new algorithm for semi-supervised representation learning. In this algorithm, we first find a vector representation for the labels of the data points based on their local positions in the space. Then, we map the…
Deep learning usually requires large amounts of labeled training data, but annotating data is costly and tedious. The framework of semi-supervised learning provides the means to use both labeled data and arbitrary amounts of unlabeled data…
Preference-based reinforcement learning (RL) has shown potential for teaching agents to perform the target tasks without a costly, pre-defined reward function by learning the reward with a supervisor's preference between the two agent…
While supervised learning has achieved remarkable success, obtaining large-scale labeled datasets in biomedical imaging is often impractical due to high costs and the time-consuming annotations required from radiologists. Semi-supervised…
Existing large-dimensional theory for spectral algorithms resolves either the optimally tuned point or the interpolation limit, but leaves the under-regularized regime unexplored. We study the learning curve and benign overfitting of…
Automated semantic segmentation of cell nuclei in microscopic images is crucial for disease diagnosis and tissue microenvironment analysis. Nonetheless, this task presents challenges due to the complexity and heterogeneity of cells. While…
There has been increased interest in devising learning techniques that combine unlabeled data with labeled data ? i.e. semi-supervised learning. However, to the best of our knowledge, no study has been performed across various techniques…
Recent work on curvilinear structure segmentation has mostly focused on backbone network design and loss engineering. The challenge of collecting labelled data, an expensive and labor intensive process, has been overlooked. While labelled…
Improving a semi-supervised image segmentation task has the option of adding more unlabelled images, labelling the unlabelled images or combining both, as neither image acquisition nor expert labelling can be considered trivial in most…
Quantum computing leverages quantum effects to build algorithms that are faster then their classical variants. In machine learning, for a given model architecture, the speed of training the model is typically determined by the size of the…
The problem of fully supervised classification is that it requires a tremendous amount of annotated data, however, in many datasets a large portion of data is unlabeled. To alleviate this problem semi-supervised learning (SSL) leverages the…
Retinal image registration, particularly for color fundus images, is a challenging yet essential task with diverse clinical applications. Existing registration methods for color fundus images typically rely on keypoints and descriptors for…
Deep-learning metrics have recently demonstrated extremely good performance to match image patches for stereo reconstruction. However, training such metrics requires large amount of labeled stereo images, which can be difficult or costly to…
For challenging machine learning problems such as zero-shot learning and fine-grained categorization, embedding learning is the machinery of choice because of its ability to learn generic notions of similarity, as opposed to class-specific…
The search for new high-performance organic semiconducting molecules is challenging due to the vastness of the chemical space, machine learning methods, particularly deep learning models like graph neural networks (GNNs), have shown…
The performance of supervised deep learning methods for medical image segmentation is often limited by the scarcity of labeled data. As a promising research direction, semi-supervised learning addresses this dilemma by leveraging unlabeled…
Neural networks have been successfully used as classification models yielding state-of-the-art results when trained on a large number of labeled samples. These models, however, are more difficult to train successfully for semi-supervised…
Despite significant advances, the performance of state-of-the-art continual learning approaches hinges on the unrealistic scenario of fully labeled data. In this paper, we tackle this challenge and propose an approach for continual…
Imposing an effective structural assumption on neural network weight matrices has been the major paradigm for designing Parameter-Efficient Fine-Tuning (PEFT) systems for adapting modern large pre-trained models to various downstream tasks.…