Related papers: Divide and Conquer: Static-Dynamic Collaboration f…
Continual learning (CL) has shown promising results and comparable performance to learning at once in a fully supervised manner. However, CL strategies typically require a large number of labeled samples, making their real-life deployment…
Human intelligence gradually accepts new information and accumulates knowledge throughout the lifespan. However, deep learning models suffer from a catastrophic forgetting phenomenon, where they forget previous knowledge when acquiring new…
We consider class incremental learning (CIL) problem, in which a learning agent continuously learns new classes from incrementally arriving training data batches and aims to predict well on all the classes learned so far. The main challenge…
Data-Free Class Incremental Learning (DFCIL) aims to enable models to continuously learn new classes while retraining knowledge of old classes, even when the training data for old classes is unavailable. Although explored primarily with…
Instance-incremental learning (IIL) focuses on learning continually with data of the same classes. Compared to class-incremental learning (CIL), the IIL is seldom explored because IIL suffers less from catastrophic forgetting (CF). However,…
Real-world visual recognition requires handling the extreme sample imbalance in large-scale long-tailed data. We propose a "divide&conquer" strategy for the challenging LVIS task: divide the whole data into balanced parts and then apply…
Class-incremental with repetition (CIR), where previously trained classes repeatedly introduced in future tasks, is a more realistic scenario than the traditional class incremental setup, which assumes that each task contains unseen…
Class-Incremental Learning (CIL) aims to sequentially learn new classes while mitigating catastrophic forgetting of previously learned knowledge. Conventional CIL approaches implicitly assume that classes are morphologically static,…
Real-world scenarios are usually accompanied by continuously appearing classes with scare labeled samples, which require the machine learning model to incrementally learn new classes and maintain the knowledge of base classes. In this…
The dynamic expansion architecture is becoming popular in class incremental learning, mainly due to its advantages in alleviating catastrophic forgetting. However, task confusion is not well assessed within this framework, e.g., the…
Class-incremental learning (CIL) seeks to enable a model to sequentially learn new classes while retaining knowledge of previously learned ones. Balancing flexibility and stability remains a significant challenge, particularly when the task…
This paper focuses on Federated Domain-Incremental Learning (FDIL) where each client continues to learn incremental tasks where their domain shifts from each other. We propose a novel adaptive knowledge matching-based personalized FDIL…
Video semantic segmentation(VSS) has been widely employed in lots of fields, such as simultaneous localization and mapping, autonomous driving and surveillance. Its core challenge is how to leverage temporal information to achieve better…
While reinforcement learning (RL) is increasingly used for LLM-based tool learning, its efficiency is often hampered by an overabundance of simple samples that provide diminishing learning value as training progresses. Existing dynamic…
Federated Class-Incremental Learning (FCIL) refers to a scenario where a dynamically changing number of clients collaboratively learn an ever-increasing number of incoming tasks. FCIL is known to suffer from local forgetting due to class…
The proliferation of Few-Shot Class Incremental Learning (FSCIL) methodologies has highlighted the critical challenge of maintaining robust anti-amnesia capabilities in FSCIL learners. In this paper, we present a novel conceptualization of…
We address the problem of few-shot semantic segmentation (FSS), which aims to segment novel class objects in a target image with a few annotated samples. Though recent advances have been made by incorporating prototype-based metric…
Few-shot learning (FSL) aims to learn models that generalize to novel classes with limited training samples. Recent works advance FSL towards a scenario where unlabeled examples are also available and propose semi-supervised FSL methods.…
There is an increasing need of continual learning in dynamic systems, such as the self-driving vehicle, the surveillance drone, and the robotic system. Such a system requires learning from the data stream, training the model to preserve…
Deep learning-based approaches have shown remarkable performance in the 3D object detection task. However, they suffer from a catastrophic performance drop on the originally trained classes when incrementally learning new classes without…