Related papers: Iterative Pseudo-Labeling with Deep Feature Annota…
Deep neural networks have achieved remarkable performance across various tasks when supplied with large-scale labeled data. However, the collection of labeled data can be time-consuming and labor-intensive. Semi-supervised learning (SSL),…
Learning semantic segmentation models under image-level supervision is far more challenging than under fully supervised setting. Without knowing the exact pixel-label correspondence, most weakly-supervised methods rely on external models to…
In this paper, we propose an iterative framework for self-supervised speaker representation learning based on a deep neural network (DNN). The framework starts with training a self-supervision speaker embedding network by maximizing…
Deep Active Learning (DAL) aims to reduce labeling costs in neural-network training by prioritizing the most informative unlabeled samples for annotation. Beyond selecting which samples to label, several DAL approaches further enhance data…
Unlike unsupervised approaches such as autoencoders that learn to reconstruct their inputs, this paper introduces an alternative approach to unsupervised feature learning called divergent discriminative feature accumulation (DDFA) that…
Weakly supervised video anomaly detection aims to identify abnormal events in videos using only video-level labels. Recently, two-stage self-training methods have achieved significant improvements by self-generating pseudo labels and…
Image matting requires high-quality pixel-level human annotations to support the training of a deep model in recent literature. Whereas such annotation is costly and hard to scale, significantly holding back the development of the research.…
Complex image processing and computer vision systems often consist of a processing pipeline of functional modules. We intend to replace parts or all of a target pipeline with deep neural networks to achieve benefits such as increased…
Unsupervised Domain Adaptation (UDA) methods for person Re-Identification (Re-ID) rely on target domain samples to model the marginal distribution of the data. To deal with the lack of target domain labels, UDA methods leverage information…
Semi-supervised learning, which leverages both annotated and unannotated data, is an efficient approach for medical image segmentation, where obtaining annotations for the whole dataset is time-consuming and costly. Traditional…
Source-free domain adaptation (SFDA) utilizes a pre-trained source model with unlabeled target data. Self-supervised SFDA techniques generate pseudolabels from the pre-trained source model, but these pseudolabels often contain noise due to…
Acquiring and training on large-scale labeled data can be impractical due to cost constraints. Additionally, the use of small training datasets can result in considerable variability in model outcomes, overfitting, and learning of spurious…
We present a technique to improve the transferability of deep representations learned on small labeled datasets by introducing self-supervised tasks as auxiliary loss functions. While recent approaches for self-supervised learning have…
Training deep neural networks requires many training samples, but in practice training labels are expensive to obtain and may be of varying quality, as some may be from trusted expert labelers while others might be from heuristics or other…
Enhancing the instruction-following ability of Large Language Models (LLMs) primarily demands substantial instruction-tuning datasets. However, the sheer volume of these imposes a considerable computational burden and annotation cost. To…
Human annotations are an important source of information in the development of natural language understanding approaches. As under the pressure of productivity annotators can assign different labels to a given text, the quality of produced…
Despite that deep learning has achieved state-of-the-art performance for medical image segmentation, its success relies on a large set of manually annotated images for training that are expensive to acquire. In this paper, we propose an…
Language model pre-training has proven to be useful in many language understanding tasks. In this paper, we investigate whether it is still helpful to add the self-training method in the pre-training step and the fine-tuning step. Towards…
Deep learning has proven to be an essential tool for medical image analysis. However, the need for accurately labeled input data, often requiring time- and labor-intensive annotation by experts, is a major limitation to the use of deep…
Deep learning perception models require a massive amount of labeled training data to achieve good performance. While unlabeled data is easy to acquire, the cost of labeling is prohibitive and could create a tremendous burden on companies or…