Related papers: SAMCLR: Contrastive pre-training on complex scenes…
We present a comparative study on how and why contrastive learning (CL) and masked image modeling (MIM) differ in their representations and in their performance of downstream tasks. In particular, we demonstrate that self-supervised Vision…
Contrastive language-image pretraining (CLIP) using image-text pairs has achieved impressive results on image classification in both zero-shot and transfer learning settings. However, we show that directly applying such models to recognize…
Content-based image retrieval (CBIR) with self-supervised learning (SSL) accelerates clinicians' interpretation of similar images without manual annotations. We develop a CBIR from the contrastive learning SimCLR and incorporate a…
While contrastive learning (CL) shows considerable promise in self-supervised representation learning, its deployment on resource-constrained devices remains largely underexplored. The substantial computational demands required for training…
We propose SigCLR: Sigmoid Contrastive Learning of Visual Representations. SigCLR utilizes the logistic loss that only operates on pairs and does not require a global view as in the cross-entropy loss used in SimCLR. We show that logistic…
Contrastive learning predicts whether two images belong to the same category by training a model to make their feature representations as close or as far away as possible. In this paper, we rethink how to mine samples in contrastive…
Image-Text pretraining on web-scale image caption datasets has become the default recipe for open vocabulary classification and retrieval models thanks to the success of CLIP and its variants. Several works have also used CLIP features for…
A key requirement for the success of supervised deep learning is a large labeled dataset - a condition that is difficult to meet in medical image analysis. Self-supervised learning (SSL) can help in this regard by providing a strategy to…
In the field of vision-language contrastive learning, models such as CLIP capitalize on matched image-caption pairs as positive examples and leverage within-batch non-matching pairs as negatives. This approach has led to remarkable outcomes…
The recent advances in representation learning inspire us to take on the challenging problem of unsupervised image classification tasks in a principled way. We propose ContraCluster, an unsupervised image classification method that combines…
We introduce SuperClass, a super simple classification method for vision-language pre-training on image-text data. Unlike its contrastive counterpart CLIP who contrast with a text encoder, SuperClass directly utilizes tokenized raw text as…
In-context learning (ICL) enables generalization to new tasks with minimal labeled data. However, mainstream ICL approaches rely on a gridding strategy, which lacks the flexibility required for vision applications. We introduce Temporal, a…
Contrastive learning is commonly used as a method of self-supervised learning with the "anchor" and "positive" being two random augmentations of a given input image, and the "negative" is the set of all other images. However, the…
Recent advancements in self-supervised learning have demonstrated that effective visual representations can be learned from unlabeled images. This has led to increased interest in applying self-supervised learning to the medical domain,…
Promising results have been achieved in image classification problems by exploiting the discriminative power of sparse representations for classification (SRC). Recently, it has been shown that the use of \emph{class-specific}…
Recently, contrastive learning has largely advanced the progress of unsupervised visual representation learning. Pre-trained on ImageNet, some self-supervised algorithms reported higher transfer learning performance compared to…
Computer vision tasks are traditionally defined and evaluated using semantic categories. However, it is known to the field that semantic classes do not necessarily correspond to a unique visual class (e.g. inside and outside of a car).…
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…
Aligning image and text encoders from scratch using contrastive learning requires large amounts of paired image-text data. We alleviate this need by aligning individually pre-trained language and vision representation models using a much…
Satellite imagery is being leveraged for many societally critical tasks across climate, economics, and public health. Yet, because of heterogeneity in landscapes (e.g. how a road looks in different places), models can show disparate…