相关论文: Dynamical Adapter Fusion: Constructing A Global Ad…

The ability to learn new concepts continually is necessary in this ever-changing world. However, deep neural networks suffer from catastrophic forgetting when learning new categories. Many works have been proposed to alleviate this…

Model ensemble is an effective strategy in continual learning, which alleviates catastrophic forgetting by interpolating model parameters, achieving knowledge fusion learned from different tasks. However, existing model ensemble methods…

Existing automatic data augmentation (DA) methods either ignore updating DA's parameters according to the target model's state during training or adopt update strategies that are not effective enough. In this work, we design a novel data…

Domain adaptive object detection (DAOD) aims to adapt the detector from a labelled source domain to an unlabelled target domain. In recent years, DAOD has attracted massive attention since it can alleviate performance degradation due to the…

Incremental learning (IL) aims to overcome catastrophic forgetting of previous tasks while learning new ones. Existing IL methods make strong assumptions that the incoming task type will either only increases new classes or domains (i.e.…

Active learning (AL) aims to improve model performance within a fixed labeling budget by choosing the most informative data points to label. Existing AL focuses on the single-domain setting, where all data come from the same domain (e.g.,…

Deep learning (DL) techniques are highly effective for defect detection from images. Training DL classification models, however, requires vast amounts of labeled data which is often expensive to collect. In many cases, not only the…

In domain adaptation (DA), the effectiveness of deep learning-based models is often constrained by batch learning strategies that fail to fully apprehend the global statistical and geometric characteristics of data distributions. Addressing…

Imitation learning aims to learn a policy from observing expert demonstrations without access to reward signals from environments. Generative adversarial imitation learning (GAIL) formulates imitation learning as adversarial learning,…

The phenomenon of adversarial examples illustrates one of the most basic vulnerabilities of deep neural networks. Among the variety of techniques introduced to surmount this inherent weakness, adversarial training has emerged as the most…

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…

Domain-Incremental Learning (DIL) focuses on continual learning in non-stationary environments, requiring models to adjust to evolving domains while preserving historical knowledge. DIL faces two critical challenges in the context of…

Although deep neural networks perform extremely well in controlled environments, they fail in real-world scenarios where data isn't available all at once, and the model must adapt to a new data distribution that may or may not follow the…

Unsupervised domain adaptive (UDA) person re-identification (ReID) has gained increasing attention for its effectiveness on the target domain without manual annotations. Most fine-tuning based UDA person ReID methods focus on encoding…

Path smoothness is often overlooked in path imitation learning from expert demonstrations. In this paper, we introduce a novel learning method, termed deep angular A* (DAA*), by incorporating the proposed path angular freedom (PAF) into A*…

Domain Incremental Learning (DIL) aims to learn from non-stationary data streams across domains while retaining and utilizing past knowledge. Although prompt-based methods effectively store multi-domain knowledge in prompt parameters and…

Federated learning (FL) is a burgeoning distributed machine learning framework where a central parameter server (PS) coordinates many local users to train a globally consistent model. Conventional federated learning inevitably relies on a…

Continual learning aims to empower artificial intelligence (AI) with strong adaptability to the real world. For this purpose, a desirable solution should properly balance memory stability with learning plasticity, and acquire sufficient…

Class-incremental learning (CIL) with pre-trained models (PTMs) faces a critical trade-off between efficient adaptation and long-term stability. While analytic learning enables rapid, recursive closed-form updates, its efficacy is often…

One important desideratum of lifelong learning aims to discover novel classes from unlabelled data in a continuous manner. The central challenge is twofold: discovering and learning novel classes while mitigating the issue of catastrophic…