title

Visual Perception via Learning in an Open World

Content-Type

text/html; charset=UTF-8

viewport

width=device-width, initial-scale=1.0

X-UA-Compatible

IE=edge,chrome=1

keywords

open-world vision, open-set recognition, long-tail, continual learning, lifelong learning, deep learning, computer vision, few-shot learning, zero-shot learning, active learning, transfer learning, catastrophic forgetting, self-supervised learning, weakly supervised learning, uncertainty, interpretability, anomaly detection, robustness, generalization, large-scale testing, simulation testing, evaluation metrics, train-test domain gap, streaming data, few-shot annotation, synthetic data, data bias, diverse annotations, multi-modality, AI safety, autonomous driving, medical image, auto diagnosis, real-world applications, inter-disciplinary research, carnegie mellon, machine learning, finetuning, foundation model, generative AI

og:title

Visual Perception via Learning in an Open World

og:url

https://vplow.github.io/vplow_3rd.html

og:type

article

og:image

https://vplow.github.io/vplow_3rd_files/logo.png

twitter:card

summary

twitter:site

@aimerykong

twitter:title

Visual Perception via Learning in an Open World

twitter:image

https://vplow.github.io/vplow_3rd_files/logo.png

twitter:description

computer vision in the real open world

shortcut icon

./vplow_3rd_files/logo.png

stylesheet

./vplow_3rd_files/bootstrap.min.css

stylesheet

./vplow_3rd_files/bootstrap-theme.min.css

stylesheet

./vplow_3rd_files/style.css