Semi-Supervised Image Classification
117 papers with code • 49 benchmarks • 13 datasets
Semi-supervised image classification leverages unlabelled data as well as labelled data to increase classification performance.
You may want to read some blog posts to get an overview before reading the papers and checking the leaderboards:
- An overview of proxy-label approaches for semi-supervised learning - Sebastian Ruder
- Semi-Supervised Learning in Computer Vision - Amit Chaudhary
( Image credit: Self-Supervised Semi-Supervised Learning )
Semi-supervised learning has proven to be a powerful paradigm for leveraging unlabeled data to mitigate the reliance on large labeled datasets.
The key insight of our model is to learn such representations by predicting the future in latent space by using powerful autoregressive models.
From an augmented view of an image, we train the online network to predict the target network representation of the same image under a different augmented view.
Convolutional neural networks are capable of learning powerful representational spaces, which are necessary for tackling complex learning tasks.
Semi-supervised learning (SSL) provides an effective means of leveraging unlabeled data to improve a model's performance.
This causes the embedding vectors of distorted versions of a sample to be similar, while minimizing the redundancy between the components of these vectors.