Related papers: Three Towers: Flexible Contrastive Learning with P…

Self-supervised pre-training of deep learning models with contrastive learning is a widely used technique in image analysis. Current findings indicate a strong potential for contrastive pre-training on medical images. However, further…

Iterative learning to infer approaches have become popular solvers for inverse problems. However, their memory requirements during training grow linearly with model depth, limiting in practice model expressiveness. In this work, we propose…

Contrastive pre-training on image-text pairs, exemplified by CLIP, becomes a standard technique for learning multi-modal visual-language representations. Although CLIP has demonstrated remarkable performance, training it from scratch on…

The popularity of self-supervised learning has made it possible to train models without relying on labeled data, which saves expensive annotation costs. However, most existing self-supervised contrastive learning methods often overlook the…

Contrastive learning has proven effective for pre-training image models on unlabeled data with promising results for tasks such as medical image classification. Using paired text (like radiological reports) during pre-training improves the…

Texture classification is a pivotal task in computer vision, presenting unique challenges due to high inter-class similarity and the sensitivity of structural patterns to scale and illumination changes. While Convolutional Neural Networks…

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…

The goal of text-to-image synthesis is to generate a visually realistic image that matches a given text description. In practice, the captions annotated by humans for the same image have large variance in terms of contents and the choice of…

In visual retrieval systems, updating the embedding model requires recomputing features for every piece of data. This expensive process is referred to as backfilling. Recently, the idea of backward compatible training (BCT) was proposed. To…

Contrastive learning has been used to learn a high-quality representation of the image in computer vision. However, contrastive learning is not widely utilized in natural language processing due to the lack of a general method of data…

Various contrastive learning approaches have been proposed in recent years and achieve significant empirical success. While effective and prevalent, contrastive learning has been less explored for time series data. A key component of…

We propose a novel unsupervised backlit image enhancement method, abbreviated as CLIP-LIT, by exploring the potential of Contrastive Language-Image Pre-Training (CLIP) for pixel-level image enhancement. We show that the open-world CLIP…

Multilingual vision-language (V&L) pre-training has achieved remarkable progress in learning universal representations across different modalities and languages. In spite of recent success, there still remain challenges limiting further…

Image enhancement is a significant research area in the fields of computer vision and image processing. In recent years, many learning-based methods for image enhancement have been developed, where the Look-up-table (LUT) has proven to be…

An effective framework for learning 3D representations for perception tasks is distilling rich self-supervised image features via contrastive learning. However, image-to point representation learning for autonomous driving datasets faces…

The existing contrastive learning methods widely adopt one-hot instance discrimination as pretext task for self-supervised learning, which inevitably neglects rich inter-instance similarities among natural images, then leading to potential…

Traditional supervised learning with deep neural networks requires a tremendous amount of labelled data to converge to a good solution. For 3D medical images, it is often impractical to build a large homogeneous annotated dataset for a…

We present a new approach to instill 4D dynamic object priors into learned 3D representations by unsupervised pre-training. We observe that dynamic movement of an object through an environment provides important cues about its objectness,…

Large-scale pre-trained models such as CodeBERT, GraphCodeBERT have earned widespread attention from both academia and industry. Attributed to the superior ability in code representation, they have been further applied in multiple…

Cross-modal representation learning learns a shared embedding between two or more modalities to improve performance in a given task compared to using only one of the modalities. Cross-modal representation learning from different data types…