Model Optimization
69 papers with code • 0 benchmarks • 0 datasets
To Optimize already existing models in Training/Inferencing tasks.
Benchmarks
These leaderboards are used to track progress in Model Optimization
Most implemented papers
Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics
allenai/cartography
•
•
EMNLP 2020
Experiments across four datasets show that these model-dependent measures reveal three distinct regions in the data map, each with pronounced characteristics.
Real-Time Scene Text Detection with Differentiable Binarization and Adaptive Scale Fusion
MhLiao/DB
•
•
By incorporating the proposed DB and ASF with the segmentation network, our proposed scene text detector consistently achieves state-of-the-art results, in terms of both detection accuracy and speed, on five standard benchmarks.
Dynamic Scale Training for Object Detection
We propose a Dynamic Scale Training paradigm (abbreviated as DST) to mitigate scale variation challenge in object detection.
Personalized Federated Learning with Moreau Envelopes
CharlieDinh/pFedMe
•
•
NeurIPS 2020
Federated learning (FL) is a decentralized and privacy-preserving machine learning technique in which a group of clients collaborate with a server to learn a global model without sharing clients' data.
Iterative Surrogate Model Optimization (ISMO): An active learning algorithm for PDE constrained optimization with deep neural networks
We present a novel active learning algorithm, termed as iterative surrogate model optimization (ISMO), for robust and efficient numerical approximation of PDE constrained optimization problems.
Personalized Federated Learning with First Order Model Optimization
While federated learning traditionally aims to train a single global model across decentralized local datasets, one model may not always be ideal for all participating clients.
PIXOR: Real-time 3D Object Detection from Point Clouds
DerrickXuNu/OpenCOOD
•
•
CVPR 2018
Existing approaches are, however, expensive in computation due to high dimensionality of point clouds.
AutoScale: Learning to Scale for Crowd Counting and Localization
A major issue is that the density map on dense regions usually accumulates density values from a number of nearby Gaussian blobs, yielding different large density values on a small set of pixels.
Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairness
Then, we have applied 7 mitigation techniques on these models and analyzed the fairness, mitigation results, and impacts on performance.
Multi-objective Asynchronous Successive Halving
Hyperparameter optimization (HPO) is increasingly used to automatically tune the predictive performance (e. g., accuracy) of machine learning models.
