scholar.google.com › citations
Jun 7, 2022 · In this paper, we aim to leverage the abundant unlabeled data from a target domain to improve the performance of a pre-trained zero-shot ...
Feb 1, 2023 · This paper introduces MUST (MASKED UNSUPERVISED SELF-TRAINING) to improve the performance of CLIP-like models in zero-shot recognition. Based on ...
This paper proposes Masked Unsupervised Self-Training (MUST), a new unsupervised adaptation method which leverages two different and complementary sources ...
Jun 7, 2022 · In this paper, we aim to leverage the abundant unlabeled data to improve the performance of a pre-trained zero-shot classifier on downstream ...
Masked Unsupervised Self-training for Zero-shot Image Classification ... This is the PyTorch code of the MUST paper. The repository supports finetuning a CLIP ...
People also ask
Is Zero Shot learning unsupervised learning?
What is image classification using unsupervised learning?
What is self supervised learning in image classification?
What is zero shot learning for classification?
This paper presents contrastive-tuning, a simple method employing contrastive training to align image and text models while still taking advantage of their pre ...
We propose a Self Structural Semantic Alignment (S 3 A ) framework, to address the challenging Realistic Zero-Shot Classification problem.
UNITE first employs self-supervised pre-training to promote discriminative feature learning on target domain videos using a teacher-guided masked distillation ...
Our results emphasize the cooperation between the self-training and our CVPR structural alignment approach. Our approach exhibits superiority over other prompt ...
Self-training is a simple semi-supervised learning approach: Unlabelled examples that attract high-confidence predictions are labelled with their ...