Related papers: Learning to Count Anything: Reference-less Class-a…

Few-shot learning aims at rapidly adapting to novel categories with only a handful of samples at test time, which has been predominantly tackled with the idea of meta-learning. However, meta-learning approaches essentially learn across a…

We present a novel unsupervised framework for instance-level image-to-image translation. Although recent advances have been made by incorporating additional object annotations, existing methods often fail to handle images with multiple…

Unsupervised crowd counting is a challenging yet not largely explored task. In this paper, we explore it in a transfer learning setting where we learn to detect and count persons in an unlabeled target set by transferring bi-knowledge…

Incremental or continual learning has been extensively studied for image classification tasks to alleviate catastrophic forgetting, a phenomenon that earlier learned knowledge is forgotten when learning new concepts. For class incremental…

Referring image segmentation, the task of segmenting any arbitrary entities described in free-form texts, opens up a variety of vision applications. However, manual labeling of training data for this task is prohibitively costly, leading to…

We propose a method for the weakly supervised detection of objects in paintings. At training time, only image-level annotations are needed. This, combined with the efficiency of our multiple-instance learning method, enables one to learn…

Few-shot segmentation aims to train a segmentation model that can fast adapt to a novel task for which only a few annotated images are provided. Most recent models have adopted a prototype-based paradigm for few-shot inference. These…

Conventional training of a deep CNN based object detector demands a large number of bounding box annotations, which may be unavailable for rare categories. In this work we develop a few-shot object detector that can learn to detect novel…

Object counting aims to estimate the number of objects in images. The leading counting approaches focus on the single category counting task and achieve impressive performance. Note that there are multiple categories of objects in real…

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…

Unsupervised meta-learning aims to learn feature representations from unsupervised datasets that can transfer to downstream tasks with limited labeled data. In this paper, we propose a novel approach to unsupervised meta-learning that…

Any-shot image classification allows to recognize novel classes with only a few or even zero samples. For the task of zero-shot learning, visual attributes have been shown to play an important role, while in the few-shot regime, the effect…

Labeling training data is a key bottleneck in the modern machine learning pipeline. Recent weak supervision approaches combine labels from multiple noisy sources by estimating their accuracies without access to ground truth labels; however,…

Generative zero-shot learning (ZSL) methods typically synthesize visual features for unseen classes using predefined semantic attributes, followed by training a fully supervised classification model. While effective, these methods require…

Object recognition systems usually require fully complete manually labeled training data to train the classifier. In this paper, we study the problem of object recognition where the training samples are missing during the classifier…

Counterfactual instances are a powerful tool to obtain valuable insights into automated decision processes, describing the necessary minimal changes in the input space to alter the prediction towards a desired target. Most previous…

The field of visual few-shot classification aims at transferring the state-of-the-art performance of deep learning visual systems onto tasks where only a very limited number of training samples are available. The main solution consists in…

We propose a novel approach for unsupervised zero-shot learning (ZSL) of classes based on their names. Most existing unsupervised ZSL methods aim to learn a model for directly comparing image features and class names. However, this proves…

Modern classification models tend to struggle when the amount of annotated data is scarce. To overcome this issue, several neural few-shot classification models have emerged, yielding significant progress over time, both in Computer Vision…

In search, exploration, and reconnaissance tasks performed with autonomous ground vehicles, an image classification capability is needed for specifically identifying targeted objects (relevant classes) and at the same time recognize when a…