Related papers: SID: Incremental Learning for Anchor-Free Object D…

As deep learning continues to advance, self-supervised learning has made considerable strides. It allows 2D image encoders to extract useful features for various downstream tasks, including those related to vision-based systems.…

Continual learning, also known as lifelong learning or incremental learning, refers to the process by which a model learns from a stream of incoming data over time. A common problem in continual learning is the classification layer's bias…

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…

Although deep neural networks enable impressive visual perception performance for autonomous driving, their robustness to varying weather conditions still requires attention. When adapting these models for changed environments, such as…

Current state-of-the-art object detectors are at the expense of high computational costs and are hard to deploy to low-end devices. Knowledge distillation, which aims at training a smaller student network by transferring knowledge from a…

We propose Algorithm Distillation (AD), a method for distilling reinforcement learning (RL) algorithms into neural networks by modeling their training histories with a causal sequence model. Algorithm Distillation treats learning to…

Federated Learning, a new machine learning paradigm enhancing the use of edge devices, is receiving a lot of attention in the pervasive community to support the development of smart services. Nevertheless, this approach still needs to be…

Self-supervised learning has been widely applied to train high-quality vision transformers. Unleashing their excellent performance on memory and compute constraint devices is therefore an important research topic. However, how to distill…

Developing accurate and efficient detectors for drone imagery is challenging due to the inherent complexity of aerial scenes. While some existing methods aim to achieve high accuracy by utilizing larger models, their computational cost is…

Conventional knowledge distillation (KD) approaches are designed for the student model to predict similar output as the teacher model for each sample. Unfortunately, the relationship across samples with same class is often neglected. In…

Traditional methods for view-invariant learning rely on controlled multi-view training data with minimal scene clutter. However, they struggle with in-the-wild videos that exhibit extreme viewpoint differences and share little visual…

Plasticity and stability are needed in class-incremental learning in order to learn from new data while preserving past knowledge. Due to catastrophic forgetting, finding a compromise between these two properties is particularly challenging…

Incremental object detection (IOD) aims to sequentially learn new classes, while maintaining the capability to locate and identify old ones. As the training data arrives with annotations only with new classes, IOD suffers from catastrophic…

Lifelong or continual learning remains to be a challenge for artificial neural network, as it is required to be both stable for preservation of old knowledge and plastic for acquisition of new knowledge. It is common to see previous…

Knowledge Distillation has shown very promising abil-ity in transferring learned representation from the largermodel (teacher) to the smaller one (student).Despitemany efforts, prior methods ignore the important role ofretaining…

Reinforcement learning can solve decision-making problems and train an agent to behave in an environment according to a predesigned reward function. However, such an approach becomes very problematic if the reward is too sparse and so the…

To address the problem of catastrophic forgetting due to the invisibility of old categories in sequential input, existing work based on relatively simple categorization tasks has made some progress. In contrast, video captioning is a more…

Event detection is one of the fundamental tasks in information extraction and knowledge graph. However, a realistic event detection system often needs to deal with new event classes constantly. These new classes usually have only a few…

Object detection has advanced significantly with Detection Transformers (DETRs). However, these models are computationally demanding, posing challenges for deployment in resource-constrained environments (e.g., self-driving cars). Knowledge…

We address the problem of class incremental learning, which is a core step towards achieving adaptive vision intelligence. In particular, we consider the task setting of incremental learning with limited memory and aim to achieve better…