AdCo
AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries (by maple-research-lab)
Unsupervised-Semantic-Segmentation
Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals. [ICCV 2021] (by wvangansbeke)
| AdCo | Unsupervised-Semantic-Segmentation | |
|---|---|---|
| 2 | 1 | |
| 161 | 386 | |
| 0.0% | - | |
| 0.9 | 1.8 | |
| about 1 year ago | almost 2 years ago | |
| Python | Python | |
| MIT License | GNU General Public License v3.0 or later |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
AdCo
Posts with mentions or reviews of AdCo.
We have used some of these posts to build our list of alternatives
and similar projects.
-
[D] Negative examples are still useful in self-supervised learning even after the BYOL, and they are directly trainable end-to-end with a backbone.
The paper showed that with only 8196 negatives, the AdCo can achieve better performance than the SOTA self-supervised methods (MoCo V2, SimCLR, AdCo and SWAV) with fewer epochs, thus making the AdCo a very efficient self-supervised learning algorithm to pretrain a backbone. The source code has been released at https://github.com/maple-research-lab/AdCo.
-
[R] AdCo: Adversarial Contrast for Efficient Learning of Unsupervised Representations from Self-Trained Negative Adversaries
The source code is available at https://github.com/maple-research-lab/AdCo/. The paper will be presented at CVPR 2021.
Unsupervised-Semantic-Segmentation
Posts with mentions or reviews of Unsupervised-Semantic-Segmentation.
We have used some of these posts to build our list of alternatives
and similar projects.
-
Unsupervised semantic segmentation
Check out these unsupervised masks created in exactly such way in this paper. They are nearly perfect
What are some alternatives?
When comparing AdCo and Unsupervised-Semantic-Segmentation you can also consider the following projects:
Unsupervised-Classification - SCAN: Learning to Classify Images without Labels, incl. SimCLR. [ECCV 2020]
mmselfsup - OpenMMLab Self-Supervised Learning Toolbox and Benchmark
DA-RetinaNet - Official Detectron2 implementation of DA-RetinaNet of our Image and Vision Computing 2021 work 'An unsupervised domain adaptation scheme for single-stage artwork recognition in cultural sites'
solo-learn - solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning
DiffCSE - Code for the NAACL 2022 long paper "DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings"
PASS - The PASS dataset: pretrained models and how to get the data
AdCo vs Unsupervised-Classification
Unsupervised-Semantic-Segmentation vs mmselfsup
Unsupervised-Semantic-Segmentation vs Unsupervised-Classification
Unsupervised-Semantic-Segmentation vs DA-RetinaNet
Unsupervised-Semantic-Segmentation vs solo-learn
Unsupervised-Semantic-Segmentation vs DiffCSE
Unsupervised-Semantic-Segmentation vs PASS