Related papers: Sparse Spatial Transformers for Few-Shot Learning

Few-shot classification which aims to recognize unseen classes using very limited samples has attracted more and more attention. Usually, it is formulated as a metric learning problem. The core issue of few-shot classification is how to…

Recent Few-Shot Learning (FSL) methods put emphasis on generating a discriminative embedding features to precisely measure the similarity between support and query sets. Current CNN-based cross-attention approaches generate discriminative…

Human visual recognition is a sparse process, where only a few salient visual cues are attended to rather than traversing every detail uniformly. However, most current vision networks follow a dense paradigm, processing every single visual…

Semantic segmentation based on sparse annotation has advanced in recent years. It labels only part of each object in the image, leaving the remainder unlabeled. Most of the existing approaches are time-consuming and often necessitate a…

Few-shot detection is a major task in pattern recognition which seeks to localize objects using models trained with few labeled data. One of the mainstream few-shot methods is transfer learning which consists in pretraining a detection…

Few-shot Semantic Segmentation (FSS) was proposed to segment unseen classes in a query image, referring to only a few annotated examples named support images. One of the characteristics of FSS is spatial inconsistency between query and…

Deep learning models have become the mainstream method for medical image segmentation, but they require a large manually labeled dataset for training and are difficult to extend to unseen categories. Few-shot segmentation(FSS) has the…

Learning expressive representations for high-dimensional yet sparse features has been a longstanding problem in information retrieval. Though recent deep learning methods can partially solve the problem, they often fail to handle the…

In this paper, we aim to tackle the challenging few-shot segmentation task from a new perspective. Typical methods follow the paradigm to firstly learn prototypical features from support images and then match query features in pixel-level…

Few-Shot Learning (FSL) alleviates the data shortage challenge via embedding discriminative target-aware features among plenty seen (base) and few unseen (novel) labeled samples. Most feature embedding modules in recent FSL methods are…

Few-shot Semantic Segmentation addresses the challenge of segmenting objects in query images with only a handful of annotated examples. However, many previous state-of-the-art methods either have to discard intricate local semantic features…

Few-shot learning often involves metric learning-based classifiers, which predict the image label by comparing the distance between the extracted feature vector and class representations. However, applying global pooling in the backend of…

Given new tasks with very little data$-$such as new classes in a classification problem or a domain shift in the input$-$performance of modern vision systems degrades remarkably quickly. In this work, we illustrate how the neural network…

Deep neural networks have emerged as powerful tools for learning operators defined over infinite-dimensional function spaces. However, existing theories frequently encounter difficulties related to dimensionality and limited…

Real world images often have highly imbalanced content density. Some areas are very uniform, e.g., large patches of blue sky, while other areas are scattered with many small objects. Yet, the commonly used successive grid downsampling…

Current few-shot learning models capture visual object relations in the so-called meta-learning setting under a fixed-resolution input. However, such models have a limited generalization ability under the scale and location mismatch between…

Single image-level annotations only correctly describe an often small subset of an image's content, particularly when complex real-world scenes are depicted. While this might be acceptable in many classification scenarios, it poses a…

Spatio-temporal sensor data in real-world systems is often sparse, noisy, and irregular, making latent field reconstruction fundamentally underconstrained. Under extreme sparsity, multiple physically plausible fields may remain consistent…

This paper presents a sparse representation-based classification approach with a novel dictionary construction procedure. By using the constructed dictionary sophisticated prior knowledge about the spatial nature of the image can be…

Few-shot object detection is a challenging but realistic scenario, where only a few annotated training images are available for training detectors. A popular approach to handle this problem is transfer learning, i.e., fine-tuning a detector…