IC-357Off-the-shelf foundation models (DINO, CLIP, DINOv2, ViT) exhibit higher variance in their cosine similarity distributions than dataset-specific models, reducing the discriminative power of cosine similarity retrieval

Mohammad Omama, Po-han Li, Sandeep P. Chinchali

SourceExploiting Distribution Constraints for Scalable and Efficient Image Retrieval

The paper measures the probability mass function of pairwise cosine similarities in the reference set for both off-the-shelf foundation models and a dataset-specific model (CoPlace) on Pittsburgh30k. Foundation models show a broader, higher-variance cosine similarity distribution, meaning high-variance dimensions dominate the similarity computation and reduce the ability to distinguish relevant from irrelevant matches. Applying the authors' variance-constrained autoencoder (AE-SVC) reduces this variance and yields up to 15.5% average improvement in MAP@k across four datasets, with the improvement being larger for foundation models (~10%) than for the dataset-specific model (~2%), confirming that the distributional property is the limiting factor for the off-the-shelf models.

Evidence
correlational
Key metric
ae-svc achieves an average improvement of 15.5% across all datasets and embeddings at full size; dinov2-large shows 24% improvement on inshop, 10% on sop, 2% on pittsburgh30k, and 22% on tokyoval; ae-svc benefits the off-the-shelf foundation model more (10%) than the dataset-specific model (2%)
Caveat
The improvement from AE-SVC on dataset-specific models is limited (2%), suggesting the distributional issue is specific to foundation models; the paper notes the fundamental discrepancy between embedding spaces of foundation and dataset-specific models remains unknown
Model
DINO, DINOv2, CLIP / CLIP-ViT (LC), ViT, CoPlace
Concepts
Distance preservation
Datasets
InShop [eval], Stanford Online Products [eval], Pittsburgh30k [eval], TokyoVal [eval]
Methods
Principal component analysis [compared-to], TLDR [compared-to]
Related work
CoPlace [compared-to], TLDR [compared-to]
Extraction
automatic-extraction