paper-with-me

Papers

Class-Incremental Continual Learning into the eXtended DER-verse

2022-01-03 · Matteo Boschini, Lorenzo Bonicelli, Pietro Buzzega, Angelo Porrello, Simone Calderara

The staple of human intelligence is the capability of acquiring knowledge in a continuous fashion. In stark contrast, Deep Networks forget catastrophically and, for this reason, the sub-field of Class-Incremental Continual Learning fosters methods that learn a sequence of tasks incrementally, blending sequentially-gained knowledge into a comprehensive prediction. This work aims at assessing and overcoming the pitfalls of our previous proposal Dark Experience Replay (DER), a simple and effective approach that combines rehearsal and Knowledge Distillation. Inspired by the way our minds constantly rewrite past recollections and set expectations for the future, we endow our model with the abilities to i) revise its replay memory to welcome novel information regarding past data ii) pave the way for learning yet unseen classes. We show that the application of these strategies leads to remarkable improvements; indeed, the resulting method - termed eXtended-DER (X-DER) - outperforms the state of the art on both standard benchmarks (such as CIFAR-100 and miniImagenet) and a novel one here introduced. To gain a better understanding, we further provide extensive ablation studies that corroborate and extend the findings of our previous research (e.g. the value of Knowledge Distillation and flatter minima in continual learning setups).

📄 PDF Abstract BibTeX arXiv:2201.00766

Code (1)

aimagelab/mammoth 공식 구현 pytorch

Tasks

Continual LearningKnowledge Distillation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…
Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…

Similar Papers 제목 키워드 기반

iNeMo: Incremental Neural Mesh Models for Robust Class-Incremental Learning

2024-07-12 · Tom Fischer, Yaoyao Liu, Artur Jesslen, Noor Ahmed 외

Different from human nature, it is still common practice today for vision tasks to train deep learning models only initially and on fixed datasets. A variety of approaches have recently addressed handling continual data …

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning+1

In-context Continual Learning Assisted by an External Continual Learner

2024-12-20 · Saleh Momeni, Sahisnu Mazumder, Zixuan Ke, Bing Liu

Existing continual learning (CL) methods mainly rely on fine-tuning or adapting large language models (LLMs). They still suffer from catastrophic forgetting (CF). Little work has been done to exploit in-context learning …

Continual LearningIn-Context Learning

ReConText3D: Replay-based Continual Text-to-3D Generation

2026-04-15 · Muhammad Ahmed Ullah Khan, Muhammad Haris Bin Amir, Didier Stricker, Muhammad Zeshan Afzal arxiv

Continual learning enables models to acquire new knowledge over time while retaining previously learned capabilities. However, its application to text-to-3D generation remains unexplored. We present ReConText3D, the firs…

Continual Learning3D Generation

Tangent Model Composition for Ensembling and Continual Fine-tuning

2023-07-16 · ICCV 2023 1 · Tian Yu Liu, Stefano Soatto

Tangent Model Composition (TMC) is a method to combine component models independently fine-tuned around a pre-trained point. Component models are tangent vectors to the pre-trained model that can be added, scaled, or sub…

Incremental Learning

Continual Diffusion with STAMINA: STack-And-Mask INcremental Adapters

2023-11-30 · James Seale Smith, Yen-Chang Hsu, Zsolt Kira, Yilin Shen 외

Recent work has demonstrated a remarkable ability to customize text-to-image diffusion models to multiple, fine-grained concepts in a sequential (i.e., continual) manner while only providing a few example images for each…

Continual LearningHard Attentionimage-classificationImage Classification