相关论文: BOIL: Towards Representation Change for Few-shot L…

Few-shot class-incremental learning (FSCIL) aims to incrementally recognize new classes using a few samples while maintaining the performance on previously learned classes. One of the effective methods to solve this challenge is to…

Data driven control of a continuum manipulator requires a lot of data for training but generating sufficient amount of real time data is not cost efficient. Random actuation of the manipulator can also be unsafe sometimes. Meta learning has…

Multi-Class Incremental Learning (MCIL) aims to learn new concepts by incrementally updating a model trained on previous concepts. However, there is an inherent trade-off to effectively learning new concepts without catastrophic forgetting…

Despite its popularity, several recent works question the effectiveness of MAML when test tasks are different from training tasks, thus suggesting various task-conditioned methodology to improve the initialization. Instead of searching for…

Multi-modal learning has emerged as a key technique for improving performance across domains such as autonomous driving, robotics, and reasoning. However, in certain scenarios, particularly in resource-constrained environments, some…

Despite the recent success of speech separation models, they fail to separate sources properly while facing different sets of people or noisy environments. To tackle this problem, we proposed to apply meta-learning to the speech separation…

Few-shot learning (FSL) is a central problem in meta-learning, where learners must efficiently learn from few labeled examples. Within FSL, feature pre-training has recently become an increasingly popular strategy to significantly improve…

The Continual Learning (CL) problem involves performing well on a sequence of tasks under limited compute. Current algorithms in the domain are either slow, offline or sensitive to hyper-parameters. La-MAML, an optimization-based…

Image-point class incremental learning helps the 3D-points-vision robots continually learn category knowledge from 2D images, improving their perceptual capability in dynamic environments. However, some incremental learning methods address…

The predictive accuracy of Machine Learning (ML) models of molecular properties depends on the choice of the molecular representation. Based on the postulates of quantum mechanics, we introduce a hierarchy of representations which meet…

One of the main challenges in imitation learning is determining what action an agent should take when outside the state distribution of the demonstrations. Inverse reinforcement learning (IRL) can enable generalization to new states by…

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,…

Current pre-trained vison-language models (PVLMs) achieve excellent performance on a range of multi-modal datasets. Recent work has aimed at building multilingual models, and a range of novel multilingual multi-modal datasets have been…

This paper discusses an Enhanced Model-Agnostic Meta-Learning (E-MAML) algorithm that generates fast convergence of the policy function from a small number of training examples when applied to new learning tasks. Built on top of…

Meta-learning aims at learning quickly on novel tasks with limited data by transferring generic experience learned from previous tasks. Naturally, few-shot learning has been one of the most popular applications for meta-learning. However,…

Most meta-learning approaches assume the existence of a very large set of labeled data available for episodic meta-learning of base knowledge. This contrasts with the more realistic continual learning paradigm in which data arrives…

Imitation learning has been a trend recently, yet training a generalist agent across multiple tasks still requires large-scale expert demonstrations, which are costly and labor-intensive to collect. To address the challenge of limited…

Meta-learning for few-shot learning entails acquiring a prior over previous tasks and experiences, such that new tasks be learned from small amounts of data. However, a critical challenge in few-shot learning is task ambiguity: even when a…

Software refactoring is the process of changing the structure of software without any alteration in its behavior and functionality. Presuming it is carried out in appropriate opportunities, refactoring enhances software quality…

Aiming to incrementally learn new classes with only few samples while preserving the knowledge of base (old) classes, few-shot class-incremental learning (FSCIL) faces several challenges, such as overfitting and catastrophic forgetting.…