相关论文: Self-Supervised Visual Representation Learning on …

While data-driven approaches excel at many image analysis tasks, the performance of these approaches is often limited by a shortage of annotated data available for training. Recent work in semi-supervised learning has shown that meaningful…

Self-supervised learning methods have witnessed a recent surge of interest after proving successful in multiple application fields. In this work, we leverage these techniques, and we propose 3D versions for five different self-supervised…

Food image classification serves as the foundation of image-based dietary assessment to predict food categories. Since there are many different food classes in real life, conventional models cannot achieve sufficiently high accuracy.…

A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning…

Semisupervised learning is a learning standard which deals with the study of how computers and natural systems such as human beings acquire knowledge in the presence of both labeled and unlabeled data. Semisupervised learning based methods…

We address the problem of learning self-supervised representations from unlabeled image collections. Unlike existing approaches that attempt to learn useful features by maximizing similarity between augmented versions of each input image or…

Deep learning-based food recognition has made significant progress in predicting food types from eating occasion images. However, two key challenges hinder real-world deployment: (1) continuously learning new food classes without forgetting…

Food image classification is challenging for real-world applications since existing methods require static datasets for training and are not capable of learning from sequentially available new food images. Online continual learning aims to…

In this paper, we are interested in modeling a how-to instructional procedure, such as a cooking recipe, with a meaningful and rich high-level representation. Specifically, we propose to represent cooking recipes and food images as cooking…

Hyperspectral image (HSI) classification is gaining a lot of momentum in present time because of high inherent spectral information within the images. However, these images suffer from the problem of curse of dimensionality and usually…

Accurate food intake monitoring is crucial for maintaining a healthy diet and preventing nutrition-related diseases. With the diverse range of foods consumed across various cultures, classic food classification models have limitations due…

Deep learning models trained in a fully supervised manner have been shown to rely on so-called "shortcut" features. Shortcut features are inputs that are associated with the outcome of interest in the training data, but are either no longer…

Accurate dietary intake estimation is critical for informing policies and programs to support healthy eating, as malnutrition has been directly linked to decreased quality of life. However self-reporting methods such as food diaries suffer…

Semi-supervised learning aims to boost the accuracy of a model by exploring unlabeled images. The state-of-the-art methods are consistency-based which learn about unlabeled images by encouraging the model to give consistent predictions for…

Automatically constructing a food diary that tracks the ingredients consumed can help people follow a healthy diet. We tackle the problem of food ingredients recognition as a multi-label learning problem. We propose a method for adapting a…

With the arrival of convolutional neural networks, the complex problem of food recognition has experienced an important improvement in recent years. The best results have been obtained using methods based on very deep convolutional neural…

Deep neural networks often struggle to learn robust representations in the presence of dataset biases, leading to suboptimal generalization on unbiased datasets. This limitation arises because the models heavily depend on peripheral and…

Self-supervised learning has emerged as a powerful paradigm for label-free model pretraining, particularly in the video domain, where manual annotation is costly and time-intensive. However, existing self-supervised approaches employ…

Learning robust and effective representations of visual data is a fundamental task in computer vision. Traditionally, this is achieved by training models with labeled data which can be expensive to obtain. Self-supervised learning attempts…

We aim to estimate food portion size, a property that is strongly related to the presence of food object in 3D space, from single monocular images under real life setting. Specifically, we are interested in end-to-end estimation of food…