Related papers: Few-shot Single-view 3D Reconstruction with Memory…
We present a novel 3D shape reconstruction method which learns to predict an implicit 3D shape representation from a single RGB image. Our approach uses a set of single-view images of multiple object categories without viewpoint annotation,…
Recent approaches based on metric learning have achieved great progress in few-shot learning. However, most of them are limited to image-level representation manners, which fail to properly deal with the intra-class variations and spatial…
Traditional shape descriptors have been gradually replaced by convolutional neural networks due to their superior performance in feature extraction and classification. The state-of-the-art methods recognize object shapes via image…
We study many-class few-shot (MCFS) problem in both supervised learning and meta-learning settings. Compared to the well-studied many-class many-shot and few-class few-shot problems, the MCFS problem commonly occurs in practical…
In multi-contrast magnetic resonance imaging (MRI), compressed sensing theory can accelerate imaging by sampling fewer measurements within each contrast. The conventional optimization-based models suffer several limitations: strict…
Deep learning-based methods in computational microscopy have been shown to be powerful but in general face some challenges due to limited generalization to new types of samples and requirements for large and diverse training data. Here, we…
We present an approach for the reconstruction of textured 3D meshes of human heads from one or few views. Since such few-shot reconstruction is underconstrained, it requires prior knowledge which is hard to impose on traditional 3D…
Few-shot image classification(FSIC) aims to recognize novel classes given few labeled images from base classes. Recent works have achieved promising classification performance, especially for metric-learning methods, where a measure at only…
In this paper, we propose Global Context Convolutional Network (GCCN) for visual recognition. GCCN computes global features representing contextual information across image patches. These global contextual features are defined as local…
Recently proposed adversarial self-supervised learning methods usually require big batches and long training epochs to extract robust features, which will bring heavy computational overhead on platforms with limited resources. In order to…
Reconstruction of CT images from a limited set of projections through an object is important in several applications ranging from medical imaging to industrial settings. As the number of available projections decreases, traditional…
Feature quality is paramount for classification performance, particularly in few-shot scenarios. Contrastive learning, a widely adopted technique for enhancing feature quality, leverages sample relations to extract intrinsic features that…
Few-shot point cloud 3D object detection (FS3D) aims to identify and localise objects of novel classes from point clouds, using knowledge learnt from annotated base classes and novel classes with very few annotations. Thus far, this…
Single-image 3D reconstruction is a research challenge focused on predicting 3D object shapes from single-view images. This task requires significant data acquisition to predict both visible and occluded portions of the shape. Furthermore,…
Most 3D neural networks are trained from scratch owing to the lack of large-scale labeled 3D datasets. In this paper, we present a novel 3D pretraining method by leveraging 2D networks learned from rich 2D datasets. We propose the…
Few-shot object classification is the task of classifying objects in an image with limited number of examples as supervision. We propose a one-shot/few-shot classification model that can classify an object of any unseen class into a…
The rapid growth of visual content consumption across platforms necessitates automated video classification for age-suitability standards like the MPAA rating system (G, PG, PG-13, R). Traditional methods struggle with large labeled data…
Few-shot remote sensing image classification is challenging due to limited labeled samples and high variability in land-cover types. We propose a reconstruction-guided few-shot network (RGFS-Net) that enhances generalization to unseen…
Few-shot learning aims to recognize novel classes from a few examples. Although significant progress has been made in the image domain, few-shot video classification is relatively unexplored. We argue that previous methods underestimate the…
Recently, learning frameworks have shown the capability of inferring the accurate shape, pose, and texture of an object from a single RGB image. However, current methods are trained on image collections of a single category in order to…