Embedding Contrastive Unsupervised Features to Cluster In- And Out-of-Distribution Noise in Corrupted Image Datasets.
Paul AlbertEric ArazoNoel E. O'ConnorKevin McGuinnessPublished in: ECCV (31) (2022)
Keyphrases
- spatial distribution
- additive gaussian noise
- feature space
- supervised learning
- unsupervised learning
- training and testing data
- unsupervised feature selection
- noise free
- noise level
- data clustering
- machine learning
- feature vectors
- vector space
- co occurrence
- noise reduction
- digital images
- image features
- noise model
- feature extraction
- image segmentation
- clustering algorithm