홈 › Papers

Incremental Few-Shot Object Detection for Robotics

2020-05-06 · Yiting Li, Haiyue Zhu, Sichao Tian, Fan Feng, Jun Ma, Chek Sing Teo, Cheng Xiang, Prahlad Vadakkepat, Tong Heng Lee

Incremental few-shot learning is highly expected for practical robotics applications. On one hand, robot is desired to learn new tasks quickly and flexibly using only few annotated training samples; on the other hand, such new additional tasks should be learned in a continuous and incremental manner without forgetting the previous learned knowledge dramatically. In this work, we propose a novel Class-Incremental Few-Shot Object Detection (CI-FSOD) framework that enables deep object detection network to perform effective continual learning from just few-shot samples without re-accessing the previous training data. We achieve this by equipping the widely-used Faster-RCNN detector with three elegant components. Firstly, to best preserve performance on the pre-trained base classes, we propose a novel Dual-Embedding-Space (DES) architecture which decouples the representation learning of base and novel categories into different spaces. Secondly, to mitigate the catastrophic forgetting on the accumulated novel classes, we propose a Sequential Model Fusion (SMF) method, which is able to achieve long-term memory without additional storage cost. Thirdly, to promote inter-task class separation in feature space, we propose a novel regularization technique that extends the classification boundary further away from the previous classes to avoid misclassification. Overall, our framework is simple yet effective and outperforms the previous SOTA with a significant margin of 2.4 points in AP performance.

📄 PDF Abstract BibTeX arXiv:2005.02641

Code (0)

등록된 구현이 없습니다.

Tasks

Classification Continual Learning Few-Shot Learning Few-Shot Object Detection General ClassificationObjectobject-detection Object Detection Representation Learning

Towards Generalized and Incremental Few-Shot Object Detection

2021-09-23 · Yiting Li, Haiyue Zhu, Jun Ma, Chek Sing Teo 외

Real-world object detection is highly desired to be equipped with the learning expandability that can enlarge its detection classes incrementally. Moreover, such learning from only few annotated training samples further …

Autonomous Driving Continual Learning Few-Shot Learning Few-Shot Object Detection+3

Incremental-DETR: Incremental Few-Shot Object Detection via Self-Supervised Learning

2022-05-09 · Na Dong, Yongqiang Zhang, Mingli Ding, Gim Hee Lee

Incremental few-shot object detection aims at detecting novel classes without forgetting knowledge of the base classes with only a few labeled training data from the novel classes. Most related prior works are on increme…

Few-Shot Object Detection Knowledge Distillation Object object-detection+2

Few-Shot Batch Incremental Road Object Detection via Detector Fusion

2021-08-18 · Anuj Tambwekar, Kshitij Agrawal, Anay Majee, Anbumani Subramanian

Incremental few-shot learning has emerged as a new and challenging area in deep learning, whose objective is to train deep learning models using very few samples of new class data, and none of the old class data. In this…

Few-Shot Learning object-detection Object Detection

Active Class Selection for Few-Shot Class-Incremental Learning

2023-07-05 · Christopher McClurg, Ali Ayub, Harsh Tyagi, Sarah M. Rajtmajer 외

For real-world applications, robots will need to continually learn in their environments through limited interactions with their users. Toward this, previous works in few-shot class incremental learning (FSCIL) and activ…

class-incremental learning Class Incremental Learning Few-Shot Class-Incremental Learning Incremental Learning+1