REVIEW 2 cited by
Extreme Masking for Learning Instance and Distributed Visual Representations
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
The paper presents a scalable approach for learning spatially distributed visual representations over individual tokens and a holistic instance representation simultaneously. We use self-attention blocks to represent spatially distributed tokens, followed by cross-attention blocks to aggregate the holistic image instance. The core of the approach is the use of extremely large token masking (75\%-90\%) as the data augmentation for supervision. Our model, named ExtreMA, follows the plain BYOL approach where the instance representation from the unmasked subset is trained to predict that from the intact input. Instead of encouraging invariance across inputs, the model is required to capture informative variations in an image. The paper makes three contributions: 1) It presents random masking as a strong and computationally efficient data augmentation for siamese representation learning. 2) With multiple sampling per instance, extreme masking greatly speeds up learning and improves performance with more data. 3) ExtreMA obtains stronger linear probing performance than masked modeling methods, and better transfer performance than prior contrastive models.
Forward citations
Cited by 2 Pith papers
-
One Leaf Reveals the Season: Occlusion-Based Contrastive Learning with Semantic-Aware Views for Efficient Visual Representation
OCL pre-trains vision transformers by contrasting two non-overlapping randomly masked views of each image, reaching 85.8% ImageNet fine-tuning accuracy with ViT-L/16 in 133 hours on 4 A100s.
-
MINR: Implicit Neural Representations with Masked Image Modelling
A hybrid of implicit neural representations and masked image modeling, called MINR, reconstructs masked image patches better than MAE in the reported in-domain and out-of-distribution tests with fewer parameters.
Discussion (0). Continue with ORCID to comment.