paper-with-me

홈 › Papers

A Distinct Unsupervised Reference Model From The Environment Helps Continual Learning

2023-01-11 · Seyyed AmirHossein Ameli Kalkhoran, Mohammadamin Banayeeanzade, Mahdi Samiei, Mahdieh Soleymani Baghshah

The existing continual learning methods are mainly focused on fully-supervised scenarios and are still not able to take advantage of unlabeled data available in the environment. Some recent works tried to investigate semi-supervised continual learning (SSCL) settings in which the unlabeled data are available, but it is only from the same distribution as the labeled data. This assumption is still not general enough for real-world applications and restricts the utilization of unsupervised data. In this work, we introduce Open-Set Semi-Supervised Continual Learning (OSSCL), a more realistic semi-supervised continual learning setting in which out-of-distribution (OoD) unlabeled samples in the environment are assumed to coexist with the in-distribution ones. Under this configuration, we present a model with two distinct parts: (i) the reference network captures general-purpose and task-agnostic knowledge in the environment by using a broad spectrum of unlabeled samples, (ii) the learner network is designed to learn task-specific representations by exploiting supervised samples. The reference model both provides a pivotal representation space and also segregates unlabeled data to exploit them more efficiently. By performing a diverse range of experiments, we show the superior performance of our model compared with other competitors and prove the effectiveness of each component of the proposed model.

📄 PDF Abstract BibTeX arXiv:2301.04506

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Similar Papers 제목 키워드 기반

CULT: Continual Unsupervised Learning with Typicality-Based Environment Detection

2022-07-17 · Oliver Daniels-Koch

We introduce CULT (Continual Unsupervised Representation Learning with Typicality-Based Environment Detection), a new algorithm for continual unsupervised learning with variational auto-encoders. CULT uses a simple typic…

Representation Learning

UnCLe: Unsupervised Continual Learning of Depth Completion

2024-10-23 · Suchisrit Gangopadhyay, Xien Chen, Michael Chu, Patrick Rim 외

We propose UnCLe, a standardized benchmark for Unsupervised Continual Learning of a multimodal depth estimation task: Depth completion aims to infer a dense depth map from a pair of synchronized RGB image and sparse dept…

Continual LearningDepth CompletionDepth Estimation

Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn

2025-05-31 · Hongyao Tang, Johan Obando-Ceron, Pablo Samuel Castro, Aaron Courville 외

Plasticity, or the ability of an agent to adapt to new tasks, environments, or distributions, is crucial for continual learning. In this paper, we study the loss of plasticity in deep continual RL from the lens of churn:…

Continual LearningOpenAI Gym

lpSpikeCon: Enabling Low-Precision Spiking Neural Network Processing for Efficient Unsupervised Continual Learning on Autonomous Agents

2022-05-24 · Rachmad Vidya Wicaksana Putra, Muhammad Shafique

Recent advances have shown that SNN-based systems can efficiently perform unsupervised continual learning due to their bio-plausible learning rule, e.g., Spike-Timing-Dependent Plasticity (STDP). Such learning capabiliti…

Continual Learning

EverAdapt: Continuous Adaptation for Dynamic Machine Fault Diagnosis Environments

2024-07-24 · Edward, Mohamed Ragab, Min Wu, Yuecong Xu 외

Unsupervised Domain Adaptation (UDA) has emerged as a key solution in data-driven fault diagnosis, addressing domain shift where models underperform in changing environments. However, under the realm of continually chang…

Domain AdaptationFault DiagnosisUnsupervised Domain Adaptation