相关论文: Using Shape to Categorize: Low-Shot Learning with …

Recent research has seen numerous supervised learning-based methods for 3D shape segmentation and remarkable performance has been achieved on various benchmark datasets. These supervised methods require a large amount of annotated data to…

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…

Humans are able to learn to recognize new objects even from a few examples. In contrast, training deep-learning-based object detectors requires huge amounts of annotated data. To avoid the need to acquire and annotate these huge amounts of…

Few-shot learning (FSL) techniques seek to learn the underlying patterns in data using fewer samples, analogous to how humans learn from limited experience. In this limited-data scenario, the challenges associated with deep neural networks,…

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…

Zero-shot learning, which aims to recognize new categories that are not included in the training set, has gained popularity owing to its potential ability in the real-word applications. Zero-shot learning models rely on learning an…

The impressive performance of deep convolutional neural networks in single-view 3D reconstruction suggests that these models perform non-trivial reasoning about the 3D structure of the output space. Recent work has challenged this belief,…

Few-shot learning (FSL) enables object detection models to recognize novel classes given only a few annotated examples, thereby reducing expensive manual data labeling. This survey examines recent FSL advances for video and 3D object…

Humans are capable of learning new concepts from small numbers of examples. In contrast, supervised deep learning models usually lack the ability to extract reliable predictive rules from limited data scenarios when attempting to classify…

Since the advent of deep learning, neural networks have demonstrated remarkable results in many visual recognition tasks, constantly pushing the limits. However, the state-of-the-art approaches are largely unsuitable in scarce data regimes.…

We introduce OpenShape, a method for learning multi-modal joint representations of text, image, and point clouds. We adopt the commonly used multi-modal contrastive learning framework for representation alignment, but with a specific focus…

By describing the features and abstractions of our world, language is a crucial tool for human learning and a promising source of supervision for machine learning models. We use language to improve few-shot visual classification in the…

The goal of few-shot classification is to classify new categories with few labeled examples within each class. Nowadays, the excellent performance in handling few-shot classification problems is shown by metric-based meta-learning methods.…

Low-shot visual learning---the ability to recognize novel object categories from very few examples---is a hallmark of human visual intelligence. Existing machine learning approaches fail to generalize in the same way. To make progress on…

Zero-shot learning extends the conventional object classification to the unseen class recognition by introducing semantic representations of classes. Existing approaches predominantly focus on learning the proper mapping function for…

The goal of object-centric representation learning is to decompose visual scenes into a structured representation that isolates the entities. Recent successes have shown that object-centric representation learning can be scaled to…

As a consequence of an ever-increasing number of service robots, there is a growing demand for highly accurate real-time 3D object recognition. Considering the expansion of robot applications in more complex and dynamic environments,it is…

Object detection has achieved a huge breakthrough with deep neural networks and massive annotated data. However, current detection methods cannot be directly transferred to the scenario where the annotated data is scarce due to the severe…

We propose a novel technique for producing high-quality 3D models that match a given target object image or scan. Our method is based on retrieving an existing shape from a database of 3D models and then deforming its parts to match the…

For many applications, robots will need to be incrementally trained to recognize the specific objects needed for an application. This paper presents a practical system for incrementally training a robot to recognize different object…