paper-with-me

홈 › Papers

Foundation Model-Powered 3D Few-Shot Class Incremental Learning via Training-free Adaptor

2024-10-11 · Sahar Ahmadi, Ali Cheraghian, Morteza Saberi, Md. Towsif Abir, Hamidreza Dastmalchi, Farookh Hussain, Shafin Rahman

Recent advances in deep learning for processing point clouds hold increased interest in Few-Shot Class Incremental Learning (FSCIL) for 3D computer vision. This paper introduces a new method to tackle the Few-Shot Continual Incremental Learning (FSCIL) problem in 3D point cloud environments. We leverage a foundational 3D model trained extensively on point cloud data. Drawing from recent improvements in foundation models, known for their ability to work well across different tasks, we propose a novel strategy that does not require additional training to adapt to new tasks. Our approach uses a dual cache system: first, it uses previous test samples based on how confident the model was in its predictions to prevent forgetting, and second, it includes a small number of new task samples to prevent overfitting. This dynamic adaptation ensures strong performance across different learning tasks without needing lots of fine-tuning. We tested our approach on datasets like ModelNet, ShapeNet, ScanObjectNN, and CO3D, showing that it outperforms other FSCIL methods and demonstrating its effectiveness and versatility. The code is available at \url{https://github.com/ahmadisahar/ACCV_FCIL3D}.

📄 PDF Abstract BibTeX arXiv:2410.09237

Code (1)

ahmadisahar/accv_fcil3d 공식 구현 pytorch

Tasks

class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental Learning

Similar Papers 제목 키워드 기반

Few-shot Tuning of Foundation Models for Class-incremental Learning

2024-05-26 · Shuvendu Roy, Elham Dolatabadi, Arash Afkanpour, Ali Etemad

For the first time, we explore few-shot tuning of vision foundation models for class-incremental learning. Unlike existing few-shot class incremental learning (FSCIL) methods, which train an encoder on a base session to …

class-incremental learningClass Incremental LearningContinual LearningFew-Shot Class-Incremental Learning+1

Knowledge Adaptation Network for Few-Shot Class-Incremental Learning

2024-09-18 · Ye Wang, Yaxiong Wang, Guoshuai Zhao, Xueming Qian

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 chal…

class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental Learning

A New Benchmark for Few-Shot Class-Incremental Learning: Redefining the Upper Bound

2025-03-13 · Shiwon Kim, Dongjun Hwang, Sungwon Woo, Rita Singh

Class-incremental learning (CIL) aims to continuously adapt to emerging classes while retaining knowledge of previously learned ones. Few-shot class-incremental learning (FSCIL) presents an even greater challenge which r…

class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental Learning

12 mJ per Class On-Device Online Few-Shot Class-Incremental Learning

2024-03-12 · Yoga Esa Wibowo, Cristian Cioflan, Thorir Mar Ingolfsson, Michael Hersche 외

Few-Shot Class-Incremental Learning (FSCIL) enables machine learning systems to expand their inference capabilities to new classes using only a few labeled examples, without forgetting the previously learned classes. Cla…

class-incremental learningClass Incremental LearningContinual LearningFew-Shot Class-Incremental Learning+2

Modular Embedding Recomposition for Incremental Learning

2025-08-22 · Aniello Panariello, Emanuele Frascaroli, Pietro Buzzega, Lorenzo Bonicelli 외 arxiv

The advent of pre-trained Vision-Language Models (VLMs) has significantly transformed Continual Learning (CL), mainly due to their zero-shot classification abilities. Such proficiency makes VLMs well-suited for real-worl…

Incremental LearningContinual Learning