SimCLR learns visual representations by contrasting augmented views of the same image and reaches 76.5% ImageNet top-1 accuracy with a linear classifier, matching a supervised ResNet-50.
M., Rupprecht, C., and Vedaldi, A
2 Pith papers cite this work, alongside 65 external citations. Polarity classification is still indexing.
2
Pith papers citing it
65
external citations · Pith
abstract
We look critically at popular self-supervision techniques for learning deep convolutional neural networks without manual labels. We show that three different and representative methods, BiGAN, RotNet and DeepCluster, can learn the first few layers of a convolutional network from a single image as well as using millions of images and manual labels, provided that strong data augmentation is used. However, for deeper layers the gap with manual supervision cannot be closed even if millions of unlabelled images are used for training. We conclude that: (1) the weights of the early layers of deep networks contain limited information about the statistics of natural images, that (2) such low-level statistics can be learned through self-supervision just as well as through strong supervision, and that (3) the low-level statistics can be captured via synthetic transformations instead of using a large image dataset.
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
A frozen SAM2 backbone with adaptive token selection and symmetric KL clustering achieves competitive self-supervised video object segmentation by aligning soft part assignments across time.
citing papers explorer
-
A Simple Framework for Contrastive Learning of Visual Representations
SimCLR learns visual representations by contrasting augmented views of the same image and reaches 76.5% ImageNet top-1 accuracy with a linear classifier, matching a supervised ResNet-50.
-
`Attention-Guided Cross-Temporal Clustering for Self-Supervised Video Object Segmentation
A frozen SAM2 backbone with adaptive token selection and symmetric KL clustering achieves competitive self-supervised video object segmentation by aligning soft part assignments across time.