paper-with-me

Papers

Image augmentation improves few-shot classification performance in plant disease recognition

2022-08-25 · Frank Xiao

With the world population projected to near 10 billion by 2050, minimizing crop damage and guaranteeing food security has never been more important. Machine learning has been proposed as a solution to quickly and efficiently identify diseases in crops. Convolutional Neural Networks typically require large datasets of annotated data which are not available on demand. Collecting this data is a long and arduous process which involves manually picking, imaging, and annotating each individual leaf. I tackle the problem of plant image data scarcity by exploring the efficacy of various data augmentation techniques when used in conjunction with transfer learning. I evaluate the impact of various data augmentation techniques both individually and combined on the performance of a ResNet. I propose an augmentation scheme utilizing a sequence of different augmentations which consistently improves accuracy through many trials. Using only 10 total seed images, I demonstrate that my augmentation framework can increase model accuracy by upwards of 25\%.

📄 PDF Abstract BibTeX arXiv:2208.12613

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationImage AugmentationTransfer Learning

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Average Pooling 설명 없음
Batch Normalization 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Residual Connection 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

Similar Papers 제목 키워드 기반

Frozen Feature Augmentation for Few-Shot Image Classification

2024-03-15 · CVPR 2024 1 · Andreas Bär, Neil Houlsby, Mostafa Dehghani, Manoj Kumar

Training a linear classifier or lightweight model on top of pretrained vision model outputs, so-called 'frozen features', leads to impressive performance on a number of downstream few-shot tasks. Currently, frozen featur…

ClassificationData AugmentationFew-Shot Image Classificationimage-classification+1

VOCABULARY-INFORMED VISUAL FEATURE AUGMENTATION FOR ONE-SHOT LEARNING

2018-01-01 · ICLR 2018 1 · jianqi ma, Hangyu Lin, yinda zhang, Yanwei Fu 외

A natural solution for one-shot learning is to augment training data to handle the data deficiency problem. However, directly augmenting in the image domain may not necessarily generate training data that sufficiently ex…

ClassificationData AugmentationDecoderGeneral Classification+1

Few-Shot Text Classification with Triplet Networks, Data Augmentation, and Curriculum Learning

2021-03-12 · NAACL 2021 4 · Jason Wei, Chengyu Huang, Soroush Vosoughi, Yu Cheng 외

Few-shot text classification is a fundamental NLP task in which a model aims to classify text into a large number of categories, given only a few training examples per category. This paper explores data augmentation -- a…

ClassificationData AugmentationFew-Shot Text ClassificationGeneral Classification+3

1S-DAug: One-Shot Data Augmentation for Robust Few-Shot Generalization

2026-01-27 · Yunwei Bai, Ying Kiat Tan, Yao Shu, Tsuhan Chen arxiv

Few-shot learning (FSL) challenges model generalization to novel classes based on just a few shots of labeled examples, a testbed where traditional test-time augmentations fail to be effective. We introduce 1S-DAug, a on…

Few-Shot LearningData Augmentation

Data Augmentation for Meta-Learning

2020-10-14 · Renkun Ni, Micah Goldblum, Amr Sharaf, Kezhi Kong 외

Conventional image classifiers are trained by randomly sampling mini-batches of images. To achieve state-of-the-art performance, practitioners use sophisticated data augmentation schemes to expand the amount of training …

Data AugmentationMeta-Learning