SOTAVerified

Computational Efficiency

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.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 641–650 of 4891 papers

TitleStatusHype
Learnable Lookup Table for Neural Network QuantizationCode1
AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video RecognitionCode1
MSeg: A Composite Dataset for Multi-domain Semantic SegmentationCode1
PRIME: A few primitives can boost robustness to common corruptionsCode1
Reconstructing Compact Building Models from Point Clouds Using Deep Implicit FieldsCode1
A Deep Reinforcement Learning Approach for Solving the Traveling Salesman Problem with DroneCode1
StyleSwin: Transformer-based GAN for High-resolution Image GenerationCode1
GPU optimization of the 3D Scale-invariant Feature Transform Algorithm and a Novel BRIEF-inspired 3D Fast DescriptorCode1
Stable Long-Term Recurrent Video Super-ResolutionCode1
TRACER: Extreme Attention Guided Salient Object Tracing NetworkCode1
Show:102550
← PrevPage 65 of 490Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ViTaLHamming Loss0.05—Unverified