7 citations · 8 across the 6 of their papers we have counts for
6 papers
DataComp-VLM: Improved Open Datasets for Vision-Language Models
Matteo Farina, Vishaal Udandarao, Thao Nguyen +33
Building performant Vision-Language Models (VLMs) requires carefully curating large-scale training datasets, yet the community lacks systematic benchmarks for evaluating such curat…
Concept-Aware Batch Sampling Improves Language-Image Pretraining
Adhiraj Ghosh, Vishaal Udandarao, Thao Nguyen +7
What data should a vision-language model be trained on? To answer this question, many data curation efforts center on the quality of a dataset. However, most of these existing meth…
ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities
Adhiraj Ghosh, Sebastian Dziadzio, Ameya Prabhu +3
Traditional fixed test sets fall short in evaluating open-ended capabilities of foundation models. To address this, we propose ONEBench(OpeN-Ended Benchmarking), a new testing para…
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
Vishaal Udandarao, Ameya Prabhu, Adhiraj Ghosh +5
Web-crawled pretraining datasets underlie the impressive "zero-shot" evaluation performance of multimodal models, such as CLIP for classification/retrieval and Stable-Diffusion for…
ViPE: Visualise Pretty-much Everything
Hassan Shahmohammadi, Adhiraj Ghosh, Hendrik P. A. Lensch
Figurative and non-literal expressions are profoundly integrated in human communication. Visualising such expressions allow us to convey our creative thoughts, and evoke nuanced em…
Relation Preserving Triplet Mining for Stabilising the Triplet Loss in Re-identification Systems
Adhiraj Ghosh, Kuruparan Shanmugalingam, Wen-Yan Lin
Object appearances change dramatically with pose variations. This creates a challenge for embedding schemes that seek to map instances with the same object ID to locations that are…