相关论文: L3A: Label-Augmented Analytic Adaptation for Multi…

Class-Incremental Learning (CIL) aims to continuously acquire new categories while preserving previously learned knowledge. Recently, Contrastive Language-Image Pre-trained (CLIP) models have shown strong potential for CIL due to their…

Class imbalance is an inherent characteristic of multi-label data that hinders most multi-label learning methods. One efficient and flexible strategy to deal with this problem is to employ sampling techniques before training a multi-label…

Class Incremental Learning (CIL) aims at learning a multi-class classifier in a phase-by-phase manner, in which only data of a subset of the classes are provided at each phase. Previous works mainly focus on mitigating forgetting in phases…

Machine learning models are increasingly being utilized across various fields and tasks due to their outstanding performance and strong generalization capabilities. Nonetheless, their success hinges on the availability of large volumes of…

Multi-label Classification (MLC) assigns an instance to one or more non-exclusive classes. A challenge arises when the dataset contains a large proportion of instances with no assigned class, referred to as negative data, which can…

Large amounts of labeled training data are one of the main contributors to the great success that deep models have achieved in the past. Label acquisition for tasks other than benchmarks can pose a challenge due to requirements of both…

The incremental sequence labeling task involves continuously learning new classes over time while retaining knowledge of the previous ones. Our investigation identifies two significant semantic shifts: E2O (where the model mislabels an old…

We propose Adapter Merging with Centroid Prototype Mapping (ACMap), an exemplar-free framework for class-incremental learning (CIL) that addresses both catastrophic forgetting and scalability. While existing methods involve a trade-off…

Given a model well-trained with a large-scale base dataset, Few-Shot Class-Incremental Learning (FSCIL) aims at incrementally learning novel classes from a few labeled samples by avoiding overfitting, without catastrophically forgetting all…

In this paper, we learn to classify visual object instances, incrementally and via self-supervision (self-incremental). Our learner observes a single instance at a time, which is then discarded from the dataset. Incremental instance…

Label Distribution Learning (LDL) is a novel machine learning paradigm that assigns label distribution to each instance. Many LDL methods proposed to leverage label correlation in the learning process to solve the exponential-sized output…

Modern systems that rely on Machine Learning (ML) for predictive modelling, may suffer from the cold-start problem: supervised models work well but, initially, there are no labels, which are costly or slow to obtain. This problem is even…

Using multiple spatial modalities has been proven helpful in improving semantic segmentation performance. However, there are several real-world challenges that have yet to be addressed: (a) improving label efficiency and (b) enhancing…

Due to the model aging problem, Deep Neural Networks (DNNs) need updates to adjust them to new data distributions. The common practice leverages incremental learning (IL), e.g., Class-based Incremental Learning (CIL) that updates output…

Deep learning has shown remarkable success in medical image analysis, but its reliance on large volumes of high-quality labeled data limits its applicability. While noisy labeled data are easier to obtain, directly incorporating them into…

Incremental learning is useful if an AI agent needs to integrate data from a stream. The problem is non trivial if the agent runs on a limited computational budget and has a bounded memory of past data. In a deep learning approach, the…

Multi-label image recognition is a challenging computer vision task of practical use. Progresses in this area, however, are often characterized by complicated methods, heavy computations, and lack of intuitive explanations. To effectively…

Compared with multi-class classification, multi-label classification that contains more than one class is more suitable in real life scenarios. Obtaining fully labeled high-quality datasets for multi-label classification problems, however,…

While 3D instance segmentation (3DIS) has advanced significantly, most existing methods assume that all object classes are known in advance and uniformly distributed. However, this assumption is unrealistic in dynamic, real-world…

In class incremental learning (CIL) a model must learn new classes in a sequential manner without forgetting old ones. However, conventional CIL methods consider a balanced distribution for each new task, which ignores the prevalence of…