paper-with-me

Papers

Algorithmic progress in computer vision

2022-12-10 · Ege Erdil, Tamay Besiroglu

We investigate algorithmic progress in image classification on ImageNet, perhaps the most well-known test bed for computer vision. We estimate a model, informed by work on neural scaling laws, and infer a decomposition of progress into the scaling of compute, data, and algorithms. Using Shapley values to attribute performance improvements, we find that algorithmic improvements have been roughly as important as the scaling of compute for progress computer vision. Our estimates indicate that algorithmic innovations mostly take the form of compute-augmenting algorithmic advances (which enable researchers to get better performance from less compute), not data-augmenting algorithmic advances. We find that compute-augmenting algorithmic advances are made at a pace more than twice as fast as the rate usually associated with Moore's law. In particular, we estimate that compute-augmenting innovations halve compute requirements every nine months (95\% confidence interval: 4 to 25 months).

📄 PDF Abstract BibTeX arXiv:2212.05153

Code (0)

등록된 구현이 없습니다.

Tasks

Attributeimage-classificationImage Classification

Methods 이 논문이 사용한 방법론

Test 설명 없음

Similar Papers 제목 키워드 기반

Exploring Quantum-Enhanced Machine Learning for Computer Vision: Applications and Insights on Noisy Intermediate-Scale Quantum Devices

2024-04-01 · Purnachandra Mandadapu

As medium-scale quantum computers progress, the application of quantum algorithms across diverse fields like simulating physical systems, chemistry, optimization, and cryptography becomes more prevalent. However, these q…

CloudCV: Large Scale Distributed Computer Vision as a Cloud Service

2015-06-12 · Harsh Agrawal, Clint Solomon Mathialagan, Yash Goyal, Neelima Chavali 외

We are witnessing a proliferation of massive visual data. Unfortunately scaling existing computer vision algorithms to large datasets leaves researchers repeatedly solving the same algorithmic, logistical, and infrastruc…

Distributed Computing

A Time Leap Challenge for SAT Solving

2020-08-05 · Johannes K. Fichte, Markus Hecher, Stefan Szeider

We compare the impact of hardware advancement and algorithm advancement for SAT solving over the last two decades. In particular, we compare 20-year-old SAT-solvers on new computer hardware with modern SAT-solvers on 20-…

Algorithmic Performance-Accuracy Trade-off in 3D Vision Applications Using HyperMapper

2017-02-02 · Luigi Nardi, Bruno Bodin, Sajad Saeedi, Emanuele Vespa 외

In this paper we investigate an emerging application, 3D scene understanding, likely to be significant in the mobile space in the near future. The goal of this exploration is to reduce execution time while meeting our qu…

Active LearningGPUScene Understanding

How to transfer algorithmic reasoning knowledge to learn new algorithms?

2021-10-26 · NeurIPS 2021 12 · Louis-Pascal A. C. Xhonneux, Andreea Deac, Petar Velickovic, Jian Tang

Learning to execute algorithms is a fundamental problem that has been widely studied. Prior work~\cite{veli19neural} has shown that to enable systematic generalisation on graph algorithms it is critical to have access to…

Learning to ExecuteMulti-Task Learning