Related papers: Interventional Few-Shot Learning

Interventional Few-Shot Learning

URL: http://arxiv.org/abs/2009.13000v2
Date: Fri, 4 Dec 2020 06:51:09 GMT
Title: Interventional Few-Shot Learning
Authors: Zhongqi Yue and Hanwang Zhang and Qianru Sun and Xian-Sheng Hua
Abstract summary: We propose a novel Few-Shot Learning paradigm: Interventional Few-Shot Learning. Code is released at https://github.com/yue-zhongqi/ifsl.
Score: 88.31112565383457
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: We uncover an ever-overlooked deficiency in the prevailing Few-Shot Learning (FSL) methods: the pre-trained knowledge is indeed a confounder that limits the performance. This finding is rooted from our causal assumption: a Structural Causal Model (SCM) for the causalities among the pre-trained knowledge, sample features, and labels. Thanks to it, we propose a novel FSL paradigm: Interventional Few-Shot Learning (IFSL). Specifically, we develop three effective IFSL algorithmic implementations based on the backdoor adjustment, which is essentially a causal intervention towards the SCM of many-shot learning: the upper-bound of FSL in a causal view. It is worth noting that the contribution of IFSL is orthogonal to existing fine-tuning and meta-learning based FSL methods, hence IFSL can improve all of them, achieving a new 1-/5-shot state-of-the-art on \textit{mini}ImageNet, \textit{tiered}ImageNet, and cross-domain CUB. Code is released at https://github.com/yue-zhongqi/ifsl.

Related papers

Towards Understanding Why FixMatch Generalizes Better Than Supervised Learning [97.1805039692731]
Semi-supervised learning (SSL) has shown significant generalization advantages over supervised learning (SL) We present the first theoretical justification for the enhanced test accuracy observed in FixMatch-like SSL applied to deep neural networks (DNNs) We show that our analysis framework can be applied to other FixMatch-like SSL methods, e.g., FlexMatch, FreeMatch, Dash, and SoftMatch.
arXiv Detail & Related papers (2024-10-15T02:47:57Z)
Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning [4.137391543972184]
Semi-supervised learning (SSL) has witnessed remarkable progress, resulting in numerous method variations. In this paper, we present a novel SSL approach named FineSSL that significantly addresses this limitation by adapting pre-trained foundation models. We demonstrate that FineSSL sets a new state of the art for SSL on multiple benchmark datasets, reduces the training cost by over six times, and can seamlessly integrate various fine-tuning and modern SSL algorithms.
arXiv Detail & Related papers (2024-05-20T03:33:12Z)
Instance-based Max-margin for Practical Few-shot Recognition [32.26577845735846]
IbM2 is a novel instance-based max-margin method for few-shot learning. This paper shows that IbM2 almost always leads to improvements compared to its respective baseline methods.
arXiv Detail & Related papers (2023-05-27T04:55:13Z)
Constrained Few-Shot Learning: Human-Like Low Sample Complexity Learning and Non-Episodic Text Classification [11.35732215154172]
Few-shot learning is an emergent paradigm of learning that attempts to learn to reason with low sample complexity. We propose a method for CFSL leveraging Cat2Vec using a novel categorical contrastive loss inspired by cognitive theories.
arXiv Detail & Related papers (2022-08-17T06:05:41Z)
A Strong Baseline for Semi-Supervised Incremental Few-Shot Learning [54.617688468341704]
Few-shot learning aims to learn models that generalize to novel classes with limited training samples. We propose a novel paradigm containing two parts: (1) a well-designed meta-training algorithm for mitigating ambiguity between base and novel classes caused by unreliable pseudo labels and (2) a model adaptation mechanism to learn discriminative features for novel classes while preserving base knowledge using few labeled and all the unlabeled data.
arXiv Detail & Related papers (2021-10-21T13:25:52Z)
End-to-end Generative Zero-shot Learning via Few-shot Learning [76.9964261884635]
State-of-the-art approaches to Zero-Shot Learning (ZSL) train generative nets to synthesize examples conditioned on the provided metadata. We introduce an end-to-end generative ZSL framework that uses such an approach as a backbone and feeds its synthesized output to a Few-Shot Learning algorithm.
arXiv Detail & Related papers (2021-02-08T17:35:37Z)
TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classification [50.358839666165764]
We show that the Task-Adaptive Feature Sub-Space Learning (TAFSSL) can significantly boost the performance in Few-Shot Learning scenarios. Specifically, we show that on the challenging miniImageNet and tieredImageNet benchmarks, TAFSSL can improve the current state-of-the-art in both transductive and semi-supervised FSL settings by more than $5%$.
arXiv Detail & Related papers (2020-03-14T16:59:17Z)
AdarGCN: Adaptive Aggregation GCN for Few-Shot Learning [112.95742995816367]
We propose a new few-shot fewshot learning setting termed FSFSL. Under FSFSL, both the source and target classes have limited training samples. We also propose a graph convolutional network (GCN)-based label denoising (LDN) method to remove irrelevant images.
arXiv Detail & Related papers (2020-02-28T10:34:36Z)

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