Few-Shot Object Detection via Classification Refinement and Distractor Retreatment(CVPR. 2021)

最新推荐文章于 2024-08-05 18:37:28 发布

Ah丶Weii

最新推荐文章于 2024-08-05 18:37:28 发布

阅读量810

点赞数

分类专栏：笔记

本文链接：https://blog.csdn.net/weixin_43823854/article/details/119546978

版权

本文针对Few-Shot Object Detection问题，提出了一种新的框架，通过分类细化和干扰物再处理提高性能。研究发现当前方法在IOU意识和类别判别性上存在不足。为此，文章介绍了Few-Shot Correction Network (FSCN)，用于消除类别混淆导致的假阳性，并提出了半监督干扰物利用损失和基于信心的数据集修剪策略，有效解决了未标注干扰物的影响，提高了在少量样本下的检测效果。

摘要由CSDN通过智能技术生成

1. Motivation

The current state-of-the-art approach TFA [17] is still far away from satisfaction compared with those general data-abundant detection tasks
Given the fact that TFA is IOU-aware but less semantic discriminative, our key insight is to enhance the original classification results by injecting additional category-discriminative information.
we focus on a unique but practically-existed problem of FSOD in this work the presence of distractor samples due to the incomplete annotations, where objects belonging to novel classes can exist in the base set but remain unlabelled.

本文认为TFA可以从2个方面改进①IOU awareness，指的是对于hard negative的鲁棒性；②category discriminability，指的是不同类别之间confusion。

IOU awareness, i.e., robustness to hard negatives
category discriminability, i.e., robustness to category confusion.

作者使用的方法是，对于某一个object的预测得分（IOU = 0.4的poor box），对于IOU awareness，，将gt 类别的分类得分消除，其余类别不变；对于category discriminability，将除了gt以外的分类得分消除，gt得分不变。

这里想了很久，感觉需要结合focal loss分析，如果是第一种情况，那么正确类别的得分为0， $loss_+$ 就很大，那么网络就倾向于学习这种false positive样本。

如果是第二种情况，那么除了正确类别以外的得分都置0，那么 $_ loss_{\_}$ 就是0了，也还是网络会倾向于优化 gt类别。
$loss_+ = y \times log(\hat y) \\ loss_{\_} = (1-y) \times log(1 - \hat y)$

本文通过图1的实验，分别对2个方面进进行消融实验，得出TFA是IOU-aware 但是less discriminative。

2. Contribution

本文提出了FSCN的结构，来改善FSOD的性能，correction network用于消除category confusion带来的false positive。

We explore the limitations of the classifier rebalancing method (TFA) for FSOD problems and propose a novel few-shot classification refinement framework for exhaustively boosting its FSOD performance. A novel few-shot correction network is developed to achieve great semantic discriminability so as to eliminate false positives caused by category confusion.

在fine-tune过程中使用CGDP方法。
We are the first to address the destructive distractor issue for FSOD. Instead of blindly treating it, a confidence-guided filtering strategy is proposed to exclude the distractors for base detector fine-tuning.
A semi-supervised distractor utilization strategy is proposed to cooperate with FSCN, which not only stabilizes the training process but also significantly promotes the learning on data-scarce novel classes with no extra annotation cost.
Our proposed FSOD framework achieves the state-of- the-art results in various datasets with remarkable few- shot performance and knowledge retention ability.