songweige/Contrastive-Learning-with-Non-Semantic-Negatives
Robust Contrastive Learning Using Negative Samples with Diminished Semantics (NeurIPS 2021)
This project offers a method to train computer vision models that are more resilient to changes in image style, texture, or background noise. It takes a collection of images as input and produces a robust, pre-trained image recognition model. This would be used by researchers and engineers building image classification systems for diverse or challenging real-world environments.
No commits in the last 6 months.
Use this if you need an image recognition model that performs reliably even when images have varying visual characteristics like different artistic styles, textures, or minor corruptions.
Not ideal if your image data is perfectly clean, uniform, and you do not anticipate variations in visual features that are irrelevant to the core content.
Stars
40
Forks
7
Language
Python
License
MIT
Category
Last pushed
Dec 06, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/songweige/Contrastive-Learning-with-Non-Semantic-Negatives"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
AdaptiveMotorControlLab/CEBRA
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
theolepage/sslsv
Toolkit for training and evaluating Self-Supervised Learning (SSL) frameworks for Speaker...
PaddlePaddle/PASSL
PASSL包含 SimCLR，MoCo v1/v2，BYOL，CLIP，PixPro，simsiam, SwAV, BEiT，MAE 等图像自监督算法以及 Vision...
YGZWQZD/LAMDA-SSL
30 Semi-Supervised Learning Algorithms
ModSSC/ModSSC
ModSSC: A Modular Framework for Semi Supervised Classification