time-series-1

Computational Efficiency

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in computational-efficiency-1

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find computational-efficiency-1 models and implementations

benedekrozemberczki/karateclub

3 papers 2,085

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Rethinking the Inception Architecture for Computer Vision

Z. Wojna, Sergey Ioffe, Christian Szegedy, Vincent Vanhoucke, Jonathon Shlens•Tue Dec 01 2015

This work is exploring ways to scale up networks in ways that aim at utilizing the added computation as efficiently as possible by suitably factorized convolutions and aggressive regularization.

29572

Content

PaddlePaddle/PaddleOCR

2 papers 38,418

microsoft/DeepSpeed

2 papers 32,603

rwightman/pytorch-image-models

2 papers 29,735

benedekrozemberczki/littleballoffur

2 papers 691

faceonlive/ai-research

2 papers 144

0

Paper Graph

Attention U-Net: Learning Where to Look for the Pancreas

D. Rueckert, Nils Y. Hammerla, Ben Glocker, M. Heinrich, O. Oktay, Jo Schlemper, Steven G. McDonagh, Loic Le Folgoc, M. J. Lee, K. Misawa, K. Mori, Bernhard Kainz•Tue Apr 10 2018

A novel attention gate (AG) model for medical imaging that automatically learns to focus on target structures of varying shapes and sizes is proposed to eliminate the necessity of using explicit external tissue/organ localisation modules of cascaded convolutional neural networks (CNNs).

6614 0

Paper Graph

EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies

Kilian Batzner, Rebecca König, Lars Heckler•Fri Mar 24 2023

This work proposes a lightweight feature extractor that processes an image in less than a millisecond on a modern GPU and proposes a training loss that hinders the student from imitating the teacher feature extractor beyond the normal images, allowing it to drastically reduce the computational cost of the student–teacher model.

271 0

Paper Graph

Simple random search provides a competitive approach to reinforcement learning

B. Recht, Aurelia Guy, Horia Mania•Sun Mar 18 2018

This work introduces a random search method for training static, linear policies for continuous control problems, matching state-of-the-art sample efficiency on the benchmark MuJoCo locomotion tasks.

330 0

Paper Graph

Efficient Neural Network Robustness Certification with General Activation Functions

Cho-Jui Hsieh, Pin-Yu Chen, Huan Zhang, L. Daniel, Tsui-Wei Weng•Wed Oct 31 2018

This paper introduces CROWN, a general framework to certify robustness of neural networks with general activation functions for given input data points and facilitates the search for a tighter certified lower bound by adaptively selecting appropriate surrogates for each neuron activation.

848 0

Paper Graph

Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping

L. Carlone, Antoni Rosinol, Marcus Abate, Yun Chang•Sat Oct 05 2019

The flexibility, computational efficiency, robustness, and accuracy afforded by Kimera will build a solid basis for future metric-semantic SLAM and perception research, and will allow researchers across multiple areas to benchmark and prototype their own efforts without having to start from scratch.

554 0

Paper Graph

PP-OCR: A Practical Ultra Lightweight OCR System

Qingqing Dang, Yuning Du, Hongya Wang, Chenxia Li, Ruoyu Guo, Xiaoting Yin, Weiwei Liu, Jun Zhou, Yifan Bai, Zilin Yu, Yehua Yang•Sun Sep 20 2020

This paper proposes a practical ultra lightweight OCR system, i.e., PP-OCR, with an overall model size of only 3.5M, and introduces a bag of strategies to either enhance the model ability or reduce the model size.

263 0

Paper Graph

PointNetLK: Robust & Efficient Point Cloud Registration Using PointNet

S. Lucey, Yasuhiro Aoki, Hunter Goforth, Rangaprasad Arun Srivatsan•Tue Mar 12 2019

It is argued that PointNet itself can be thought of as a learnable "imaging" function, and classical vision algorithms for image alignment can be brought to bear on the problem -- namely the Lucas & Kanade (LK) algorithm.

856 0

Paper Graph

Scalable Bayesian Rule Lists

C. Rudin, Hongyu Yang, M. Seltzer•Fri Feb 26 2016

An algorithm for building probabilistic rule lists that is two orders of magnitude faster than previous work and optimizes the posterior of a Bayesian hierarchical model over rule lists.

224 0

Paper Graph

Resurrecting Recurrent Neural Networks for Long Sequences

Caglar Gulcehre, Razvan Pascanu, Albert Gu, Antonio Orvieto, Samuel L. Smith, Anushan Fernando, Soham De•Fri Mar 10 2023

This paper shows that careful design of deep RNNs using standard signal propagation arguments can recover the impressive performance of deep SSMs on long-range reasoning tasks, whileAlso introducing an RNN block called the Linear Recurrent Unit that matches both their performance on the Long Range Arena benchmark and their computational efficiency.

435 0

Paper Graph

Adding a benchmark result helps the community track progress.