Shot in the Dark: Few-Shot Learning with No Base-Class Labels
- URL: http://arxiv.org/abs/2010.02430v2
- Date: Fri, 23 Apr 2021 01:16:11 GMT
- Title: Shot in the Dark: Few-Shot Learning with No Base-Class Labels
- Authors: Zitian Chen, Subhransu Maji, Erik Learned-Miller
- Abstract summary: We show that off-the-shelf self-supervised learning outperforms transductive few-shot methods by 3.9% for 5-shot accuracy on miniImageNet.
This motivates us to examine more carefully the role of features learned through self-supervision in few-shot learning.
- Score: 32.96824710484196
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Few-shot learning aims to build classifiers for new classes from a small
number of labeled examples and is commonly facilitated by access to examples
from a distinct set of 'base classes'. The difference in data distribution
between the test set (novel classes) and the base classes used to learn an
inductive bias often results in poor generalization on the novel classes. To
alleviate problems caused by the distribution shift, previous research has
explored the use of unlabeled examples from the novel classes, in addition to
labeled examples of the base classes, which is known as the transductive
setting. In this work, we show that, surprisingly, off-the-shelf
self-supervised learning outperforms transductive few-shot methods by 3.9% for
5-shot accuracy on miniImageNet without using any base class labels. This
motivates us to examine more carefully the role of features learned through
self-supervision in few-shot learning. Comprehensive experiments are conducted
to compare the transferability, robustness, efficiency, and the complementarity
of supervised and self-supervised features.
Related papers
- Few-shot Classification via Ensemble Learning with Multi-Order
Statistics [9.145742362513932]
We show that leveraging ensemble learning on the base classes can correspondingly reduce the true error in the novel classes.
A novel method named Ensemble Learning with Multi-Order Statistics (ELMOS) is proposed in this paper.
We show that our method can produce a state-of-the-art performance on multiple few-shot classification benchmark datasets.
arXiv Detail & Related papers (2023-04-30T11:41:01Z) - Realistic Evaluation of Transductive Few-Shot Learning [41.06192162435249]
Transductive inference is widely used in few-shot learning.
We study the effect of arbitrary class distributions within the query sets of few-shot tasks at inference.
We evaluate experimentally state-of-the-art transductive methods over 3 widely used data sets.
arXiv Detail & Related papers (2022-04-24T03:35:06Z) - On the Importance of Distractors for Few-Shot Classification [13.486661391097387]
Few-shot classification aims at classifying categories of a novel task by learning from just a few (typically, 1 to 5) labelled examples.
An effective approach to few-shot classification involves a prior model trained on a large-sample base domain, which is then finetuned over the novel few-shot task to yield generalizable representations.
We propose a new finetuning approach based on contrastive learning that reuses unlabelled examples from the base domain in the form of distractors.
arXiv Detail & Related papers (2021-09-20T23:35:56Z) - Generalized and Incremental Few-Shot Learning by Explicit Learning and
Calibration without Forgetting [86.56447683502951]
We propose a three-stage framework that allows to explicitly and effectively address these challenges.
We evaluate the proposed framework on four challenging benchmark datasets for image and video few-shot classification.
arXiv Detail & Related papers (2021-08-18T14:21:43Z) - Few-Shot Learning with Part Discovery and Augmentation from Unlabeled
Images [79.34600869202373]
We show that inductive bias can be learned from a flat collection of unlabeled images, and instantiated as transferable representations among seen and unseen classes.
Specifically, we propose a novel part-based self-supervised representation learning scheme to learn transferable representations.
Our method yields impressive results, outperforming the previous best unsupervised methods by 7.74% and 9.24%.
arXiv Detail & Related papers (2021-05-25T12:22:11Z) - Are Fewer Labels Possible for Few-shot Learning? [81.89996465197392]
Few-shot learning is challenging due to its very limited data and labels.
Recent studies in big transfer (BiT) show that few-shot learning can greatly benefit from pretraining on large scale labeled dataset in a different domain.
We propose eigen-finetuning to enable fewer shot learning by leveraging the co-evolution of clustering and eigen-samples in the finetuning.
arXiv Detail & Related papers (2020-12-10T18:59:29Z) - Variational Feature Disentangling for Fine-Grained Few-Shot
Classification [30.350307891161865]
Fine-grained few-shot recognition often suffers from the problem of training data scarcity for novel categories.
In this paper, we focus one enlarging the intra-class variance of the unseen class to improve few-shot classification performance.
arXiv Detail & Related papers (2020-10-07T08:13:42Z) - Few-Shot Learning with Intra-Class Knowledge Transfer [100.87659529592223]
We consider the few-shot classification task with an unbalanced dataset.
Recent works have proposed to solve this task by augmenting the training data of the few-shot classes using generative models.
We propose to leverage the intra-class knowledge from the neighbor many-shot classes with the intuition that neighbor classes share similar statistical information.
arXiv Detail & Related papers (2020-08-22T18:15:38Z) - Cooperative Bi-path Metric for Few-shot Learning [50.98891758059389]
We make two contributions to investigate the few-shot classification problem.
We report a simple and effective baseline trained on base classes in the way of traditional supervised learning.
We propose a cooperative bi-path metric for classification, which leverages the correlations between base classes and novel classes to further improve the accuracy.
arXiv Detail & Related papers (2020-08-10T11:28:52Z) - Learning What Makes a Difference from Counterfactual Examples and
Gradient Supervision [57.14468881854616]
We propose an auxiliary training objective that improves the generalization capabilities of neural networks.
We use pairs of minimally-different examples with different labels, a.k.a counterfactual or contrasting examples, which provide a signal indicative of the underlying causal structure of the task.
Models trained with this technique demonstrate improved performance on out-of-distribution test sets.
arXiv Detail & Related papers (2020-04-20T02:47:49Z)
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.