Google Brain & CMU Semi-Supervised ‘Noisy Student’ Achieves 88.4% Top-1 Accuracy on ImageNet

Google Brain & CMU Semi-Supervised ‘Noisy Student’ Achieves 88.4% Top-1 Accuracy on ImageNet

The proposed method’s 88.4 percent accuracy on ImageNet is 2.0 percent better than the SOTA model.

5 mentions: @Synced_Global@Synced_Global
Keywords: imagenet
Date: 2020/02/13 16:56

Referring Tweets

@Synced_Global On robustness test sets, it improves ImageNet-A top-1 accuracy from 61.0% to 83.7%, reduces ImageNet-C mean corruption error from 45.7 to 28.3, and reduces ImageNet-P mean flip rate from 27.8 to 12.2. #DeepLearning #machinelearning #AI t.co/xrqJmz3jsi
@Synced_Global Researchers from @GoogleAI Brain Team and @CarnegieMellon have released models trained with a semi-supervised learning method called “Noisy Student” that achieve 88.4 percent top-1 accuracy on ImageNet. #SOTA #DeepLearning #MachineLearning t.co/xrqJmyLIAK

Related Entries

Read more Say Woof? AI in Animal Language Translation | Synced
0 users, 2 mentions 2020/01/27 20:42
Read more ‘Active Neural Slam’ Uses Classical and Learning Approaches to Explore 3D Spaces
0 users, 3 mentions 2020/04/14 18:15
Read more Google Brain Rethinks Pre-training and Self-training | Synced
0 users, 1 mentions 2020/06/17 20:47
Read more ACL 2020 Announces Best Paper & Test-Of-Time Awards | Synced
0 users, 1 mentions 2020/07/08 17:21
Read more The GPT-3 Obsession; Facebook to Pay $650 M to Settle Facial Recognition Suit;  Watch Animal Crossin...
0 users, 1 mentions 2020/07/27 17:21