Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples

By Mahmoud Assran, Mathilde Caron, Ishan Misra, Piotr Bojanowski, Armand Joulin, Nicolas Ballas, Michael G. Rabbat. 2021

175 citations recorded by the source corpus.

This paper proposes a novel method of learning by predicting view assignments with support samples (PAWS). The method trains a model to minimize a consistency loss, which ensures that different views of the same unlabeled instance are assigned similar pseudo-labels. The pseudo-labels are generated non-parametrically, by comparing the representations of the image views to those of a set of randomly sampled labeled images. The distance between the view representations and labeled representations is used to provide a weighting over class labels, which we interpret as a soft pseudo-label. By non-parametrically incorporating labeled samples in this way, PAWS extends the distance-metric loss used in self-supervised methods such as BYOL and SwAV to the semi-supervised setting. Despite the simplicity of the approach, PAWS outperforms other semi-supervised methods across architectures, setting a new state-of-the-art for a ResNet-50 on ImageNet trained with either 10% or 1% of the labels, reaching 75.5% and 66.5% top-1 respectively. than the previous best methods. PAWS requires 4× to 12× less training

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

A soft nearest-neighbor framework for continual semi-supervised learning (2022, positive): “Previous work [3] showed that using a more powerful network such as wider or deeper ResNet can further improve performance.”
Are Large-scale Datasets Necessary for Self-Supervised Pre-training? (2021, unknown): “We consider subsets of ImageNet containing 10% and 1% of the total number of examples, and use the balanced (in terms of classes) subsets from [57].”
Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture (2023, background): “gated to prevent representation collapse, such as contrastive losses that explicitly push apart embeddings of negative examples [15,24,37], non-contrastive losses that minimize the informational redundancy across embeddings [10, 74], and clustering-based approaches that maximize the entropy of the a”
Masked Siamese Networks for Label-Efficient Learning (2022, methodology): “Most similar to our approach is DINO (Caron et al., 2021) which leverages a Siamese Network with a cross-entropy loss and a momentum encoder.”
Understanding Dimensional Collapse in Contrastive Self-supervised Learning (2021, background): “…2020; Zbontar et al., 2021; Bardes et al., 2021; Chen et al., 2020b; Dwibedi et al., 2021; Li et al., 2021; Misra & Maaten, 2020a; HaoChen et al., 2021; Assran et al., 2021; Caron et al., 2021) show that self-supervised representations have competitive performances compared with supervised ones.”