Related papers: Dynamic Integration of Task-Specific Adapters for …
New classes arise frequently in our ever-changing world, e.g., emerging topics in social media and new types of products in e-commerce. A model should recognize new classes and meanwhile maintain discriminability over old classes. Under…
Graph Neural Networks (GNN) endure catastrophic forgetting, undermining their capacity to preserve previously acquired knowledge amid the assimilation of novel information. Rehearsal-based techniques revisit historical examples, adopted as…
This paper introduces a two-stage framework designed to enhance long-tail class incremental learning, enabling the model to progressively learn new classes, while mitigating catastrophic forgetting in the context of long-tailed data…
Multi-label Class-Incremental Learning aims to continuously recognize novel categories in complex scenes where multiple objects co-occur. However, existing approaches often incur high computational costs due to full-parameter fine-tuning…
Class incremental learning consists in training discriminative models to classify an increasing number of classes over time. However, doing so using only the newly added class data leads to the known problem of catastrophic forgetting of…
Exemplar-Free Class Incremental Learning (EFCIL) tackles the problem of training a model on a sequence of tasks without access to past data. Existing state-of-the-art methods represent classes as Gaussian distributions in the feature…
Unsupervised domain adaptation (UDA) is a critical challenge in the field of point cloud analysis. Previous works tackle the problem either by feature extractor adaptation to enable a shared classifier to distinguish domain-invariant…
Continual learning requires learning incremental tasks with dynamic data distributions. So far, it has been observed that employing a combination of contrastive loss and distillation loss for training in continual learning yields strong…
Current research on class-incremental learning primarily focuses on single-label classification tasks. However, real-world applications often involve multi-label scenarios, such as image retrieval and medical imaging. Therefore, this paper…
Improving the reasoning capabilities of large language models (LLMs) typically relies either on the model's ability to sample a correct solution to be reinforced or on the existence of a stronger model able to solve the problem. However,…
To adapt effectively to dynamic real-world environments, intelligent systems must continually acquire new skills while generalizing them to diverse, unseen scenarios. Here, we introduce a novel and realistic setting named domain…
Interpolation-based Data Augmentation (DA) methods (Mixup) linearly interpolate the inputs and labels of two or more training examples. Mixup has more recently been adapted to the field of Natural Language Processing (NLP), mainly for…
Few-shot class-incremental learning (FSCIL) aims to continuously recognize novel classes under limited data, which suffers from the key stability-plasticity dilemma: balancing the retention of old knowledge with the acquisition of new…
Continual learning (CL) with Vision-Language Models (VLMs) has overcome the constraints of traditional CL, which only focuses on previously encountered classes. During the CL of VLMs, we need not only to prevent the catastrophic forgetting…
We present a bag of tricks framework for few-shot class-incremental learning (FSCIL), which is a challenging form of continual learning that involves continuous adaptation to new tasks with limited samples. FSCIL requires both stability and…
Class-incremental learning (CIL) is typically evaluated under predefined schedules with equal-sized tasks, leaving more realistic and complex cases unexplored. However, a practical CIL system should learns immediately when any number of new…
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…
Few-shot class-incremental learning (FSCIL), which targets at continuously expanding model's representation capacity under few supervisions, is an important yet challenging problem. On the one hand, when fitting new tasks (novel classes),…
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…
New objects are continuously emerging in the dynamically changing world and a real-world artificial intelligence system should be capable of continual and effectual adaptation to new emerging classes without forgetting old ones. In view of…