REVIEW 5 cited by
With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of 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
With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations
read the original abstract
Self-supervised learning algorithms based on instance discrimination train encoders to be invariant to pre-defined transformations of the same instance. While most methods treat different views of the same image as positives for a contrastive loss, we are interested in using positives from other instances in the dataset. Our method, Nearest-Neighbor Contrastive Learning of visual Representations (NNCLR), samples the nearest neighbors from the dataset in the latent space, and treats them as positives. This provides more semantic variations than pre-defined transformations. We find that using the nearest-neighbor as positive in contrastive losses improves performance significantly on ImageNet classification, from 71.7% to 75.6%, outperforming previous state-of-the-art methods. On semi-supervised learning benchmarks we improve performance significantly when only 1% ImageNet labels are available, from 53.8% to 56.5%. On transfer learning benchmarks our method outperforms state-of-the-art methods (including supervised learning with ImageNet) on 8 out of 12 downstream datasets. Furthermore, we demonstrate empirically that our method is less reliant on complex data augmentations. We see a relative reduction of only 2.1% ImageNet Top-1 accuracy when we train using only random crops.
Forward citations
Cited by 5 Pith papers
-
Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution
Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.
-
Star-forming clump detection in nearby galaxies using Faster R-CNN and $ugrizy$ imaging data from CLAUDS and HSC-SSP
A multi-band Faster R-CNN with Zoobot backbone detects star-forming clumps in low-z galaxies at ≥0.9 completeness and ≥0.8 purity on simulated injections, yielding ~1.5M candidates.
-
Star-forming clump detection in nearby galaxies using Faster R-CNN and $ugrizy$ imaging data from CLAUDS and HSC-SSP
A six-band Faster R-CNN with the Zoobot backbone detects star-forming clump candidates in ~700,000 local galaxies, claiming ~90% completeness and ~80% purity for clumps brighter than the surveys' detection limits.
-
Contrastive learning of extragalactic stellar streams. Sculpting a latent space of representations with DES DR2 photometry
Applying NNCLR contrastive learning to DES DR2 galaxy cutouts yields embeddings that cluster major-merger galaxies but not stellar streams; a tiered sigmoid scaling redirects the network's saliency toward low-surface-...
-
Vision Transformers Need Registers
Adding register tokens to Vision Transformers eliminates high-norm background artifacts and raises state-of-the-art performance on dense visual prediction tasks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.