相关论文: The Championship-Winning Solution for the 5th CLVI…

Pseudo-label-based semi-supervised learning (SSL) has achieved great success on raw data utilization. However, its training procedure suffers from confirmation bias due to the noise contained in self-generated artificial labels. Moreover,…

Continual learning (CL) enables models to adapt to new tasks and environments without forgetting previously learned knowledge. While current CL setups have ignored the relationship between labels in the past task and the new task with or…

The continuous changes in the world have resulted in the performance regression of neural networks. Therefore, continual learning (CL) area gradually attracts the attention of more researchers. For edge intelligence, the CL model not only…

Continual learning (CL) aims to learn a sequence of tasks without forgetting the previously acquired knowledge. However, recent CL advances are restricted to supervised continual learning (SCL) scenarios. Consequently, they are not scalable…

A fundamental limitation of applying semi-supervised learning in real-world settings is the assumption that unlabeled test data contains only classes previously encountered in the labeled training data. However, this assumption rarely holds…

This paper presents our contribution to the ChaLearn Challenge 2015 on Cultural Event Classification. The challenge in this task is to automatically classify images from 50 different cultural events. Our solution is based on the combination…

Class-incremental learning (CIL) suffers from the notorious dilemma between learning newly added classes and preserving previously learned class knowledge. That catastrophic forgetting issue could be mitigated by storing historical data for…

Generalized Category Discovery (GCD) aims to identify a mix of known and novel categories within unlabeled data sets, providing a more realistic setting for image recognition. Essentially, GCD needs to remember existing patterns thoroughly…

This paper studies the problem of novel category discovery on single- and multi-modal data with labels from different but relevant categories. We present a generic, end-to-end framework to jointly learn a reliable representation and assign…

Contrastive Learning (CL) has been proved to be a powerful self-supervised approach for a wide range of domains, including computer vision and graph representation learning. However, the incremental learning issue of CL has rarely been…

Supervised Continual learning involves updating a deep neural network (DNN) from an ever-growing stream of labeled data. While most work has focused on overcoming catastrophic forgetting, one of the major motivations behind continual…

Partially-supervised learning can be challenging for segmentation due to the lack of supervision for unlabeled structures, and the methods directly applying fully-supervised learning could lead to incompatibility, meaning ground truth is…

Long-tailed semi-supervised learning poses a significant challenge in training models with limited labeled data exhibiting a long-tailed label distribution. Current state-of-the-art LTSSL approaches heavily rely on high-quality…

The current dominant paradigm when building a machine learning model is to iterate over a dataset over and over until convergence. Such an approach is non-incremental, as it assumes access to all images of all categories at once. However,…

Non-Centralized Continual Learning (NCCL) has become an emerging paradigm for enabling distributed devices such as vehicles and servers to handle streaming data from a joint non-stationary environment. To achieve high reliability and…

Learning feature correspondence is a foundational task in computer vision, holding immense importance for downstream applications such as visual odometry and 3D reconstruction. Despite recent progress in data-driven models, feature…

Continual Learning (CL) aims to develop agents emulating the human ability to sequentially learn new tasks while being able to retain knowledge obtained from past experiences. In this paper, we introduce the novel problem of…

This paper identifies the flaws in existing open-world learning approaches and attempts to provide a complete picture in the form of \textbf{True Open-World Learning}. We accomplish this by proposing a comprehensive generalize-able…

Semi-supervised learning methods have shown promising results in solving many practical problems when only a few labels are available. The existing methods assume that the class distributions of labeled and unlabeled data are equal;…

Supervised learning in large discriminative models is a mainstay for modern computer vision. Such an approach necessitates investing in large-scale human-annotated datasets for achieving state-of-the-art results. In turn, the efficacy of…