paper-with-me

Papers

Better Generalized Few-Shot Learning Even Without Base Data

2022-11-29 · Seong-Woong Kim, Dong-Wan Choi

This paper introduces and studies zero-base generalized few-shot learning (zero-base GFSL), which is an extreme yet practical version of few-shot learning problem. Motivated by the cases where base data is not available due to privacy or ethical issues, the goal of zero-base GFSL is to newly incorporate the knowledge of few samples of novel classes into a pretrained model without any samples of base classes. According to our analysis, we discover the fact that both mean and variance of the weight distribution of novel classes are not properly established, compared to those of base classes. The existing GFSL methods attempt to make the weight norms balanced, which we find helps only the variance part, but discard the importance of mean of weights particularly for novel classes, leading to the limited performance in the GFSL problem even with base data. In this paper, we overcome this limitation by proposing a simple yet effective normalization method that can effectively control both mean and variance of the weight distribution of novel classes without using any base samples and thereby achieve a satisfactory performance on both novel and base classes. Our experimental results somewhat surprisingly show that the proposed zero-base GFSL method that does not utilize any base samples even outperforms the existing GFSL methods that make the best use of base data. Our implementation is available at: https://github.com/bigdata-inha/Zero-Base-GFSL.

📄 PDF Abstract BibTeX arXiv:2211.16095

Code (1)

bigdata-inha/zero-base-gfsl 공식 구현 pytorch

Tasks

Few-Shot LearningGeneralized Few-Shot Learning

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

Generalized and Incremental Few-Shot Learning by Explicit Learning and Calibration without Forgetting

2021-08-18 · ICCV 2021 10 · Anna Kukleva, Hilde Kuehne, Bernt Schiele

Both generalized and incremental few-shot learning have to deal with three major challenges: learning novel classes from only few samples per class, preventing catastrophic forgetting of base classes, and classifier cali…

Classifier calibrationFew-Shot Learning

Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognition

2020-06-16 · CVPR 2020 6 · Zongyan Han, Zhen-Yong Fu, Jian Yang

Zero-shot object recognition or zero-shot learning aims to transfer the object recognition ability among the semantically related categories, such as fine-grained animal or bird species. However, the images of different …

Generalized Zero-Shot LearningObjectObject RecognitionZero-Shot Learning

Toward a More Ethical Facial Age Estimation: A Generalized Zero-Shot Benchmark Without Training on Children's Data

2026-05-28 · Caio Petrucci, Leo Sampaio Ferraz Ribeiro, Sandra Avila arxiv

Age estimation from facial images typically relies on training data that includes images of minors, a practice that raises ethical, legal, and privacy concerns and that child-data governance frameworks explicitly advise …

Generalized Zero-Shot LearningAge Estimation

AVGZSLNet: Audio-Visual Generalized Zero-Shot Learning by Reconstructing Label Features from Multi-Modal Embeddings

2020-05-27 · Pratik Mazumder, Pravendra Singh, Kranti Kumar Parida, Vinay P. Namboodiri

In this paper, we propose a novel approach for generalized zero-shot learning in a multi-modal setting, where we have novel classes of audio/video during testing that are not seen during training. We use the semantic rel…

DecoderGeneralized Zero-Shot LearningGZSL Video ClassificationRetrieval+3

Generalized Adaptation for Few-Shot Learning

2019-11-25 · Liang Song, Jinlu Liu, Yongqiang Qin

Many Few-Shot Learning research works have two stages: pre-training base model and adapting to novel model. In this paper, we propose to use closed-form base learner, which constrains the adapting stage with pre-trained …

Few-Shot Image ClassificationFew-Shot Learning