paper-with-me

홈 › Papers

Deriving a Quantitative Relationship Between Resolution and Human Classification Error

2019-08-24 · Josiah I. Clark, Caroline A. Clark

For machine learning perception problems, human-level classification performance is used as an estimate of top algorithm performance. Thus, it is important to understand as precisely as possible the factors that impact human-level performance. Knowing this 1) provides a benchmark for model performance, 2) tells a project manager what type of data to obtain for human labelers in order to get accurate labels, and 3) enables ground-truth analysis--largely conducted by humans--to be carried out smoothly. In this empirical study, we explored the relationship between resolution and human classification performance using the MNIST data set down-sampled to various resolutions. The quantitative heuristic we derived could prove useful for predicting machine model performance, predicting data storage requirements, and saving valuable resources in the deployment of machine learning projects. It also has the potential to be used in a wide variety of fields such as remote sensing, medical imaging, scientific imaging, and astronomy.

📄 PDF Abstract BibTeX arXiv:1908.09183

Code (0)

등록된 구현이 없습니다.

Tasks

AstronomyBIG-bench Machine LearningClassificationGeneral Classification

Similar Papers 제목 키워드 기반

Deep Learning-based Image Super-Resolution Considering Quantitative and Perceptual Quality

2018-09-13 · Jun-Ho Choi, Jun-Hyuk Kim, Manri Cheon, Jong-Seok Lee

Recently, it has been shown that in super-resolution, there exists a tradeoff relationship between the quantitative and perceptual quality of super-resolved images, which correspond to the similarity to the ground-truth …

Image Super-ResolutionSuper-Resolution

Open Vocabulary Compositional Explanations for Neuron Alignment

2025-11-25 · Biagio La Rosa, Leilani H. Gilpin arxiv

Neurons are the fundamental building blocks of deep neural networks, and their interconnections allow AI to achieve unprecedented results. Motivated by the goal of understanding how neurons encode information, compositio…

Open Vocabulary Semantic Segmentation

Single-Image Super-Resolution Reconstruction based on the Differences of Neighboring Pixels

2022-12-28 · Huipeng Zheng, Lukman Hakim, Takio Kurita, Junichi Miyao

The deep learning technique was used to increase the performance of single image super-resolution (SISR). However, most existing CNN-based SISR approaches primarily focus on establishing deeper or larger networks to extr…

Image Super-ResolutionSuper-Resolution

Navigating Efficiency in MobileViT through Gaussian Process on Global Architecture Factors

2024-06-07 · Ke Meng, Kai Chen

Numerous techniques have been meticulously designed to achieve optimal architectures for convolutional neural networks (CNNs), yet a comparable focus on vision transformers (ViTs) has been somewhat lacking. Despite the r…

Dynamic Cross Feature Fusion for Remote Sensing Pansharpening

2021-01-01 · ICCV 2021 10 · Xiao Wu, Ting-Zhu Huang, Liang-Jian Deng, Tian-Jing Zhang

Deep Convolution Neural Networks have been adopted for pansharpening and achieved state-of-the-art performance. However, most of the existing works mainly focus on single-scale feature fusion, which leads to failure …

Pansharpening