Computational Efficiency
1495 papers with code • 1 benchmarks • 0 datasets
Methods and optimizations to reduce the computational resources (e.g., time, memory, or power) needed for training and inference in models. This involves techniques that streamline processing, optimize algorithms, or leverage hardware to enhance performance without compromising accuracy.
Benchmarks
These leaderboards are used to track progress in Computational Efficiency
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Most implemented papers
Rethinking the Inception Architecture for Computer Vision
tensorflow/models
•
•
CVPR 2016
Convolutional networks are at the core of most state-of-the-art computer vision solutions for a wide variety of tasks.
Attention U-Net: Learning Where to Look for the Pancreas
ozan-oktay/Attention-Gated-Networks
•
•
We propose a novel attention gate (AG) model for medical imaging that automatically learns to focus on target structures of varying shapes and sizes.
EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies
We train a student network to predict the extracted features of normal, i. e., anomaly-free training images.
Mamba: Linear-Time Sequence Modeling with Selective State Spaces
Foundation models, now powering most of the exciting applications in deep learning, are almost universally based on the Transformer architecture and its core attention module.
Simple random search provides a competitive approach to reinforcement learning
A common belief in model-free reinforcement learning is that methods based on random search in the parameter space of policies exhibit significantly worse sample complexity than those that explore the space of actions.
Efficient Neural Network Robustness Certification with General Activation Functions
huanzhang12/CROWN-Robustness-Certification
•
•
NeurIPS 2018
Finding minimum distortion of adversarial examples and thus certifying robustness in neural network classifiers for given data points is known to be a challenging problem.
RWKV: Reinventing RNNs for the Transformer Era
BlinkDL/RWKV-LM
•
•
This work presents a significant step towards reconciling trade-offs between computational efficiency and model performance in sequence processing tasks.
Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping
MIT-SPARK/Kimera
•
•
We provide an open-source C++ library for real-time metric-semantic visual-inertial Simultaneous Localization And Mapping (SLAM).
VMamba: Visual State Space Model
mzeromiko/vmamba
•
•
At the core of VMamba is a stack of Visual State-Space (VSS) blocks with the 2D Selective Scan (SS2D) module.
Resurrecting Recurrent Neural Networks for Long Sequences
Recurrent Neural Networks (RNNs) offer fast inference on long sequences but are hard to optimize and slow to train.
