相关论文: Learning Placeholders for Open-Set Recognition

In Open Set Domain Adaptation (OSDA), large amounts of target samples are drawn from the implicit categories that never appear in the source domain. Due to the lack of their specific belonging, existing methods indiscriminately regard them…

Classification is one of the most popular and widely used supervised learning tasks, which categorizes objects into predefined classes based on known knowledge. Classification has been an important research topic in machine learning and…

While the majority of today's object class models provide only 2D bounding boxes, far richer output hypotheses are desirable including viewpoint, fine-grained category, and 3D geometry estimate. However, models trained to provide richer…

This paper presents a conformal prediction method for classification in highly imbalanced and open-set settings, where there are many possible classes and not all may be represented in the data. Existing approaches require a finite, known…

With the explosive 3D data growth, the urgency of utilizing zero-shot learning to facilitate data labeling becomes evident. Recently, methods transferring language or language-image pre-training models like Contrastive Language-Image…

Prototypical Learning is based on the idea that there is a point (which we call prototype) around which the embeddings of a class are clustered. It has shown promising results in scenarios with little labeled data or to design explainable…

3D recognition is the foundation of 3D deep learning in many emerging fields, such as autonomous driving and robotics.Existing 3D methods mainly focus on the recognition of a fixed set of known classes and neglect possible unknown classes…

Understanding the trustworthiness of a prediction yielded by a classifier is critical for the safe and effective use of AI models. Prior efforts have been proven to be reliable on small-scale datasets. In this work, we study the problem of…

Large language models are able to learn new tasks in context, where they are provided with instructions and a few annotated examples. However, the effectiveness of in-context learning is dependent on the provided context, and the…

In this work we propose a novel joint training method for Visual Place Recognition (VPR), which simultaneously learns a global descriptor and a pair classifier for re-ranking. The pair classifier can predict whether a given pair of images…

In classification, it is usual to observe that models trained on a given set of classes can generalize to previously unseen ones, suggesting the ability to learn beyond the initial task. This ability is often leveraged in the context of…

In machine learning, if the training data is an unbiased sample of an underlying distribution, then the learned classification function will make accurate predictions for new samples. However, if the training data is not an unbiased sample,…

Despite the remarkable progress in generative technology, the Janus-faced issues of intellectual property protection and malicious content supervision have arisen. Efforts have been paid to manage synthetic images by attributing them to a…

Classical semantic segmentation methods, including the recent deep learning ones, assume that all classes observed at test time have been seen during training. In this paper, we tackle the more realistic scenario where unexpected objects of…

Modern pattern recognition tasks use complex algorithms that take advantage of large datasets to make more accurate predictions than traditional algorithms such as decision trees or k-nearest-neighbor better suited to describe simple…

We propose a novel memory-modular learner for image classification that separates knowledge memorization from reasoning. Our model enables effective generalization to new classes by simply replacing the memory contents, without the need for…

We study the open-set label shift problem, where the test data may include a novel class absent from training. This setting is challenging because both the class proportions and the distribution of the novel class are not identifiable…

Open set recognition enables deep neural networks (DNNs) to identify samples of unknown classes, while maintaining high classification accuracy on samples of known classes. Existing methods basing on auto-encoder (AE) and prototype learning…

In many applications, data is easy to acquire but expensive and time-consuming to label prominent examples include medical imaging and NLP. This disparity has only grown in recent years as our ability to collect data improves. Under these…

Open-world instance segmentation is a rising task, which aims to segment all objects in the image by learning from a limited number of base-category objects. This task is challenging, as the number of unseen categories could be hundreds of…