☆ 4.8 Article

Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2023)

Related references

Note: Only part of the references are listed.

Article Computer Science, Artificial Intelligence

Incremental Object Detection via Meta-Learning

K. J. Joseph et al.

Summary: In this study, a meta-learning approach is proposed to achieve incremental learning by learning how to reshape model gradients. Compared to existing methods, this approach can adapt to new tasks and performs well in various incremental learning scenarios.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

FOSTER: Feature Boosting and Compression for Class-Incremental Learning

Fu-Yun Wang et al.

Summary: The ability to learn new concepts continually is necessary in this ever-changing world. However, deep neural networks suffer from catastrophic forgetting when learning new categories. This study proposes a novel two-stage learning approach called FOSTER to address this problem and achieves state-of-the-art performance on multiple datasets.

COMPUTER VISION, ECCV 2022, PT XXV (2022)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Forward Compatible Few-Shot Class-Incremental Learning

Da-Wei Zhou et al.

Summary: In a dynamically changing world, novel classes frequently emerge, and machine learning models need to recognize both new and old classes. Few-shot class-incremental learning (FSCIL) becomes even more challenging when there is a scarcity of instances for new classes. This paper proposes ForwArd Compatible Training (FACT) to handle FSCIL by learning prospectively and reserving embedding space for future new classes. FACT efficiently incorporates new classes with forward compatibility and resists forgetting of old ones, demonstrating state-of-the-art performance.

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learning

Han-Jia Ye et al.

Summary: This study investigates the challenge of object recognition in the real-world, introducing a learning framework called Castle and its adaptive version, aCastle, that can effectively handle long-tailed data and classify various categories. Experimental results demonstrate that these two methods outperform previous GFSL algorithms and baselines.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Hierarchical Graph Attention Network for Few-shot Visual-Semantic Learning

Chengxiang Yin et al.

Summary: This paper investigates few-shot visual-semantic learning and presents the Hierarchical Graph ATtention network (HGAT), achieving superior performance in multi-modal scenarios.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

TRAR: Routing the Attention Spans in Transformer for Visual Question Answering

Yiyi Zhou et al.

Summary: This paper proposes an example-dependent routing scheme called TRAnsformer Routing (TRAR) to dynamically schedule global and local dependency modeling, achieving superior performance on VQA and REC tasks compared to standard Transformers and state-of-the-art methods through extensive experiments on benchmark datasets.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Learning Placeholders for Open-Set Recognition

Da-Wei Zhou et al.

Summary: Traditional classifiers in a closed-set setting may struggle with unknown categories, leading to overconfident predictions and the need for calibration when moving to an open-set environment. The proposed PRosER method tackles this issue by allocating placeholders for unknown classes, achieving effective open-set recognition and maintaining classification performance. Experimental results demonstrate the effectiveness of this approach on various datasets.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning

Kai Zhu et al.

Summary: The study introduces an incremental prototype learning scheme that enhances the expression ability of new classes through a random episode selection strategy and a self-promoted prototype refinement mechanism, achieving remarkable incremental performance.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021 (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Few-shot learning with adaptively initialized task optimizer: a practical meta-learning approach

Han-Jia Ye et al.

MACHINE LEARNING (2020)

Add to Collection

Article Computer Science, Theory & Methods

Generalizing from a Few Examples: A Survey on Few-shot Learning

Yaqing Wang et al.

ACM COMPUTING SURVEYS (2020)

Add to Collection

Proceedings Paper Computer Science, Information Systems

Condition Aware and Revise Transformer for Question Answering

Xinyan Zhao et al.

WEB CONFERENCE 2020: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW 2020) (2020)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

3FabRec: Fast Few-shot Face alignment by Reconstruction

Bjorn Browatzki et al.

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2020)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Incremental Learning Using Conditional Adversarial Networks

Ye Xiang et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Large Scale Incremental Learning

Yue Wu et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Add to Collection

Article Computer Science, Artificial Intelligence

Learning without Forgetting

Zhizhong Li et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2018)

Add to Collection

Article Multidisciplinary Sciences

Overcoming catastrophic forgetting in neural networks

James Kirkpatricka et al.

PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA (2017)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Few-Shot Object Recognition from Machine-Labeled Web Images

Zhongwen Xu et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Add to Collection

Article Computer Science, Theory & Methods

A Survey on Ensemble Learning for Data Stream Classification

Heitor Murilo Gomes et al.

ACM COMPUTING SURVEYS (2017)

Add to Collection

Editorial Material Computer Science, Information Systems

Learnware: on the future of machine learning

Zhi-Hua Zhou

FRONTIERS OF COMPUTER SCIENCE (2016)

Add to Collection

Article Computer Science, Artificial Intelligence

ImageNet Large Scale Visual Recognition Challenge

Olga Russakovsky et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2015)

Add to Collection

Article Computer Science, Artificial Intelligence

Robust Object Tracking with Online Multiple Instance Learning

Boris Babenko et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2011)

Add to Collection

Article Computer Science, Artificial Intelligence

Tracking Multiple Occluding People by Localizing on Multiple Scene Planes

Saad M. Khan et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2009)

Add to Collection

Review Computer Science, Artificial Intelligence

Face recognition from a single image per person: A survey

Xiaoyang Tan et al.

PATTERN RECOGNITION (2006)

Add to Collection

© Peeref 2019-2024. All rights reserved.