Related papers: Solving Semi-Supervised Few-Shot Learning from an …
Self supervised learning (SSL) has become a very successful technique to harness the power of unlabeled data, with no annotation effort. A number of developed approaches are evolving with the goal of outperforming supervised alternatives,…
In the last few years, unpaired image-to-image translation has witnessed remarkable progress. Although the latest methods are able to generate realistic images, they crucially rely on a large number of labeled images. Recently, some methods…
With the advent of strong pre-trained natural language processing models like BERT, DeBERTa, MiniLM, T5, the data requirement for industries to fine-tune these models to their niche use cases has drastically reduced (typically to a few…
Semi-supervised learning (SSL) methods effectively leverage unlabeled data to improve model generalization. However, SSL models often underperform in open-set scenarios, where unlabeled data contain outliers from novel categories that do…
Large-scale pre-trained Vision-Language Models (VLMs) have exhibited impressive zero-shot performance and transferability, allowing them to adapt to downstream tasks in a data-efficient manner. However, when only a few labeled samples are…
Semi-supervised learning (SSL) has emerged as a promising paradigm in medical image segmentation, offering competitive performance while substantially reducing the need for extensive manual annotation. When combined with active learning…
Semi-Supervised Learning (SSL) has been an effective way to leverage abundant unlabeled data with extremely scarce labeled data. However, most SSL methods are commonly based on instance-wise consistency between different data…
Semi-supervised learning (SSL) is one of the dominant approaches to address the annotation bottleneck of supervised learning. Recent SSL methods can effectively leverage a large repository of unlabeled data to improve performance while…
We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the…
Lifelong learning aims to accumulate knowledge and alleviate catastrophic forgetting when learning tasks sequentially. However, existing lifelong language learning methods only focus on the supervised learning setting. Unlabeled data, which…
Self-training via pseudo labeling is a conventional, simple, and popular pipeline to leverage unlabeled data. In this work, we first construct a strong baseline of self-training (namely ST) for semi-supervised semantic segmentation via…
Few-shot learning (FSL) has shown promise in vision but remains largely unexplored for \emph{industrial} time-series data, where annotating every new defect is prohibitively expensive. We present a systematic FSL study on screw-fastening…
Unsupervised learning is argued to be the dark matter of human intelligence. To build in this direction, this paper focuses on unsupervised learning from an abundance of unlabeled data followed by few-shot fine-tuning on a downstream…
Deep learning based models have excelled in many computer vision tasks and appear to surpass humans' performance. However, these models require an avalanche of expensive human labeled training data and many iterations to train their large…
3D Referring Expression Segmentation (3D-RES) typically requires extensive instance-level annotations, which are time-consuming and costly. Semi-supervised learning (SSL) mitigates this by using limited labeled data alongside abundant…
With the increasing computing power of edge devices, Federated Learning (FL) emerges to enable model training without privacy concerns. The majority of existing studies assume the data are fully labeled on the client side. In practice,…
Object detection is an essential and fundamental task in computer vision and satellite image processing. Existing deep learning methods have achieved impressive performance thanks to the availability of large-scale annotated datasets. Yet,…
The ability of robots to manipulate objects relies heavily on their aptitude for visual perception. In domains characterized by cluttered scenes and high object variability, most methods call for vast labeled datasets, laboriously…
Vision Language Models (VLMs) have demonstrated remarkable performance in open-world zero-shot visual recognition. However, their potential in space-related applications remains largely unexplored. In the space domain, accurate manual…
Quality of deep convolutional neural network predictions strongly depends on the size of the training dataset and the quality of the annotations. Creating annotations, especially for 3D medical image segmentation, is time-consuming and…