Related papers: HyperFlow: Gradient-Free Emulation of Few-Shot Fin…
With the growing attention on learning-to-learn new tasks using only a few examples, meta-learning has been widely used in numerous problems such as few-shot classification, reinforcement learning, and domain generalization. However,…
We propose a method that can perform one-class classification given only a small number of examples from the target class and none from the others. We formulate the learning of meaningful features for one-class classification as a…
Continual Learning (CL) aims to learn from a non-stationary data stream where the underlying distribution changes over time. While recent advances have produced efficient memory-free methods in the offline CL (offCL) setting, where tasks…
Prompt tuning is a parameter-efficient method, which learns soft prompts and conditions frozen language models to perform specific downstream tasks. Though effective, prompt tuning under few-shot settings on the one hand heavily relies on a…
While few-shot learning as a transfer learning paradigm has gained significant traction for scenarios with limited data, it has primarily been explored in the context of building unimodal and unilingual models. Furthermore, a significant…
Convolutional Neural Networks (CNN) have been found to have great potential in optical flow problems thanks to an abundance of data available for training a deep network. The displacement estimation step in UltraSound Elastography (USE) can…
Few-shot Learning aims to learn and distinguish new categories with a very limited number of available images, presenting a significant challenge in the realm of deep learning. Recent researchers have sought to leverage the additional…
We propose a fast second-order method that can be used as a drop-in replacement for current deep learning solvers. Compared to stochastic gradient descent (SGD), it only requires two additional forward-mode automatic differentiation…
Gradient-based meta-learning and hyperparameter optimization have seen significant progress recently, enabling practical end-to-end training of neural networks together with many hyperparameters. Nevertheless, existing approaches are…
Few-shot segmentation (FSS) expects models trained on base classes to work on novel classes with the help of a few support images. However, when there exists a domain gap between the base and novel classes, the state-of-the-art FSS methods…
With the incorporation of the UNet architecture, diffusion probabilistic models have become a dominant force in image generation tasks. One key design in UNet is the skip connections between the encoder and decoder blocks. Although skip…
Learning quickly from very few labeled samples is a fundamental attribute that separates machines and humans in the era of deep representation learning. Unsupervised few-shot learning (U-FSL) aspires to bridge this gap by discarding the…
We introduce meta-learning algorithms that perform zero-shot weight-space adaptation of neural network models to unseen tasks. Our methods repurpose the popular generative image synthesis techniques of natural language guidance and…
Gradient-based optimization methods are commonly used to identify local optima in high-dimensional spaces. When derivatives cannot be evaluated directly, stochastic estimators can provide approximate gradients. However, these estimators'…
As deep learning models and datasets rapidly scale up, network training is extremely time-consuming and resource-costly. Instead of training on the entire dataset, learning with a small synthetic dataset becomes an efficient solution.…
Gradient-based optimization is now ubiquitous across graphics, but unfortunately can not be applied to problems with undefined or zero gradients. To circumvent this issue, the loss function can be manually replaced by a ``surrogate'' that…
We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification,…
It is well known that we need to choose the hyper-parameters in Momentum, AdaGrad, AdaDelta, and other alternative stochastic optimizers. While in many cases, the hyper-parameters are tuned tediously based on experience becoming more of an…
In scientific machine learning, regression networks have been recently applied to approximate solution maps (e.g., potential-ground state map of Schr\"odinger equation). In this paper, we aim to reduce the generalization error without…
Many real-world optimization problems contain parameters that are unknown before deployment time, either due to stochasticity or to lack of information (e.g., demand or travel times in delivery problems). A common strategy in such cases is…