Related papers: Learning Prompt with Distribution-Based Feature Re…
With the emergence of Transformers and Vision-Language Models (VLMs) such as CLIP, fine-tuning large pre-trained models has recently become a prevalent strategy in Continual Learning. This has led to the development of numerous prompting…
Class-incremental learning (CIL) has emerged as a means to learn new classes incrementally without catastrophic forgetting of previous classes. Recently, CIL has undergone a paradigm shift towards dynamic architectures due to their superior…
The dynamic nature of open-world scenarios has attracted more attention to class incremental learning (CIL). However, existing CIL methods typically presume the availability of complete ground-truth labels throughout the training process,…
The source-free cross-domain few-shot learning (CD-FSL) task aims to transfer pretrained models to target domains utilizing minimal samples, eliminating the need for source domain data. Addressing this issue requires models to have robust…
Few-shot, fine-grained classification in computer vision poses significant challenges due to the need to differentiate subtle class distinctions with limited data. This paper presents a novel method that enhances the Contrastive…
State-of-the-art deep neural networks are still struggling to address the catastrophic forgetting problem in continual learning. In this paper, we propose one simple paradigm (named as S-Prompting) and two concrete approaches to highly…
Few-Shot Class-Incremental Learning (FSCIL) challenges models to sequentially learn new classes from minimal examples without forgetting prior knowledge, a task complicated by the stability-plasticity dilemma and data scarcity. Current…
The application of activity recognition in the "AI + Education" field is gaining increasing attention. However, current work mainly focuses on the recognition of activities in manually captured videos and a limited number of activity types,…
Generalized Few-Shot Semantic Segmentation (GFSS) aims to extend a segmentation model to novel classes with only a few annotated examples while maintaining performance on base classes. Recently, pretrained vision-language models (VLMs) such…
Few-shot class-incremental learning is crucial for developing scalable and adaptive intelligent systems, as it enables models to acquire new classes with minimal annotated data while safeguarding the previously accumulated knowledge.…
Class-incremental learning (CIL) enables models to continuously learn new categories from sequential tasks without forgetting previously acquired knowledge. While recent advances in vision-language models such as CLIP have demonstrated…
The task of Few-shot learning (FSL) aims to transfer the knowledge learned from base categories with sufficient labelled data to novel categories with scarce known information. It is currently an important research question and has great…
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…
CLIP has achieved impressive zero-shot performance after pre-training on a large-scale dataset consisting of paired image-text data. Previous works have utilized CLIP by incorporating manually designed visual prompts like colored circles…
Many real-world classification problems often have classes with very few labeled training samples. Moreover, all possible classes may not be initially available for training, and may be given incrementally. Deep learning models need to deal…
Foundation Vision-Language Models (VLMs) like CLIP exhibit strong generalization capabilities due to large-scale pretraining on diverse image-text pairs. However, their performance often degrades when applied to target datasets with…
Exemplar-Free Class Incremental Learning (EFCIL) aims to learn from a sequence of tasks without having access to previous task data. In this paper, we consider the challenging Cold Start scenario in which insufficient data is available in…
Fine-tuning vision-language models (VLMs) like CLIP to downstream tasks is often necessary to optimize their performance. However, a major obstacle is the limited availability of labeled data. We study the use of pseudolabels, i.e.,…
Few-shot learning (FSL), which aims to recognise new classes by adapting the learned knowledge with extremely limited few-shot (support) examples, remains an important open problem in computer vision. Most of the existing methods for…
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…