Related papers: Projection Head is Secretly an Information Bottlen…
An effective technique for obtaining high-quality representations is adding a projection head on top of the encoder during training, then discarding it and using the pre-projection representations. Despite its proven practical…
We investigate the role of projection heads, also known as projectors, within the encoder-projector framework (e.g., SimCLR) used in contrastive learning. We aim to demystify the observed phenomenon where representations learned before…
Contrastive Learning (CL) has emerged as a powerful method for training feature extraction models using unlabeled data. Recent studies suggest that incorporating a linear projection head post-backbone significantly enhances model…
What matters for contrastive learning? We argue that contrastive learning heavily relies on informative features, or "hard" (positive or negative) features. Early works include more informative features by applying complex data…
Various graph contrastive learning models have been proposed to improve the performance of learning tasks on graph datasets in recent years. While effective and prevalent, these models are usually carefully customized. In particular,…
The superior performance of some of today's state-of-the-art deep learning models is to some extent owed to extensive (self-)supervised contrastive pretraining on large-scale datasets. In contrastive learning, the network is presented with…
Many unsupervised hashing methods are implicitly established on the idea of reconstructing the input data, which basically encourages the hashing codes to retain as much information of original data as possible. However, this requirement…
Conventionally, during the knowledge distillation process (e.g. feature distillation), an additional projector is often required to perform feature transformation due to the dimension mismatch between the teacher and the student networks.…
Self-supervised representation learning (SSRL) methods have shown great success in computer vision. In recent studies, augmentation-based contrastive learning methods have been proposed for learning representations that are invariant or…
In knowledge distillation, previous feature distillation methods mainly focus on the design of loss functions and the selection of the distilled layers, while the effect of the feature projector between the student and the teacher remains…
In this paper we revisit the efficacy of knowledge distillation as a function matching and metric learning problem. In doing so we verify three important design decisions, namely the normalisation, soft maximum function, and projection…
In this paper, we are interested in understanding self-supervised pretraining through studying the capability that self-supervised representation pretraining methods learn part-aware representations. The study is mainly motivated by that…
Despite recent success of self-supervised based contrastive learning model for 3D point clouds representation, the adversarial robustness of such pre-trained models raised concerns. Adversarial contrastive learning (ACL) is considered an…
Recently, self-supervised representation learning gives further development in multimedia technology. Most existing self-supervised learning methods are applicable to packaged data. However, when it comes to streamed data, they are…
In deep learning, transferring information from a pretrained network to a downstream task by finetuning has many benefits. The choice of task head plays an important role in fine-tuning, as the pretrained and downstream tasks are usually…
Contrastive learning between different views of the data achieves outstanding success in the field of self-supervised representation learning and the learned representations are useful in broad downstream tasks. Since all supervision…
Contrastive learning has become a key component of self-supervised learning approaches for computer vision. By learning to embed two augmented versions of the same image close to each other and to push the embeddings of different images…
While deeper and wider neural networks are actively pushing the performance limits of various computer vision and machine learning tasks, they often require large sets of labeled data for effective training and suffer from extremely high…
Contrastive learning is a popular form of self-supervised learning that encourages augmentations (views) of the same input to have more similar representations compared to augmentations of different inputs. Recent attempts to theoretically…
Recently the surprising discovery of the Bootstrap Your Own Latent (BYOL) method by Grill et al. shows the negative term in contrastive loss can be removed if we add the so-called prediction head to the network. This initiated the research…