Decoupling Classifier for Boosting Few-shot Object Detection and Instance SegmentationDownload PDF

Published: 31 Oct 2022, Last Modified: 23 Oct 2022NeurIPS 2022 AcceptReaders: Everyone
Keywords: few-shot object detection, few-shot instance segmentaton, instance-level few-shot, missing label
Abstract: This paper focus on few-shot object detection~(FSOD) and instance segmentation~(FSIS), which requires a model to quickly adapt to novel classes with a few labeled instances. The existing methods severely suffer from bias classification because of the missing label issue which naturally exists in an instance-level few-shot scenario and is first formally proposed by us. Our analysis suggests that the standard classification head of most FSOD or FSIS models needs to be decoupled to mitigate the bias classification. Therefore, we propose an embarrassingly simple but effective method that decouples the standard classifier into two heads. Then, these two individual heads are capable of independently addressing clear positive samples and noisy negative samples which are caused by the missing label. In this way, the model can effectively learn novel classes while mitigating the effects of noisy negative samples. Without bells and whistles, our model without any additional computation cost and parameters consistently outperforms its baseline and state-of-the-art by a large margin on PASCAL VOC and MS-COCO benchmarks for FSOD and FSIS tasks.\footnote{\url{https://csgaobb.github.io/Projects/DCFS}.}
Supplementary Material: pdf
TL;DR: we propose an embarrassingly simple but effective decoupling classifier for instance-level few-shot object detection and instance segmentation.
19 Replies

Loading