A Closer Look at Prototype Classifier for Few-shot Image Classification

• URL: http://arxiv.org/abs/2110.05076v3
• Date: Thu, 14 Oct 2021 01:58:38 GMT
• Title: A Closer Look at Prototype Classifier for Few-shot Image Classification
• Authors: Mingcheng Hou and Issei Sato
• Abstract summary: We show that a prototype classifier works equally well without fine-tuning and meta-learning. We derive a novel generalization bound for the prototypical network and show that focusing on the variance of the norm of a feature vector can improve performance.
• Score: 28.821731837776593
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: The prototypical network is a prototype classifier based on meta-learning and is widely used for few-shot learning because it classifies unseen examples by constructing class-specific prototypes without adjusting hyper-parameters during meta-testing. Interestingly, recent research has attracted a lot of attention, showing that a linear classifier with fine-tuning, which does not use a meta-learning algorithm, performs comparably with the prototypical network. However, fine-tuning requires additional hyper-parameters when adapting a model to a new environment. In addition, although the purpose of few-shot learning is to enable the model to quickly adapt to a new environment, fine-tuning needs to be applied every time a new class appears, making fast adaptation difficult. In this paper, we analyze how a prototype classifier works equally well without fine-tuning and meta-learning. We experimentally found that directly using the feature vector extracted using standard pre-trained models to construct a prototype classifier in meta-testing does not perform as well as the prototypical network and linear classifiers with fine-tuning and feature vectors of pre-trained models. Thus, we derive a novel generalization bound for the prototypical network and show that focusing on the variance of the norm of a feature vector can improve performance. We experimentally investigated several normalization methods for minimizing the variance of the norm and found that the same performance can be obtained by using the L2 normalization and embedding space transformation without fine-tuning or meta-learning.

Related papers

• Test-Time Model Adaptation with Only Forward Passes [68.11784295706995]
  Test-time adaptation has proven effective in adapting a given trained model to unseen test samples with potential distribution shifts. We propose a test-time Forward-Optimization Adaptation (FOA) method. FOA runs on quantized 8-bit ViT, outperforms gradient-based TENT on full-precision 32-bit ViT, and achieves an up to 24-fold memory reduction on ImageNet-C.
  arXiv  Detail & Related papers  (2024-04-02T05:34:33Z)
• RanPAC: Random Projections and Pre-trained Models for Continual Learning [59.07316955610658]
  Continual learning (CL) aims to learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. We propose a concise and effective approach for CL with pre-trained models.
  arXiv  Detail & Related papers  (2023-07-05T12:49:02Z)
• Learning Prototype Classifiers for Long-Tailed Recognition [18.36167187657728]
  We show that learning prototype classifiers addresses the biased softmax problem in long-tailed recognition. We propose to jointly learn prototypes by using distances to prototypes in representation space as the logit scores for classification. Our analysis shows that prototypes learned by Prototype classifiers are better separated than empirical centroids.
  arXiv  Detail & Related papers  (2023-02-01T15:02:58Z)
• Meta-learning Pathologies from Radiology Reports using Variance Aware Prototypical Networks [3.464871689508835]
  We propose a simple extension of the Prototypical Networks for few-shot text classification. Our main idea is to replace the class prototypes by Gaussians and introduce a regularization term that encourages the examples to be clustered near the appropriate class centroids.
  arXiv  Detail & Related papers  (2022-10-22T05:22:29Z)
• Lightweight Conditional Model Extrapolation for Streaming Data under Class-Prior Shift [27.806085423595334]
  We introduce LIMES, a new method for learning with non-stationary streaming data. We learn a single set of model parameters from which a specific classifier for any specific data distribution is derived. Experiments on a set of exemplary tasks using Twitter data show that LIMES achieves higher accuracy than alternative approaches.
  arXiv  Detail & Related papers  (2022-06-10T15:19:52Z)
• Rethinking Semantic Segmentation: A Prototype View [126.59244185849838]
  We present a nonparametric semantic segmentation model based on non-learnable prototypes. Our framework yields compelling results over several datasets. We expect this work will provoke a rethink of the current de facto semantic segmentation model design.
  arXiv  Detail & Related papers  (2022-03-28T21:15:32Z)
• Dual Prototypical Contrastive Learning for Few-shot Semantic Segmentation [55.339405417090084]
  We propose a dual prototypical contrastive learning approach tailored to the few-shot semantic segmentation (FSS) task. The main idea is to encourage the prototypes more discriminative by increasing inter-class distance while reducing intra-class distance in prototype feature space. We demonstrate that the proposed dual contrastive learning approach outperforms state-of-the-art FSS methods on PASCAL-5i and COCO-20i datasets.
  arXiv  Detail & Related papers  (2021-11-09T08:14:50Z)
• Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer [112.95747173442754]
  A few-shot semantic segmentation model is typically composed of a CNN encoder, a CNN decoder and a simple classifier. Most existing methods meta-learn all three model components for fast adaptation to a new class. In this work we propose to simplify the meta-learning task by focusing solely on the simplest component, the classifier.
  arXiv  Detail & Related papers  (2021-08-06T10:20:08Z)
• Optimal 1-NN Prototypes for Pathological Geometries [13.70633147306388]
  Using prototype methods to reduce the size of training datasets can drastically reduce the computational cost of classification. We show that it is difficult to find the optimal prototypes for a given dataset, and algorithms are used instead. We propose an algorithm for finding nearly-optimal classifier prototypes in this setting, and use it to empirically validate the theoretical results.
  arXiv  Detail & Related papers  (2020-10-31T10:15:08Z)
• Understanding Classifier Mistakes with Generative Models [88.20470690631372]
  Deep neural networks are effective on supervised learning tasks, but have been shown to be brittle. In this paper, we leverage generative models to identify and characterize instances where classifiers fail to generalize. Our approach is agnostic to class labels from the training set which makes it applicable to models trained in a semi-supervised way.
  arXiv  Detail & Related papers  (2020-10-05T22:13:21Z)
• Prototype Completion with Primitive Knowledge for Few-Shot Learning [20.449056536438658]
  Few-shot learning is a challenging task, which aims to learn a classifier for novel classes with few examples. Pre-training based meta-learning methods effectively tackle the problem by pre-training a feature extractor and then fine-tuning it through the nearest centroid based meta-learning. We propose a novel prototype completion based meta-learning framework.
  arXiv  Detail & Related papers  (2020-09-10T16:09:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.