相关论文: Self-Supervised Contrastive Learning for Robust Au…

State-of-the-art speaker verification systems are inherently dependent on some kind of human supervision as they are trained on massive amounts of labeled data. However, manually annotating utterances is slow, expensive and not scalable to…

In Magnetic Resonance Imaging (MRI), image acquisitions are often undersampled in the measurement domain to accelerate the scanning process, at the expense of image quality. However, image quality is a crucial factor that influences the…

Image classification datasets exhibit a non-negligible fraction of mislabeled examples, often due to human error when one class superficially resembles another. This issue poses challenges in supervised contrastive learning (SCL), where the…

Following SimCSE, contrastive learning based methods have achieved the state-of-the-art (SOTA) performance in learning sentence embeddings. However, the unsupervised contrastive learning methods still lag far behind the supervised…

Self-supervised pre-training using so-called "pretext" tasks has recently shown impressive performance across a wide range of modalities. In this work, we advance self-supervised learning from permutations, by pre-training a model to…

Estimating correspondences between pairs of non-rigid deformable 3D shapes remains a significant challenge in computer vision and graphics. While deep functional map methods have become the go-to solution for addressing this problem, they…

Learning based methods are now ubiquitous for solving inverse problems, but their deployment in real-world applications is often hindered by the lack of ground truth references for training. Recent self-supervised learning strategies offer…

Self-supervised learning (especially contrastive learning) has attracted great interest due to its huge potential in learning discriminative representations in an unsupervised manner. Despite the acknowledged successes, existing contrastive…

Traditional supervised learning methods are hitting a bottleneck because of their dependency on expensive manually labeled data and their weaknesses such as limited generalization ability and vulnerability to adversarial attacks. A…

A common problem with segmentation of medical images using neural networks is the difficulty to obtain a significant number of pixel-level annotated data for training. To address this issue, we proposed a semi-supervised segmentation…

Existing text recognition methods usually need large-scale training data. Most of them rely on synthetic training data due to the lack of annotated real images. However, there is a domain gap between the synthetic data and real data, which…

Recent advancements in deep learning have proven highly effective in medical image classification, notably within histopathology. However, noisy labels represent a critical challenge in histopathology image classification, where accurate…

Having access to multi-modal cues (e.g. vision and audio) empowers some cognitive tasks to be done faster compared to learning from a single modality. In this work, we propose to transfer knowledge across heterogeneous modalities, even…

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…

Dense retrievers have achieved impressive performance, but their demand for abundant training data limits their application scenarios. Contrastive pre-training, which constructs pseudo-positive examples from unlabeled data, has shown great…

Contrastive learning applied to self-supervised representation learning has seen a resurgence in recent years, leading to state of the art performance in the unsupervised training of deep image models. Modern batch contrastive approaches…

Contrastive loss has significantly improved performance in supervised classification tasks by using a multi-viewed framework that leverages augmentation and label information. The augmentation enables contrast with another view of a single…

Learning semantically meaningful sentence embeddings is an open problem in natural language processing. In this work, we propose a sentence embedding learning approach that exploits both visual and textual information via a multimodal…

Contrastive self-supervised learning methods famously produce high quality transferable representations by learning invariances to different data augmentations. Invariances established during pre-training can be interpreted as strong…

Deep neural networks trained with standard cross-entropy loss memorize noisy labels, which degrades their performance. Most research to mitigate this memorization proposes new robust classification loss functions. Conversely, we propose a…