34 datasets found

Self-supervised adversarial masking for 3D point cloud representation learning

The LeBenchmark7K dataset is a self-supervised representation of French speech.

Self-supervised ASR-TTS models suffer in out-of-domain data conditions. Here we propose an enhanced ASR-TTS model that incorporates two main features: 1) The ASR→TTS direction...

We develop techniques for refining representations for fine-grained classification and segmentation tasks in a self-supervised manner.

A self-supervised spatiotemporal representation learning approach for videos, combining temporal coherence and future clip order ranking.

Contrastive learning is one of the most successful paradigms for self-supervised learning (SSL). In a principled way, it considers two augmented views of the same image as...

Self-supervised learning of pretext-invariant representations.

Self-supervised visual representation learning framework for ranking random image views.

Self-supervised and semi-supervised learning for GANs

Geography-aware self-supervised learning

The dataset used in the paper is DINOv2, a vision foundation model trained on a large-scale dataset.

Multi-modality MRI masked autoencoder for self-supervised learning of multi-modality MRI

Adaptive Multi-head Contrastive Learning (AMCL) framework, which tackles intra- and inter-sample similarity and adaptive temperature mechanism re-weighting each similarity pair.

Self-supervised learning framework that maintains the relational consistency between instances under different augmentations.

T-Drive dataset for learning task-agnostic feature representations of geographic locations from unlabeled GPS trajectories

Probe data for learning task-agnostic feature representations of geographic locations from unlabeled GPS trajectories

GPS trajectory dataset for learning task-agnostic feature representations of geographic locations from unlabeled GPS trajectories

The dataset used in this paper is a self-supervised audio pre-training framework called HuBERT.

The dataset used in the paper is not explicitly described, but it is mentioned that the authors used the ImageNet, Places205, and VOC07 datasets for evaluation.

Contrastive multiview coding.