An open-source directory of unsupervised machine learning papers, tasks and methods with links to articles, websites, videos and code.
Joined September 2020
- Tweets43
- Following18
- Followers13
- Likes194
UnsupervisedPapers.com retweeted
Neighbor2Neighbor: Self-Supervised Denoising from Single Noisy Images. arxiv.org/abs/2101.02824
UnsupervisedPapers.com retweeted
Taxonomy of multimodal self-supervised representation learning. arxiv.org/abs/2012.13623
UnsupervisedPapers.com retweeted
"Self-Supervised Representation Learning for Astronomical Images
Md Abul Hayat, George Stein, Peter Harrington, Zarija Lukić, Mustafa Mustafa
arxiv.org/abs/2012.13083
I am looking for a job in Microscopy
NeurIPS 2020 | Conference Watch on Self-Supervised Learning by @Synced_Global link.medium.com/wWZ08KTQkcb
UnsupervisedPapers.com retweeted
Self-supervised visual representation learning from hierarchical grouping
arxiv: arxiv.org/abs/2012.03044
Use contours to partition image; group into hierarchies; loss is pairwise contrastive using positive/negatives from the grouping
UnsupervisedPapers.com retweeted
ISD: Self-Supervised Learning by Iterative Similarity Distillation. arxiv.org/abs/2012.09259
UnsupervisedPapers.com retweeted
Welcome, FERM from researchers @UCBerkeley, a framework that can train a robotic arm on 6 grasping tasks in less than 1 hour given only 10 demonstrations utilizing data augmentation, unsupervised and reinforcement learning for sample-efficient training.
bit.ly/3mrZnxz
UnsupervisedPapers.com retweeted
Understanding graph embedding methods and their applications. arxiv.org/abs/2012.08019
UnsupervisedPapers.com retweeted
Pair-view Unsupervised Graph Representation Learning. #ArtificialIntelligence #MachineLearning #BigData #Analytics #Python #RStats #JavaScript #ReactJS #Serverless #Linux #IoT #Programming #100DaysOfCode #NeuralNetworks #DeepLearning #DataScience #AI
arxiv.org/abs/2012.06113
UnsupervisedPapers.com retweeted
1/6 Check our new paper on Flexible Few-Shot Learning! arxiv.org/abs/2012.05895
We extend FSL to include flexible classification criterion in each episode. Unsupervised representation learning beats supervised approaches.
Short version @ #NeurIPS2020 metalearn workshop, 10am EST
Unsupervised part representation by Flow Capsules unsupervisedpapers.com/paper…
Unsupervised Learning of Dense Visual Representations unsupervisedpapers.com/paper…
Unsupervised Learning of Object Landmarks via Self-Training Correspondence unsupervisedpapers.com/paper…
Space-Time Correspondence as a Contrastive Random Walk unsupervisedpapers.com/paper…
UnsupervisedPapers.com retweeted
Our new paper "𝐔𝐧𝐬𝐮𝐩𝐞𝐫𝐯𝐢𝐬𝐞𝐝 𝐩𝐚𝐫𝐭 𝐫𝐞𝐩𝐫𝐞𝐬𝐞𝐧𝐭𝐚𝐭𝐢𝐨𝐧 𝐛𝐲 𝐅𝐥𝐨𝐰 𝐂𝐚𝐩𝐬𝐮𝐥𝐞𝐬" is out arxiv.org/abs/2011.13920
TL;DR: are newborns exposed to 14 million (i.e. ImageNet) labeled images? No! They learn by observing motion... in an unsupervised fashion
Unsupervised machine learning method of the day: the GIST descriptor
unsupervisedpapers.com/metho…
UnsupervisedPapers.com retweeted
This really resonates. AI/ML research is generally too focused on generating ‘novel’ methods, and re-branding tweaks on existing methods, rather than finding connections between existing methods, and solving real problems.
AI/ML tweeps, here is a must read.
It’s a wonderful article questioning whether we are spending our valuable brain cycles on the right research questions.
If you disagree, I’d love to hear why. If you agree, what can be done to accelerate this? technologyreview.com/2020/08…
Contrast-based saliency is an unsupervised learning method used for object detection.
unsupervisedpapers.com/metho…