Related papers: Sample-Specific Debiasing for Better Image-Text Mo…

Treating texts as images, combining prompts with textual labels for prompt tuning, and leveraging the alignment properties of CLIP have been successfully applied in zero-shot multi-label image recognition. Nonetheless, relying solely on…

Contrastive learning (CL) is a popular technique for self-supervised learning (SSL) of visual representations. It uses pairs of augmentations of unlabeled training examples to define a classification task for pretext learning of a deep…

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.…

In recent years, several unsupervised, "contrastive" learning algorithms in vision have been shown to learn representations that perform remarkably well on transfer tasks. We show that this family of algorithms maximizes a lower bound on…

In this work, we evaluate contrastive models for the task of image retrieval. We hypothesise that models that are learned to encode semantic similarity among instances via discriminative learning should perform well on the task of image…

Asymmetric appearance between positive pair effectively reduces the risk of representation degradation in contrastive learning. However, there are still a mass of appearance similarities between positive pair constructed by the existing…

Contrastive learning has been frequently investigated to learn effective representations for text clustering tasks. While existing contrastive learning-based text clustering methods only focus on modeling instance-wise semantic similarity…

Dense retrieval (DR) has shown promising results in information retrieval. In essence, DR requires high-quality text representations to support effective search in the representation space. Recent studies have shown that pre-trained…

Recent self-supervised representation learning techniques have largely closed the gap between supervised and unsupervised learning on ImageNet classification. While the particulars of pretraining on ImageNet are now relatively well…

Understanding of spatial attributes is central to effective 3D radiology image analysis where crop-based learning is the de facto standard. Given an image patch, its core spatial properties (e.g., position & orientation) provide helpful…

Learning visual representations of medical images (e.g., X-rays) is core to medical image understanding but its progress has been held back by the scarcity of human annotations. Existing work commonly relies on fine-tuning weights…

Learning discriminative representations of unlabelled data is a challenging task. Contrastive self-supervised learning provides a framework to learn meaningful representations using learned notions of similarity measures from simple pretext…

Reliably detecting diseases using relevant biological information is crucial for real-world applicability of deep learning techniques in medical imaging. We debias deep learning models during training against unknown bias - without…

Supervised learning for semantic segmentation requires a large number of labeled samples, which is difficult to obtain in the field of remote sensing. Self-supervised learning (SSL), can be used to solve such problems by pre-training a…

In seismic interpretation, pixel-level labels of various rock structures can be time-consuming and expensive to obtain. As a result, there oftentimes exists a non-trivial quantity of unlabeled data that is left unused simply because…

Existing contrastive language-image pre-training aims to learn a joint representation by matching abundant image-text pairs. However, the number of image-text pairs in medical datasets is usually orders of magnitude smaller than that in…

Contrastive representation learning encourages data representation to make semantically similar pairs closer than randomly drawn negative samples, which has been successful in various domains such as vision, language, and graphs. Recent…

Graph representation learning has long been an important yet challenging task for various real-world applications. However, their downstream tasks are mainly performed in the settings of supervised or semi-supervised learning. Inspired by…

Dense correspondence across semantically related images has been extensively studied, but still faces two challenges: 1) large variations in appearance, scale and pose exist even for objects from the same category, and 2) labeling…

Semi-supervised learning (SSL), which aims at leveraging a few labeled images and a large number of unlabeled images for network training, is beneficial for relieving the burden of data annotation in medical image segmentation. According to…