Christos Kaplanis

most citedSynth

^{2}

: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings

3 citations · 4 across the 3 of their papers we have counts for

collaborators

Showing cs.CVShow all

2 papers · 1 filter

cs.CV2024★ 3 cited

Synth $^{2}$ : Boosting Visual-Language Models with Synthetic Captions and Image Embeddings

Sahand Sharifzadeh, Christos Kaplanis, Shreya Pathak +5

The creation of high-quality human-labeled image-caption datasets presents a significant bottleneck in the development of Visual-Language Models (VLMs). In this work, we investigat…

cs.CV2024★ 1 cited

Improving fine-grained understanding in image-text pre-training

Ioana Bica, Anastasija Ilić, Matthias Bauer +8

We introduce SPARse Fine-grained Contrastive Alignment (SPARC), a simple method for pretraining more fine-grained multimodal representations from image-text pairs. Given that multi…

Synth2: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings

Improving fine-grained understanding in image-text pre-training

Synth $^{2}$ : Boosting Visual-Language Models with Synthetic Captions and Image Embeddings