Curriculum-Based Meta-learning
Ji Zhang,Jingkuan Song,Yazhou Yao,Lianli Gao +3 more
- 17 Oct 2021
- pp 1838-1846
TL;DR: Zhang et al. as discussed by the authors proposed a curriculum-based meta-learning method to train the meta-learner using tasks from easy to hard, which can facilitate the quick acquisition of task-specific knowledge of the target task with few samples.
read more
Abstract: Meta-learning offers an effective solution to learn new concepts with scarce supervision through an episodic training scheme: a series of target-like tasks sampled from base classes are sequentially fed into a meta-learner to extract common knowledge across tasks, which can facilitate the quick acquisition of task-specific knowledge of the target task with few samples. Despite its noticeable improvements, the episodic training strategy samples tasks randomly and uniformly, without considering their hardness and quality, which may not progressively improve the meta-leaner's generalization ability. In this paper, we present a Curriculum-Based Meta-learning (CubMeta) method to train the meta-learner using tasks from easy to hard. Specifically, the framework of CubMeta is in a progressive way, and in each step, we design a module named BrotherNet to establish harder tasks and an effective learning scheme for obtaining an ensemble of stronger meta-learners. In this way, the meta-learner's generalization ability can be progressively improved, and better performance can be obtained even with fewer training tasks. We evaluate our method for few-shot classification on two benchmarks - mini-ImageNet and tiered-ImageNet, where it achieves consistent performance improvements on various meta-learning paradigms.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Progressive Meta-Learning With Curriculum
TL;DR: Zhang et al. as mentioned in this paper proposed a curriculum-based meta-learner to measure the hardness of tasks adaptively according to what the model has already learned, which can facilitate the quick acquisition of task specific knowledge of the target task with few samples.
51
Progressive Meta-Learning With Curriculum
Ji Zhang,Jingkuan Song,Lianli Gao,Ye Liu,Heng Tao Shen +4 more
- 01 Sep 2022
TL;DR: This paper develops a Curriculum-Based Meta-learning method based on a predefined curriculum, and proposes an end-to-end Self-Paced Meta- learning (SepMeta) method, which is effectively integrated as a regularization term into the objective so that the meta-learner can measure the hardness of tasks adaptively, according to what the model has already learned.
50
Deep Evidential Learning with Noisy Correspondence for Cross-modal Retrieval
10 Oct 2022
TL;DR: Yang et al. as discussed by the authors proposed a generalized Deep Evidential Cross-modal Learning framework (DECL), which integrates a novel Cross-Modal Evidential Learning paradigm (CEL) and a Robust Dynamic Hinge loss (RDH) with positive and negative learning.
43
Meta Distribution Alignment for Generalizable Person Re-Identification
01 Jun 2022
TL;DR: In this article , the authors propose a meta distribution alignment (MDA) method to enable source and target domains to share similar distribution in a test-time training fashion, which can facilitate generalization and support fast adaption.
34
Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack
01 Jun 2022
TL;DR: In this article , Lu et al. proposed a parameter-free adaptive auto attack (A 3 ) evaluation method which addresses the efficiency and reliability in a test-time training fashion.
References
Deep Residual Learning for Image Recognition
Kaiming He,Xiangyu Zhang,Shaoqing Ren,Jian Sun +3 more
- 27 Jun 2016
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
•Posted Content
Deep Residual Learning for Image Recognition
TL;DR: This work presents a residual learning framework to ease the training of networks that are substantially deeper than those used previously, and provides comprehensive empirical evidence showing that these residual networks are easier to optimize, and can gain accuracy from considerably increased depth.
117.9K
ImageNet Large Scale Visual Recognition Challenge
Olga Russakovsky,Jia Deng,Hao Su,Jonathan Krause,Sanjeev Satheesh,Sean Ma,Zhiheng Huang,Andrej Karpathy,Aditya Khosla,Michael S. Bernstein,Alexander C. Berg,Li Fei-Fei +11 more
TL;DR: The ImageNet Large Scale Visual Recognition Challenge (ILSVRC) as mentioned in this paper is a benchmark in object category classification and detection on hundreds of object categories and millions of images, which has been run annually from 2010 to present, attracting participation from more than fifty institutions.
•Proceedings Article
Model-agnostic meta-learning for fast adaptation of deep networks
Chelsea Finn,Pieter Abbeel,Sergey Levine +2 more
- 06 Aug 2017
TL;DR: An algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification, regression, and reinforcement learning is proposed.
•Proceedings Article
Prototypical Networks for Few-shot Learning
Jake Snell,Kevin Swersky,Richard S. Zemel +2 more
- 15 Mar 2017
TL;DR: Prototypical Networks as discussed by the authors learn a metric space in which classification can be performed by computing distances to prototype representations of each class, and achieve state-of-the-art results on the CU-Birds dataset.