Zobrazeno 1 - 5
of 5
pro vyhledávání: '"Feinglass, Joshua"'
Autor:
Feinglass, Joshua, Yang, Yezhou
Zero-shot inference, where pre-trained models perform tasks without specific training data, is an exciting emergent ability of large models like CLIP. Although there has been considerable exploration into enhancing zero-shot abilities in image captio
Externí odkaz:
http://arxiv.org/abs/2409.19960
Domain Generalization (DG) is a challenging task in machine learning that requires a coherent ability to comprehend shifts across various domains through extraction of domain-invariant features. DG performance is typically evaluated by performing ima
Externí odkaz:
http://arxiv.org/abs/2405.15961
Current approaches in Generalized Zero-Shot Learning (GZSL) are built upon base models which consider only a single class attribute vector representation over the entire image. This is an oversimplification of the process of novel category recognitio
Externí odkaz:
http://arxiv.org/abs/2404.08761
Autor:
Feinglass, Joshua, Yang, Yezhou
Object proposal generation serves as a standard pre-processing step in Vision-Language (VL) tasks (image captioning, visual question answering, etc.). The performance of object proposals generated for VL tasks is currently evaluated across all availa
Externí odkaz:
http://arxiv.org/abs/2309.00215
Autor:
Feinglass, Joshua, Yang, Yezhou
The open-ended nature of visual captioning makes it a challenging area for evaluation. The majority of proposed models rely on specialized training to improve human-correlation, resulting in limited adoption, generalizability, and explainabilty. We i
Externí odkaz:
http://arxiv.org/abs/2106.01444