At this stage, research in the field of Few-shot image classification (FSC) has made good progress, but there are still many difficulties in the field of Few-shot object detection (FSOD). Almost all of the current FSOD methods face catastrophic forgetting problems, which are manifested in that the accuracy of base class recognition will drop seriously when acquiring the ability to recognize Novel classes. And for many methods, the accuracy of the model will fall back as the class increases. To address this problem we propose a new memory-based method called Memorable Faster R-CNN (MemFRCN), which makes the model remember the categories it has already seen. Specifically, we propose a new tow-stage object detector consisting of a memory-based classifier (MemCla), a fully connected neural network classifier (FCC) and an adaptive fusion block (AdFus). The former stores the embedding vector of each category as memory, which enables the model to have memory capabilities to avoid catastrophic forgetting events. The final part fuses the outputs of FCC and MemCla, which can automatically adjust the fusion method of the model when the number of samples increases so that the model can achieve better performance under various conditions. Our method can perform well on unseen classes while maintaining the detection accuracy of seen classes. Experimental results demonstrate that our method outperforms other current methods on multiple benchmarks.
TongWei LU
Hubei Key Laboratory of Intelligent Robot (Wuhan Institute of Technology),Wuhan Institute of Technology
ShiHai JIA
Hubei Key Laboratory of Intelligent Robot (Wuhan Institute of Technology),Wuhan Institute of Technology
Hao ZHANG
Hubei Key Laboratory of Intelligent Robot (Wuhan Institute of Technology),Wuhan Institute of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
TongWei LU, ShiHai JIA, Hao ZHANG, "MemFRCN: Few Shot Object Detection with Memorable Faster-RCNN" in IEICE TRANSACTIONS on Fundamentals,
vol. E105-A, no. 12, pp. 1626-1630, December 2022, doi: 10.1587/transfun.2022EAL2010.
Abstract: At this stage, research in the field of Few-shot image classification (FSC) has made good progress, but there are still many difficulties in the field of Few-shot object detection (FSOD). Almost all of the current FSOD methods face catastrophic forgetting problems, which are manifested in that the accuracy of base class recognition will drop seriously when acquiring the ability to recognize Novel classes. And for many methods, the accuracy of the model will fall back as the class increases. To address this problem we propose a new memory-based method called Memorable Faster R-CNN (MemFRCN), which makes the model remember the categories it has already seen. Specifically, we propose a new tow-stage object detector consisting of a memory-based classifier (MemCla), a fully connected neural network classifier (FCC) and an adaptive fusion block (AdFus). The former stores the embedding vector of each category as memory, which enables the model to have memory capabilities to avoid catastrophic forgetting events. The final part fuses the outputs of FCC and MemCla, which can automatically adjust the fusion method of the model when the number of samples increases so that the model can achieve better performance under various conditions. Our method can perform well on unseen classes while maintaining the detection accuracy of seen classes. Experimental results demonstrate that our method outperforms other current methods on multiple benchmarks.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/transfun.2022EAL2010/_p
Copy
@ARTICLE{e105-a_12_1626,
author={TongWei LU, ShiHai JIA, Hao ZHANG, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={MemFRCN: Few Shot Object Detection with Memorable Faster-RCNN},
year={2022},
volume={E105-A},
number={12},
pages={1626-1630},
abstract={At this stage, research in the field of Few-shot image classification (FSC) has made good progress, but there are still many difficulties in the field of Few-shot object detection (FSOD). Almost all of the current FSOD methods face catastrophic forgetting problems, which are manifested in that the accuracy of base class recognition will drop seriously when acquiring the ability to recognize Novel classes. And for many methods, the accuracy of the model will fall back as the class increases. To address this problem we propose a new memory-based method called Memorable Faster R-CNN (MemFRCN), which makes the model remember the categories it has already seen. Specifically, we propose a new tow-stage object detector consisting of a memory-based classifier (MemCla), a fully connected neural network classifier (FCC) and an adaptive fusion block (AdFus). The former stores the embedding vector of each category as memory, which enables the model to have memory capabilities to avoid catastrophic forgetting events. The final part fuses the outputs of FCC and MemCla, which can automatically adjust the fusion method of the model when the number of samples increases so that the model can achieve better performance under various conditions. Our method can perform well on unseen classes while maintaining the detection accuracy of seen classes. Experimental results demonstrate that our method outperforms other current methods on multiple benchmarks.},
keywords={},
doi={10.1587/transfun.2022EAL2010},
ISSN={1745-1337},
month={December},}
Copy
TY - JOUR
TI - MemFRCN: Few Shot Object Detection with Memorable Faster-RCNN
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1626
EP - 1630
AU - TongWei LU
AU - ShiHai JIA
AU - Hao ZHANG
PY - 2022
DO - 10.1587/transfun.2022EAL2010
JO - IEICE TRANSACTIONS on Fundamentals
SN - 1745-1337
VL - E105-A
IS - 12
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - December 2022
AB - At this stage, research in the field of Few-shot image classification (FSC) has made good progress, but there are still many difficulties in the field of Few-shot object detection (FSOD). Almost all of the current FSOD methods face catastrophic forgetting problems, which are manifested in that the accuracy of base class recognition will drop seriously when acquiring the ability to recognize Novel classes. And for many methods, the accuracy of the model will fall back as the class increases. To address this problem we propose a new memory-based method called Memorable Faster R-CNN (MemFRCN), which makes the model remember the categories it has already seen. Specifically, we propose a new tow-stage object detector consisting of a memory-based classifier (MemCla), a fully connected neural network classifier (FCC) and an adaptive fusion block (AdFus). The former stores the embedding vector of each category as memory, which enables the model to have memory capabilities to avoid catastrophic forgetting events. The final part fuses the outputs of FCC and MemCla, which can automatically adjust the fusion method of the model when the number of samples increases so that the model can achieve better performance under various conditions. Our method can perform well on unseen classes while maintaining the detection accuracy of seen classes. Experimental results demonstrate that our method outperforms other current methods on multiple benchmarks.
ER -