相关论文: Continual Gesture Learning without Data via Synthe…

As the demand for mobile robots continues to increase, social navigation has emerged as a critical task, driving active research into deep reinforcement learning (RL) approaches. However, because pedestrian dynamics and social conventions…

Data-free knowledge distillation (DFKD) aims to obtain a lightweight student model without original training data. Existing works generally synthesize data from the pre-trained teacher model to replace the original training data for student…

In Deep Reinforcement Learning (RL), it is a challenge to learn representations that do not exhibit catastrophic forgetting or interference in non-stationary environments. Successor Features (SFs) offer a potential solution to this…

Recently skeleton-based action recognition has made signif-icant progresses in the computer vision community. Most state-of-the-art algorithms are based on Graph Convolutional Networks (GCN), andtarget at improving the network structure of…

In order to encode the class correlation and class specific information in image representation, we propose a new local feature learning approach named Deep Discriminative and Shareable Feature Learning (DDSFL). DDSFL aims to hierarchically…

Few-shot class-incremental learning (FSCIL) is proposed to continually learn from novel classes with only a few samples after the (pre-)training on base classes with sufficient data. However, this remains a challenge. In contrast, humans…

Few-shot class incremental learning implies the model to learn new classes while retaining knowledge of previously learned classes with a small number of training instances. Existing frameworks typically freeze the parameters of the…

Generalized Zero-Shot Learning (GZSL) is the task of leveraging semantic information (e.g., attributes) to recognize the seen and unseen samples, where unseen classes are not observable during training. It is natural to derive generative…

In this work, we propose a new setting of continual learning: data-incremental continual offline reinforcement learning (DICORL), in which an agent is asked to learn a sequence of datasets of a single offline reinforcement learning (RL)…

Gesture is an important mean of non-verbal communication, with visual modality allows human to convey information during interaction, facilitating peoples and human-machine interactions. However, it is considered difficult to automatically…

The ability to incrementally learn new classes is vital to all real-world artificial intelligence systems. A large portion of high-impact applications like social media, recommendation systems, E-commerce platforms, etc. can be represented…

The rise of cloud-device collaborative computing has enabled intelligent services to be delivered across distributed edge devices while leveraging centralized cloud resources. In this paradigm, federated learning (FL) has become a key…

Continual learning is an emerging paradigm in machine learning, wherein a model is exposed in an online fashion to data from multiple different distributions (i.e. environments), and is expected to adapt to the distribution change.…

Aiming to incrementally learn new classes with only few samples while preserving the knowledge of base (old) classes, few-shot class-incremental learning (FSCIL) faces several challenges, such as overfitting and catastrophic forgetting.…

Skeleton-based action recognition aims to project skeleton sequences to action categories, where skeleton sequences are derived from multiple forms of pre-detected points. Compared with earlier methods that focus on exploring single-form…

Continual learning (CL) refers to the ability of an algorithm to continuously and incrementally acquire new knowledge from its environment while retaining previously learned information. A model trained on one data modality often fails when…

In robotic manipulation, acquiring samples is extremely expensive because it often requires interacting with the real world. Traditional image-level data augmentation has shown the potential to improve sample efficiency in various machine…

Federated Learning (FL) aims at unburdening the training of deep models by distributing computation across multiple devices (clients) while safeguarding data privacy. On top of that, Federated Continual Learning (FCL) also accounts for data…

Graph class-incremental learning (GCIL) allows graph neural networks (GNNs) to adapt to evolving graph analytical tasks by incrementally learning new class knowledge while retaining knowledge of old classes. Existing GCIL methods primarily…

Few-shot continual learning (FSCL) has attracted intensive attention and achieved some advances in recent years, but now it is difficult to again make a big stride in accuracy due to the limitation of only few-shot incremental samples.…