Related papers: Characterizing and Improving the Robustness of Sel…

Self-supervised learning has gained popularity because of its ability to avoid the cost of annotating large-scale datasets. It is capable of adopting self-defined pseudo labels as supervision and use the learned representations for several…

Data augmentation has become a de facto component for training high-performance deep image classifiers, but its potential is under-explored for object detection. Noting that most state-of-the-art object detectors benefit from fine-tuning a…

Self-supervised learning (SSL) has demonstrated its effectiveness in learning representations through comparison methods that align with human intuition. However, mainstream SSL methods heavily rely on high body datasets with single label,…

Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. However, current methods are still primarily applied to curated datasets like ImageNet. In this…

Despite the empirical successes of self-supervised learning (SSL) methods, it is unclear what characteristics of their representations lead to high downstream accuracies. In this work, we characterize properties that SSL representations…

Contrastive learning of auditory and visual perception has been extremely successful when investigated individually. However, there are still major questions on how we could integrate principles learned from both domains to attain effective…

Contrastive learning, a prominent approach within self-supervised learning, has demonstrated significant effectiveness in developing generalizable models for various applications involving natural images. However, recent research indicates…

Self-supervised visual representation methods are closing the gap with supervised learning performance. These methods rely on maximizing the similarity between embeddings of related synthetic inputs created through data augmentations. This…

Recent advances in large pre-trained vision-language models have demonstrated remarkable performance on zero-shot downstream tasks. Building upon this, recent studies, such as CoOp and CoCoOp, have proposed the use of prompt learning, where…

The application of deep neural networks to remote sensing imagery is often constrained by the lack of ground-truth annotations. Adressing this issue requires models that generalize efficiently from limited amounts of labeled data, allowing…

Self-supervised learning (SSL) has emerged as a promising solution for addressing the challenge of limited labeled data in deep neural networks (DNNs), offering scalability potential. However, the impact of design dependencies within the…

Deep neural networks have enabled major progresses in semantic segmentation. However, even the most advanced neural architectures suffer from important limitations. First, they are vulnerable to catastrophic forgetting, i.e. they perform…

Self-supervised deep learning methods have leveraged stereo images for training monocular depth estimation. Although these methods show strong results on outdoor datasets such as KITTI, they do not match performance of supervised methods on…

Self-supervised representation learning has made significant leaps fueled by progress in contrastive learning, which seeks to learn transformations that embed positive input pairs nearby, while pushing negative pairs far apart. While…

We consider the problem of unsupervised domain adaptation for image classification. To learn target-domain-aware features from the unlabeled data, we create a self-supervised pretext task by augmenting the unlabeled data with a certain type…

In recent years, self-supervised contrastive learning has emerged as a distinguished paradigm in the artificial intelligence landscape. It facilitates unsupervised feature learning through contrastive delineations at the instance level.…

Data augmentation for domain-specific image classification tasks often struggles to simultaneously address diversity, faithfulness, and label clarity of generated data, leading to suboptimal performance in downstream tasks. While existing…

Real-world low-light images captured by imaging devices suffer from poor visibility and require a domain-specific enhancement to produce artifact-free outputs that reveal details. In this paper, we propose an unpaired low-light image…

Recent contrastive methods show significant improvement in self-supervised learning in several domains. In particular, contrastive methods are most effective where data augmentation can be easily constructed e.g. in computer vision.…

Robust lane detection is essential for advanced driver assistance and autonomous driving, yet models trained on public datasets such as CULane often fail to generalise across different camera viewpoints. This paper addresses the challenge…