Related papers: TIDo: Source-free Task Incremental Learning in Non…

In this study, the aim is to personalize inertial sensor data-based human activity recognition models using incremental learning. At first, the recognition is based on user-independent model. However, when personal streaming data becomes…

A robot operating in unstructured environments must be able to discriminate between different grasping styles depending on the prospective manipulation task. Having a system that allows learning from remote non-expert demonstrations can…

Deep learning models in recommender systems are usually trained in the batch mode, namely iteratively trained on a fixed-size window of training data. Such batch mode training of deep learning models suffers from low training efficiency,…

Despite rapid advances in continual learning, a large body of research is devoted to improving performance in the existing setups. While a handful of work do propose new continual learning setups, they still lack practicality in certain…

Most existing works in few-shot learning rely on meta-learning the network on a large base dataset which is typically from the same domain as the target dataset. We tackle the problem of cross-domain few-shot learning where there is a large…

While tasks could come with varying the number of instances and classes in realistic settings, the existing meta-learning approaches for few-shot classification assume that the number of instances per task and class is fixed. Due to such…

Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which…

Few-shot learning aims to classify unseen classes with a few training examples. While recent works have shown that standard mini-batch training with a carefully designed training strategy can improve generalization ability for unseen…

We present an information-theoretic framework to learn fixed-dimensional embeddings for tasks in reinforcement learning. We leverage the idea that two tasks are similar if observing an agent's performance on one task reduces our uncertainty…

Real-world tabular learning production scenarios typically involve evolving data streams, where data arrives continuously and its distribution may change over time. In such a setting, most studies in the literature regarding supervised…

In recent years, meta-reinforcement learning (meta-RL) algorithm has been proposed to improve sample efficiency in the field of decision-making and control, enabling agents to learn new knowledge from a small number of samples. However,…

Most recent test-time adaptation methods focus on only classification tasks, use specialized network architectures, destroy model calibration or rely on lightweight information from the source domain. To tackle these issues, this paper…

Instruction tuning, a new learning paradigm that fine-tunes pre-trained language models on tasks specified through instructions, has shown promising zero-shot performance on various natural language processing tasks. However, it has yet to…

In this paper, we propose a method for online domain-incremental learning of acoustic scene classification from a sequence of different locations. Simply training a deep learning model on a sequence of different locations leads to…

Class incremental learning aims to solve a problem that arises when continuously adding unseen class instances to an existing model This approach has been extensively studied in the context of image classification; however its applicability…

Recent works on instruction tuning (IT) have achieved great performance with zero-shot generalizability to unseen tasks. With additional context (e.g., task definition, examples) provided to models for fine-tuning, they achieved much higher…

In autonomous driving, 3D LiDAR plays a crucial role in understanding the vehicle's surroundings. However, the newly emerged, unannotated objects presents few-shot learning problem for semantic segmentation. This paper addresses the…

Generalization and adaptation of learned skills to novel situations is a core requirement for intelligent autonomous robots. Although contextual reinforcement learning provides a principled framework for learning and generalization of…

Multi-task learning is to improve the performance of the model by transferring and exploiting common knowledge among tasks. Existing MTL works mainly focus on the scenario where label sets among multiple tasks (MTs) are usually the same,…

The goal of lifelong learning is to continuously learn from non-stationary distributions, where the non-stationarity is typically imposed by a sequence of distinct tasks. Prior works have mostly considered idealistic settings, where the…