Search Results for author:
Found 3 papers, 3 papers with code
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
Web-crawled pretraining datasets underlie the impressive "zero-shot" evaluation performance of multimodal models, such as CLIP for classification/retrieval and Stable-Diffusion for image generation.
ViPE: Visualise Pretty-much Everything
Figurative and non-literal expressions are profoundly integrated in human communication.
Relation Preserving Triplet Mining for Stabilising the Triplet Loss in Re-identification Systems
This leads us to introduce Relation Preserving Triplet Mining (RPTM), a feature-matching guided triplet mining scheme, that ensures that triplets will respect the natural subgroupings within an object ID.
Ranked #2 on
Vehicle Re-Identification
on VeRi-776
