Search Results for author:
Found 4 papers, 3 papers with code
MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations
The motivation behind MIM-Refiner is rooted in the insight that optimal representations within MIM models generally reside in intermediate layers.
Ranked #1 on
Image Clustering
on ImageNet
Text-Guided Image Clustering
We, therefore, propose Text-Guided Image Clustering, i. e., generating text using image captioning and visual question-answering (VQA) models and subsequently clustering the generated text.
Contrastive Tuning: A Little Help to Make Masked Autoencoders Forget
In this work, we study how to combine the efficiency and scalability of MIM with the ability of ID to perform downstream classification in the absence of large amounts of labeled data.
Ranked #1 on
Image Clustering
on Imagenet-dog-15
(using extra training data)
Deep Clustering With Consensus Representations
Further, we propose DECCS (Deep Embedded Clustering with Consensus representationS), a deep consensus clustering method that learns a consensus representation by enhancing the embedded space to such a degree that all ensemble members agree on a common clustering result.
