Related papers: Learning from Mistakes: Loss-Aware Memory Enhanced…

Laser degradation analysis is a crucial process for the enhancement of laser reliability. Here, we propose a data-driven fault detection approach based on Long Short-Term Memory (LSTM) recurrent neural networks to detect the different laser…

Model-free reinforcement learning has been successfully applied to a range of challenging problems, and has recently been extended to handle large neural network policies and value functions. However, the sample complexity of model-free…

Learning from changing tasks and sequential experience without forgetting the obtained knowledge is a challenging problem for artificial neural networks. In this work, we focus on two challenging problems in the paradigm of Continual…

Continual learning (CL) is essential for Large Language Models (LLMs) to adapt to evolving real-world demands, yet they are susceptible to catastrophic forgetting (CF). While traditional CF solutions rely on expensive data rehearsal, recent…

LiDAR relocalization has attracted increasing attention as it can deliver accurate 6-DoF pose estimation in complex 3D environments. Recent learning-based regression methods offer efficient solutions by directly predicting global poses…

Most existing works on continual learning (CL) focus on overcoming the catastrophic forgetting (CF) problem, with dynamic models and replay methods performing exceptionally well. However, since current works tend to assume exclusivity or…

Place recognition is the fundamental module that can assist Simultaneous Localization and Mapping (SLAM) in loop-closure detection and re-localization for long-term navigation. The place recognition community has made astonishing progress…

The ability of artificial agents to increment their capabilities when confronted with new data is an open challenge in artificial intelligence. The main challenge faced in such cases is catastrophic forgetting, i.e., the tendency of neural…

Incremental learning (IL) is an important task aimed at increasing the capability of a trained model, in terms of the number of classes recognizable by the model. The key problem in this task is the requirement of storing data (e.g. images)…

The LiDAR and inertial sensors based localization and mapping are of great significance for Unmanned Ground Vehicle related applications. In this work, we have developed an improved LiDAR-inertial localization and mapping system for…

Place recognition is crucial for loop closure detection and global localization in robotics. Although mainstream algorithms typically rely on cameras and LiDAR, these sensors are susceptible to adverse weather conditions. Fortunately, the…

LiDAR-based localization and mapping is one of the core components in many modern robotic systems due to the direct integration of range and geometry, allowing for precise motion estimation and generation of high quality maps in real-time.…

LiDAR odometry is a fundamental task for various areas such as robotics, autonomous driving. This problem is difficult since it requires the systems to be highly robust running in noisy real-world data. Existing methods are mostly local…

Lifelong learning aims to train a model with good performance for new tasks while retaining the capacity of previous tasks. However, some practical scenarios require the system to forget undesirable knowledge due to privacy issues, which is…

For several emerging technologies such as augmented reality, autonomous driving and robotics, visual localization is a critical component. Directly regressing camera pose/3D scene coordinates from the input image using deep neural networks…

Humans learn all their life long. They accumulate knowledge from a sequence of learning experiences and remember the essential concepts without forgetting what they have learned previously. Artificial neural networks struggle to learn…

Rehearsal approaches enjoy immense popularity with Continual Learning (CL) practitioners. These methods collect samples from previously encountered data distributions in a small memory buffer; subsequently, they repeatedly optimize on the…

We present a novel class incremental learning approach based on deep neural networks, which continually learns new tasks with limited memory for storing examples in the previous tasks. Our algorithm is based on knowledge distillation and…

As a critical application of computational intelligence in remote sensing, deep learning-based synthetic aperture radar (SAR) image target recognition facilitates intelligent perception but typically relies on centralized training, where…

Deep learning models suffer from catastrophic forgetting of the classes in the older phases as they get trained on the classes introduced in the new phase in the class-incremental learning setting. In this work, we show that the effect of…