Decoupled Mutual Distillation for Incremental Object Detection
GD Liu, WL Zhao, J Zhao - 2023 IEEE International Conference …, 2023 - ieeexplore.ieee.org
Visual object detection aims to localize and classify objects in the images. Popular detectors
perform well when all the object categories are pre-defined. However, they show poor …
perform well when all the object categories are pre-defined. However, they show poor …
Learning-Without-Forgetting via Memory Index in Incremental Object Detection
H Zhou, B Ye, JH Lai - Chinese Conference on Pattern Recognition and …, 2023 - Springer
Object detection has made significant progress in recent years. However, when the training
data is continuous and dynamic, notorious catastrophic forgetting will occur. In addition …
data is continuous and dynamic, notorious catastrophic forgetting will occur. In addition …
Refined Response Distillation for Class-Incremental Player Detection
Detecting players from sports broadcast videos is essential for intelligent event analysis.
However, existing methods assume fixed player categories, incapably accommodating the …
However, existing methods assume fixed player categories, incapably accommodating the …
Continual learning for computer vision applications
L Pellegrini - 2022 - amsdottorato.unibo.it
One of the most visionary goals of Artificial Intelligence is to create a system able to mimic
and eventually surpass the intelligence observed in biological systems including …
and eventually surpass the intelligence observed in biological systems including …
Alleviating catastrophic forgetting of incremental object detection via within-class and between-class knowledge distillation
M Kang, J Zhang, J Zhang, X Wang… - Proceedings of the …, 2023 - openaccess.thecvf.com
Incremental object detection (IOD) task requires a model to learn continually from newly
added data. However, directly fine-tuning a well-trained detection model on a new task will …
added data. However, directly fine-tuning a well-trained detection model on a new task will …
Reviewing continual learning from the perspective of human-level intelligence
Humans' continual learning (CL) ability is closely related to Stability Versus Plasticity
Dilemma that describes how humans achieve ongoing learning capacity and preservation …
Dilemma that describes how humans achieve ongoing learning capacity and preservation …
ViT-LR: Pushing the Envelope for Transformer-Based on-Device Embedded Continual Learning
State-of-the-Art Edge Artificial Intelligence (AI) is currently mostly targeted at a train-then-
deploy paradigm: edge devices are exclusively responsible for inference, whereas training …
deploy paradigm: edge devices are exclusively responsible for inference, whereas training …
Contrastive R-CNN for Incremental Learning in Object Detection
P Qian, K Zheng, C Chen, Z Cheng… - … Digital Twin, Privacy …, 2022 - ieeexplore.ieee.org
Incremental learning for image classification has been widely studied in the past few years,
but few works explored incremental learning for object detection. Most existing incremental …
but few works explored incremental learning for object detection. Most existing incremental …
Distributed On-line Training for Object Detection on Embedded Devices.
K Mottakin - 2022 - eprints.bournemouth.ac.uk
In this thesis, we develop a scalable distributed approach for object detection model training
and inference, using low cost embedded devices. Examples of the usage of such an …
and inference, using low cost embedded devices. Examples of the usage of such an …
Analysis and Enhancement of Resource-Hungry Applications
S Huang - 2022 - search.proquest.com
Resource-hungry applications play a very important role in people's daily lives, such as real-
time video streaming applications and mobile augmented reality applications. However …
time video streaming applications and mobile augmented reality applications. However …