Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data

07/28/2018
by   Yabin Zhang, et al.
0

Fine-grained visual categorization (FGVC) is challenging due in part to the fact that it is often difficult to acquire an enough number of training samples. To employ large models for FGVC without suffering from overfitting, existing methods usually adopt a strategy of pre-training the models using a rich set of auxiliary data, followed by fine-tuning on the target FGVC task. However, the objective of pre-training does not take the target task into account, and consequently such obtained models are suboptimal for fine-tuning. To address this issue, we propose in this paper a new deep FGVC model termed MetaFGNet. Training of MetaFGNet is based on a novel regularized meta-learning objective, which aims to guide the learning of network parameters so that they are optimal for adapting to the target FGVC task. Based on MetaFGNet, we also propose a simple yet effective scheme for selecting more useful samples from the auxiliary data. Experiments on benchmark FGVC datasets show the efficacy of our proposed method.

READ FULL TEXT
research
09/17/2020

Self-Supervised Meta-Learning for Few-Shot Natural Language Classification Tasks

Self-supervised pre-training of transformer models has revolutionized NL...
research
02/25/2022

MetaVA: Curriculum Meta-learning and Pre-fine-tuning of Deep Neural Networks for Detecting Ventricular Arrhythmias based on ECGs

Ventricular arrhythmias (VA) are the main causes of sudden cardiac death...
research
06/16/2018

Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learning

Transferring the knowledge learned from large scale datasets (e.g., Imag...
research
08/25/2021

Auxiliary Task Update Decomposition: The Good, The Bad and The Neutral

While deep learning has been very beneficial in data-rich settings, task...
research
07/29/2022

Fine-grained Retrieval Prompt Tuning

Fine-grained object retrieval aims to learn discriminative representatio...
research
06/20/2023

Multi-task Collaborative Pre-training and Individual-adaptive-tokens Fine-tuning: A Unified Framework for Brain Representation Learning

Structural magnetic resonance imaging (sMRI) provides accurate estimates...
research
08/11/2021

Prototype Completion for Few-Shot Learning

Few-shot learning aims to recognize novel classes with few examples. Pre...

Please sign up or login with your details

Forgot password? Click here to reset