Search Results for author:
Found 3 papers, 2 papers with code
Exploring Curriculum Learning for Vision-Language Tasks: A Study on Small-Scale Multimodal Training
In such limited data / compute settings, various methods exist aiming to $\textit{do more with less}$, such as finetuning from a pretrained model, modulating difficulty levels as data are presented to a model (curriculum learning), and considering the role of model type / size.
It's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap
We present evidence that attributes this contrastive gap to low uniformity in CLIP space, resulting in embeddings that occupy only a small portion of the latent space.
Unsupervised Space Partitioning for Nearest Neighbor Search
We achieve the above edge by formulating a multi-objective custom loss function that does not need ground truth labels to quantify the quality of a given data-space partition, making it entirely unsupervised.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
