相关论文: StPR: Spatiotemporal Preservation and Routing for …

Existing Class Incremental Learning (CIL) methods are based on a supervised classification framework sensitive to data labels. When updating them based on the new class data, they suffer from catastrophic forgetting: the model cannot…

Knowledge Management is crucial for capturing and transferring expertise within universities, especially in high staff turnover contexts where expertise loss disrupts teaching. Documenting teachers' workflows is time-intensive and diverts…

Few-Shot Class-Incremental Learning (FSCIL) aims to enable deep neural networks to learn new tasks incrementally from a small number of labeled samples without forgetting previously learned tasks, closely mimicking human learning patterns.…

Class incremental learning (CIL) aims to recognize both the old and new classes along the increment tasks. Deep neural networks in CIL suffer from catastrophic forgetting and some approaches rely on saving exemplars from previous tasks,…

We tackle the problem of class incremental learning (CIL) in the realm of landcover classification from optical remote sensing (RS) images in this paper. The paradigm of CIL has recently gained much prominence given the fact that data are…

Incremental Learning (IL) aims to accumulate knowledge from sequential input tasks while overcoming catastrophic forgetting. Existing IL methods typically assume that an incoming task has only increments of classes or domains, referred to…

Discovery and learning of an underlying spatiotemporal hierarchy in sequential data is an important topic for machine learning. Despite this, little work has been done to explore hierarchical generative models that can flexibly adapt their…

Event cameras sense the intensity changes asynchronously and produce event streams with high dynamic range and low latency. This has inspired research endeavors utilizing events to guide the challenging video superresolution (VSR) task. In…

Few-shot class-incremental learning (FSCIL) seeks to continuously learn new classes from very limited samples while preserving previously acquired knowledge. Traditional methods often utilize a frozen pre-trained feature extractor to…

A fundamental challenge in embodied AI is verifying if agents build internal models of spatial structure or merely learn to mimic task-specific expert trajectories. This is critical as foundational approaches rooted in action-centric tasks…

Exemplar-free class-incremental learning (EFCIL) poses significant challenges, primarily due to catastrophic forgetting, necessitating a delicate balance between stability and plasticity to accurately recognize both new and previous…

Replay-based methods in class-incremental learning (CIL) have attained remarkable success. Despite their effectiveness, the inherent memory restriction results in saving a limited number of exemplars with poor diversity. In this paper, we…

Continual learning (CL) can help pre-trained vision-language models efficiently adapt to new or under-trained data distributions without re-training. Nevertheless, during the continual training of the Contrastive Language-Image Pre-training…

Class-Incremental Learning (CIL) or continual learning is a desired capability in the real world, which requires a learning system to adapt to new tasks without forgetting former ones. While traditional CIL methods focus on visual…

Integrating new class information without losing previously acquired knowledge remains a central challenge in artificial intelligence, often referred to as catastrophic forgetting. Few-shot class incremental learning (FSCIL) addresses this…

Sequential Visual Place Recognition (Seq-VPR) leverages transformers to capture spatio-temporal features effectively. In practice, a transformer-based Seq-VPR model should be flexible to the number of frames per sequence (seq- length),…

Feature Distillation (FD) strategies are proven to be effective in mitigating Catastrophic Forgetting (CF) seen in Class Incremental Learning (CIL). However, current FD approaches enforce strict alignment of feature magnitudes and…

Visual place recognition (VPR) is usually considered as a specific image retrieval problem. Limited by existing training frameworks, most deep learning-based works cannot extract sufficiently stable global features from RGB images and rely…

Class-Incremental learning (CIL) refers to the ability of artificial agents to integrate new classes as they appear in a stream. It is particularly interesting in evolving environments where agents have limited access to memory and…

Plasticity and stability are needed in class-incremental learning in order to learn from new data while preserving past knowledge. Due to catastrophic forgetting, finding a compromise between these two properties is particularly challenging…