相关论文: Self-Training and Multi-Task Learning for Limited …

Detection of objects in cluttered indoor environments is one of the key enabling functionalities for service robots. The best performing object detection approaches in computer vision exploit deep Convolutional Neural Networks (CNN) to…

Instruction tuning for large language models (LLMs) has gained attention from researchers due to its ability to unlock the potential of LLMs in following instructions. While instruction tuning offers advantages for facilitating the…

Active learning is an iterative labeling process that is used to obtain a small labeled subset, despite the absence of labeled data, thereby enabling to train a model for supervised tasks such as text classification. While active learning…

Reducing the quantity of annotations required for supervised training is vital when labels are scarce and costly. This reduction is particularly important for semantic segmentation tasks involving 3D datasets, which are often significantly…

Recent years have witnessed an abundance of new publications and approaches on meta-learning. This community-wide enthusiasm has sparked great insights but has also created a plethora of seemingly different frameworks, which can be hard to…

Labeling data is often expensive and time-consuming, especially for tasks such as object detection and instance segmentation, which require dense labeling of the image. While few-shot object detection is about training a model on novel…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

Self-supervised pretraining has made few-shot learning possible for many NLP tasks. But the pretraining objectives are not typically adapted specifically for in-context few-shot learning. In this paper, we propose to use self-supervision in…

Object detectors do not work well when domains largely differ between training and testing data. To overcome this domain gap in object detection without requiring expensive annotations, we consider two problem settings: semi-supervised…

Though deep learning based scene text detection has achieved great progress, well-trained detectors suffer from severe performance degradation for different domains. In general, a tremendous amount of data is indispensable to train the…

Self-training for unsupervised domain adaptive object detection is a challenging task, of which the performance depends heavily on the quality of pseudo boxes. Despite the promising results, prior works have largely overlooked the…

Many machine learning algorithms are based on the assumption that training examples are drawn independently. However, this assumption does not hold anymore when learning from a networked sample because two or more training examples may…

We consider a new problem of few-shot learning of compact models. Meta-learning is a popular approach for few-shot learning. Previous work in meta-learning typically assumes that the model architecture during meta-training is the same as…

For specialized and dense downstream tasks such as object detection, labeling data requires expertise and can be very expensive, making few-shot and semi-supervised models much more attractive alternatives. While in the few-shot setup we…

Despite their recent successes in tackling many NLP tasks, large-scale pre-trained language models do not perform as well in few-shot settings where only a handful of training examples are available. To address this shortcoming, we propose…

Progress has been achieved recently in object detection given advancements in deep learning. Nevertheless, such tools typically require a large amount of training data and significant manual effort to label objects. This limits their…

It is well known that for some tasks, labeled data sets may be hard to gather. Therefore, we wished to tackle here the problem of having insufficient training data. We examined learning methods from unlabeled data after an initial training…

In this paper, we study teacher-student learning from the perspective of data initialization and propose a novel algorithm called Active Teacher(Source code are available at: \url{https://github.com/HunterJ-Lin/ActiveTeacher}) for…

Object detectors are typically learned on fully-annotated training data with fixed predefined categories. However, categories are often required to be increased progressively. Usually, only the original training set annotated with old…

Self-taught learning is a technique that uses a large number of unlabeled data as source samples to improve the task performance on target samples. Compared with other transfer learning techniques, self-taught learning can be applied to a…