arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.13757cs.CV
收藏

I3Net:一种适用于一级目标检测器的隐式实例不变网络

I3Net: Implicit Instance-Invariant Network for Adapting One-Stage Object Detectors

The University of Hong Kong(香港大学);Xiamen University(厦门大学);Deepwise AI Lab(深睿医疗AI实验室)

Chaoqi Chen, Zebiao Zheng, Yue Huang, Xinghao Ding, Yizhou Yu

摘要:

最近的两阶段跨域检测工作已经广泛地探索了局部特征模式,以实现更准确的自适应结果。这些方法在很大程度上依赖于区域建议机制和基于ROI的实例级特征来设计与前景对象相关的细粒度特征对齐模块。然而,对于一级检测器,很难甚至不可能在检测管道中获得显式的实例级特征。受此启发,我们提出了一种隐式实例不变网络(I3 Net),该网络专为适应一级检测器而量身定制,并通过利用不同层中深层特征的自然特性来隐式学习实例不变特征。具体而言,我们从三个方面促进了自适应:(1)动态和类平衡重加权(DCBR)策略,该策略考虑了域内和类内变化的共存,为那些样本稀缺的类别和易于适应的样本分配更大的权重;(2)类别感知对象模式匹配(COPM)模块,该方法增强了分类信息引导下的跨域前景目标匹配,抑制了无信息背景特征;(3)正则化联合类别对齐(Regularized Joint Category Alignment,RJCA)模块,通过一致性正则化在不同领域特定层上联合执行类别对齐。实验表明,I3 Net在基准数据集上的性能超过了最先进的性能。

英文摘要:

Recent works on two-stage cross-domain detection have widely explored the local feature patterns to achieve more accurate adaptation results. These methods heavily rely on the region proposal mechanisms and ROI-based instance-level features to design fine-grained feature alignment modules with respect to the foreground objects. However, for one-stage detectors, it is hard or even impossible to obtain explicit instance-level features in the detection pipelines. Motivated by this, we propose an Implicit Instance-Invariant Network (I3Net), which is tailored for adapting one-stage detectors and implicitly learns instance-invariant features via exploiting the natural characteristics of deep features in different layers. Specifically, we facilitate the adaptation from three aspects: (1) Dynamic and Class-Balanced Reweighting (DCBR) strategy, which considers the coexistence of intra-domain and intra-class variations to assign larger weights to those sample-scarce categories and easy-to-adapt samples; (2) Category-aware Object Pattern Matching (COPM) module, which boosts the cross-domain foreground objects matching guided by the categorical information and suppresses the uninformative background features; (3) Regularized Joint Category Alignment (RJCA) module, which jointly enforces the category alignment at different domain-specific layers with a consistency regularization. Experiments reveal that I3Net exceeds the state-of-the-art performance on benchmark datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑