Though feature-alignment based Domain Adaptive Object Detection (DAOD) have
achieved remarkable progress, they ignore the source bias issue, i.e. the
aligned features are more favorable towards the source domain, leading to a
sub-optimal adaptation. Furthermore, the presence of domain shift between the
source and target domains exacerbates the problem of inconsistent
classification and localization in general detection pipelines. To overcome
these challenges, we propose a novel Distillation-based Unbiased Alignment
(DUA) framework for DAOD, which can distill the source features towards a more
balanced position via a pre-trained teacher model during the training process,
alleviating the problem of source bias effectively. In addition, we design a
Target-Relevant Object Localization Network (TROLN), which can mine
target-related knowledge to produce two classification-free metrics (IoU and
centerness). Accordingly, we implement a Domain-aware Consistency Enhancing
(DCE) strategy that utilizes these two metrics to further refine classification
confidences, achieving a harmonization between classification and localization
in cross-domain scenarios. Extensive experiments have been conducted to
manifest the effectiveness of this method, which consistently improves the
strong baseline by large margins, outperforming existing alignment-based works.

提出了基于蒸馏的无偏对齐 (Distillation-based Unbiased Alignment, DUA) 框架及目标相关对象定位网络 (Target-Relevant Object Localization Network, TROLN)，解决了领域自适应目标检测中源偏差和领域转移问题，通过蒸馏方式调整源特征位置，利用目标相关知识生成无需分类的两个度量指标 (IoU 和 centerness)，并采用领域感知的一致性增强策略 (DCE) 进一步改善分类一致性和定位准确性，在跨领域情景中显著提升性能，超过已有基于对齐的方法。

DUA-DA：基于蒸馏的无偏领域自适应目标检测

DUA-DA: Distillation-based Unbiased Alignment for Domain Adaptive Object  Detection

Aggregating features in terms of different convolutional blocks or contextual
embeddings has been proven to be an effective way to strengthen feature
representations for semantic segmentation. However, most of the current popular
network architectures tend to ignore the misalignment issues during the feature
aggregation process caused by 1) step-by-step downsampling operations, and 2)
indiscriminate contextual information fusion. In this paper, we explore the
principles in addressing such feature misalignment issues and inventively
propose Feature-Aligned Segmentation Networks (AlignSeg). AlignSeg consists of
two primary modules, i.e., the Aligned Feature Aggregation (AlignFA) module and
the Aligned Context Modeling (AlignCM) module. First, AlignFA adopts a simple
learnable interpolation strategy to learn transformation offsets of pixels,
which can effectively relieve the feature misalignment issue caused by
multiresolution feature aggregation. Second, with the contextual embeddings in
hand, AlignCM enables each pixel to choose private custom contextual
information in an adaptive manner, making the contextual embeddings aligned
better to provide appropriate guidance. We validate the effectiveness of our
AlignSeg network with extensive experiments on Cityscapes and ADE20K, achieving
new state-of-the-art mIoU scores of 82.6% and 45.95%, respectively. Our source
code will be made available.

本文提出特征对齐分割网络 (AlignSeg)，通过特征对齐聚合模块和对齐上下文建模模块解决多分辨率特征聚合所引起的特征不对齐问题。在 Cityscapes 和 ADE20K 数据集上进行的实验表明，本研究提出的 AlignSeg 网络实现了 82.6% 和 45.95% 的 IoU 分数，取得了新的最优结果。