paper-with-me

홈 › Papers

NICE: Neurogenesis Inspired Contextual Encoding for Replay-free Class Incremental Learning

2024-01-01 · CVPR 2024 1 · Mustafa Burak Gurbuz, Jean Michael Moorman, Constantine Dovrolis

Deep neural networks (DNNs) struggle to learn in dynamic settings because they mainly rely on static datasets. Continual learning (CL) aims to overcome this limitation by enabling DNNs to incrementally accumulate knowledge. A widely adopted scenario in CL is class-incremental learning (CIL) where DNNs are required to sequentially learn more classes. Among the various strategies in CL replay methods which revisit previous classes stand out as the only effective ones in CIL. Other strategies such as architectural modifications to segregate information across weights and protect them from change are ineffective in CIL. This is because they need additional information during testing to select the correct network parts to use. In this paper we propose NICE Neurogenesis Inspired Contextual Encoding a replay-free architectural method inspired by adult neurogenesis in the hippocampus. NICE groups neurons in the DNN based on different maturation stages and infers which neurons to use during testing without any additional signal. Through extensive experiments across 6 datasets and 3 architectures we show that NICE performs on par with or often outperforms replay methods. We also make the case that neurons exhibit highly distinctive activation patterns for the classes in which they specialize enabling us to determine when they should be used. The code is available at https://github.com/BurakGurbuz97/NICE.

📄 PDF Abstract BibTeX

Code (1)

burakgurbuz97/nice 공식 구현 pytorch

Tasks

class-incremental learningClass Incremental LearningContinual LearningHippocampusIncremental Learning

Methods 이 논문이 사용한 방법론

Affine Coupling 설명 없음
Normalizing Flows Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying…
NICE NICE, or Non-Linear Independent Components Estimation is a framework for modeling complex high-dimensional densities. It is based on the idea that a good representation is…

Similar Papers 제목 키워드 기반

EvenNICER-SLAM: Event-based Neural Implicit Encoding SLAM

2024-10-04 · Shi Chen, Danda Pani Paudel, Luc van Gool

The advancement of dense visual simultaneous localization and mapping (SLAM) has been greatly facilitated by the emergence of neural implicit representations. Neural implicit encoding SLAM, a typical example of which is …

Simultaneous Localization and Mapping

Neurogenesis Deep Learning

2016-12-12 · Timothy J. Draelos, Nadine E. Miner, Christopher C. Lamb, Jonathan A. Cox 외

Neural machine learning methods, such as deep neural networks (DNN), have achieved remarkable success in a number of complex data processing tasks. These methods have arguably had their strongest impact on tasks such as …

BIG-bench Machine LearningDeep LearningHippocampus

Neuroplasticity in Artificial Intelligence -- An Overview and Inspirations on Drop In & Out Learning

2025-03-27 · Yupei Li, Manuel Milling, Björn W. Schuller

Artificial Intelligence (AI) has achieved new levels of performance and spread in public usage with the rise of deep neural networks (DNNs). Initially inspired by human neurons and their connections, NNs have become the …

When, where, and how to add new neurons to ANNs

2022-02-17 · Kaitlin Maile, Emmanuel Rachelson, Hervé Luga, Dennis G. Wilson

Neurogenesis in ANNs is an understudied and difficult problem, even compared to other forms of structural learning like pruning. By decomposing it into triggers and initializations, we introduce a framework for studying …

Neurogenesis Dynamics-inspired Spiking Neural Network Training Acceleration

2023-04-24 · Shaoyi Huang, Haowen Fang, Kaleel Mahmood, Bowen Lei 외

Biologically inspired Spiking Neural Networks (SNNs) have attracted significant attention for their ability to provide extremely energy-efficient machine intelligence through event-driven operation and sparse activities.…