相关论文: TriBYOL: Triplet BYOL for Self-Supervised Represen…

We present Masked Audio-Video Learners (MAViL) to train audio-visual representations. Our approach learns with three complementary forms of self-supervision: (1) reconstruction of masked audio and video input data, (2) intra- and…

In this work, we propose a novel methodology for self-supervised learning for generating global and local attention-aware visual features. Our approach is based on training a model to differentiate between specific image transformations of…

Self-supervised learning (SSL) methods aim to learn view-invariant representations by maximizing the similarity between the features extracted from different crops of the same image regardless of cropping size and content. In essence, this…

Recently, contrastive self-supervised learning, where the proximity of representations is determined based on the identities of samples, has made remarkable progress in unsupervised representation learning. SimSiam is a well-known example…

Incorporating heterogeneous representations from different architectures has facilitated various vision tasks, e.g., some hybrid networks combine transformers and convolutions. However, complementarity between such heterogeneous…

In this paper, we propose a new self-supervised learning (SSL) method for representations that enable logic operations. Representation learning has been applied to various tasks, such as image generation and retrieval. The logical…

The increasing complexity of modern deep neural network models and the expanding sizes of datasets necessitate the development of optimized and scalable training methods. In this white paper, we addressed the challenge of efficiently…

The self-supervised learning (SSL) paradigm is an essential exploration area, which tries to eliminate the need for expensive data labeling. Despite the great success of SSL methods in computer vision and natural language processing, most…

While neural networks for learning representation of multi-view data have been previously proposed as one of the state-of-the-art multi-view dimension reduction techniques, how to make the representation discriminative with only a small…

Combining the respective advantages of cross-modality images can compensate for the lack of information in the single modality, which has attracted increasing attention of researchers into multi-modal image matching tasks. Meanwhile, due to…

Deep learning based computer vision fails to work when labeled images are scarce. Recently, Meta learning algorithm has been confirmed as a promising way to improve the ability of learning from few images for computer vision. However,…

Self-supervised learning has shown its great potential to extract powerful visual representations without human annotations. Various works are proposed to deal with self-supervised learning from different perspectives: (1) contrastive…

In this work, we propose to progressively increase the training difficulty during learning a neural network model via a novel strategy which we call mini-batch trimming. This strategy makes sure that the optimizer puts its focus in the…

Clustering-based approach has proved effective in dealing with unsupervised domain adaptive person re-identification (ReID) tasks. However, existing works along this approach still suffer from noisy pseudo labels and the unreliable…

Self-supervised learning (SSL) aims to eliminate one of the major bottlenecks in representation learning - the need for human annotations. As a result, SSL holds the promise to learn representations from data in-the-wild, i.e., without the…

While contrastive learning is proven to be an effective training strategy in computer vision, Natural Language Processing (NLP) is only recently adopting it as a self-supervised alternative to Masked Language Modeling (MLM) for improving…

Multimodal self-supervised representation learning has consistently proven to be a highly effective method in medical image analysis, offering strong task performance and producing biologically informed insights. However, these methods…

Since the advent of deep learning, neural networks have demonstrated remarkable results in many visual recognition tasks, constantly pushing the limits. However, the state-of-the-art approaches are largely unsuitable in scarce data regimes.…

Self-supervised learning aims to learn representations from the data itself without explicit manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning - the ability to scale to large amount of data because…

In robotic manipulation, acquiring samples is extremely expensive because it often requires interacting with the real world. Traditional image-level data augmentation has shown the potential to improve sample efficiency in various machine…