Zobrazeno 1 - 10
of 36
pro vyhledávání: '"Prabhu, Viraj"'
Autor:
Xue, Le, Shu, Manli, Awadalla, Anas, Wang, Jun, Yan, An, Purushwalkam, Senthil, Zhou, Honglu, Prabhu, Viraj, Dai, Yutong, Ryoo, Michael S, Kendre, Shrikant, Zhang, Jieyu, Qin, Can, Zhang, Shu, Chen, Chia-Chih, Yu, Ning, Tan, Juntao, Awalgaonkar, Tulika Manoj, Heinecke, Shelby, Wang, Huan, Choi, Yejin, Schmidt, Ludwig, Chen, Zeyuan, Savarese, Silvio, Niebles, Juan Carlos, Xiong, Caiming, Xu, Ran
This report introduces xGen-MM (also known as BLIP-3), a framework for developing Large Multimodal Models (LMMs). The framework comprises meticulously curated datasets, a training recipe, model architectures, and a resulting suite of LMMs. xGen-MM, s
Externí odkaz:
http://arxiv.org/abs/2408.08872
Autor:
Kareer, Simar, Vijaykumar, Vivek, Maheshwari, Harsh, Chattopadhyay, Prithvijit, Hoffman, Judy, Prabhu, Viraj
There has been abundant work in unsupervised domain adaptation for semantic segmentation (DAS) seeking to adapt a model trained on images from a labeled source domain to an unlabeled target domain. While the vast majority of prior work has studied th
Externí odkaz:
http://arxiv.org/abs/2402.00868
Synthetic data (SIM) drawn from simulators have emerged as a popular alternative for training models where acquiring annotated real-world images is difficult. However, transferring models trained on synthetic images to real-world applications can be
Externí odkaz:
http://arxiv.org/abs/2312.06106
Autor:
Goldblum, Micah, Souri, Hossein, Ni, Renkun, Shu, Manli, Prabhu, Viraj, Somepalli, Gowthami, Chattopadhyay, Prithvijit, Ibrahim, Mark, Bardes, Adrien, Hoffman, Judy, Chellappa, Rama, Wilson, Andrew Gordon, Goldstein, Tom
Neural network based computer vision systems are typically built on a backbone, a pretrained or randomly initialized feature extractor. Several years ago, the default option was an ImageNet-trained convolutional neural network. However, the recent pa
Externí odkaz:
http://arxiv.org/abs/2310.19909
Computer vision datasets frequently contain spurious correlations between task-relevant labels and (easy to learn) latent task-irrelevant attributes (e.g. context). Models trained on such datasets learn "shortcuts" and underperform on bias-conflictin
Externí odkaz:
http://arxiv.org/abs/2309.17430
As computer vision systems are being increasingly deployed at scale in high-stakes applications like autonomous driving, concerns about social bias in these systems are rising. Analysis of fairness in real-world vision systems, such as object detecti
Externí odkaz:
http://arxiv.org/abs/2306.04482
We propose an automated algorithm to stress-test a trained visual model by generating language-guided counterfactual test images (LANCE). Our method leverages recent progress in large language modeling and text-based image editing to augment an IID t
Externí odkaz:
http://arxiv.org/abs/2305.19164
Autor:
Prabhu, Viraj, Acuna, David, Liao, Andrew, Mahmood, Rafid, Law, Marc T., Hoffman, Judy, Fidler, Sanja, Lucas, James
Sim2Real domain adaptation (DA) research focuses on the constrained setting of adapting from a labeled synthetic source domain to an unlabeled or sparsely labeled real target domain. However, for high-stakes applications (e.g. autonomous driving), it
Externí odkaz:
http://arxiv.org/abs/2302.04832
As transformer architectures become increasingly prevalent in computer vision, it is critical to understand their fairness implications. We perform the first study of the fairness of transformers applied to computer vision and benchmark several bias
Externí odkaz:
http://arxiv.org/abs/2302.04358
Visual domain adaptation (DA) seeks to transfer trained models to unseen, unlabeled domains across distribution shift, but approaches typically focus on adapting convolutional neural network architectures initialized with supervised ImageNet represen
Externí odkaz:
http://arxiv.org/abs/2206.08222