相关论文: Multi Positive Contrastive Learning with Pose-Cons…

Contrastive learning (CL) aims to learn useful representation without relying on expert annotations in the context of medical image segmentation. Existing approaches mainly contrast a single positive vector (i.e., an augmentation of the…

Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples via a one-vs-many softmax cross-entropy loss. By…

To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level prediction and…

Modern natural language processing (NLP) methods employ self-supervised pretraining objectives such as masked language modeling to boost the performance of various application tasks. These pretraining methods are frequently extended with…

Predicting socioeconomic indicators within urban regions is crucial for fostering inclusivity, resilience, and sustainability in cities and human settlements. While pioneering studies have attempted to leverage multi-modal data for…

For human pose estimation in still images, this paper proposes three semi- and weakly-supervised learning schemes. While recent advances of convolutional neural networks improve human pose estimation using supervised training data, our…

Contrastive learning based on instance discrimination trains model to discriminate different transformations of the anchor sample from other samples, which does not consider the semantic similarity among samples. This paper proposes a new…

Contrastive learning is a cornerstone underlying recent progress in multi-view and multimodal learning, e.g., in representation learning with image/caption pairs. While its effectiveness is not yet fully understood, a line of recent work…

Multi-modal generative AI systems, such as those combining vision and language, rely on contrastive pre-training to learn representations across different modalities. While their practical benefits are widely acknowledged, a rigorous…

Recently, pretext-task based methods are proposed one after another in self-supervised video feature learning. Meanwhile, contrastive learning methods also yield good performance. Usually, new methods can beat previous ones as claimed that…

This paper introduces a new architecture for human pose estimation using a multi- layer convolutional network architecture and a modified learning technique that learns low-level features and higher-level weak spatial models. Unconstrained…

3D human pose and shape estimation from monocular images has been an active research area in computer vision. Existing deep learning methods for this task rely on high-resolution input, which however, is not always available in many…

Many contrastive representation learning methods learn a single global representation of an entire image. However, dense contrastive representation learning methods such as DenseCL (Wang et al., 2021) can learn better representations for…

We present a contrastive learning framework based on in-the-wild hand images tailored for pre-training 3D hand pose estimators, dubbed HandCLR. Pre-training on large-scale images achieves promising results in various tasks, but prior 3D…

We introduce a robust algorithm for face verification, i.e., deciding whether twoimages are of the same person or not. Our approach is a novel take on the idea ofusing deep generative networks for adversarial robustness. We use the…

Recently, some contrastive learning methods have been proposed to simultaneously learn representations and clustering assignments, achieving significant improvements. However, these methods do not take the category information and…

Contrastive learning has been widely applied to graph representation learning, where the view generators play a vital role in generating effective contrastive samples. Most of the existing contrastive learning methods employ pre-defined…

Generating new images with desired properties (e.g. new view/poses) from source images has been enthusiastically pursued recently, due to its wide range of potential applications. One way to ensure high-quality generation is to use multiple…

Motivated by the need for estimating the 3D pose of arbitrary objects, we consider the challenging problem of class-agnostic object viewpoint estimation from images only, without CAD model knowledge. The idea is to leverage features learned…

We propose a new algorithm for training generative adversarial networks that jointly learns latent codes for both identities (e.g. individual humans) and observations (e.g. specific photographs). By fixing the identity portion of the latent…