论文标题
利用各种特征和对域自适应细分的对抗性矛盾性
Exploiting Diverse Characteristics and Adversarial Ambivalence for Domain Adaptive Segmentation
论文作者
论文摘要
将语义细分模型调整为新领域是一个重要但具有挑战性的问题。最近已经取得了启发性的进度，但是现有方法的性能在真实数据集上并不令人满意，在这些数据集中，新的目标域由异质的亚域组成（例如，多样化的天气特征）。我们指出，仔细的关于目标域中多种模式的推理可以改善适应模型的鲁棒性。为此，我们提出了一个条件引导的适应框架，该框架由特殊的渐进式对抗训练（APAT）机制和新颖的自我训练政策所赋予的能力。 APAT策略逐渐执行特定条件的对齐和专注的全局功能匹配。新的自我训练方案利用了易于和硬适应区域的对抗性矛盾，以及目标子域之间的相关性。我们在天气条件下目标图像有所不同的各种适应场景上评估我们的方法（DCAA）。与基准和最先进的方法的比较证明了DCAA优于竞争对手。
Adapting semantic segmentation models to new domains is an important but challenging problem. Recently enlightening progress has been made, but the performance of existing methods are unsatisfactory on real datasets where the new target domain comprises of heterogeneous sub-domains (e.g., diverse weather characteristics). We point out that carefully reasoning about the multiple modalities in the target domain can improve the robustness of adaptation models. To this end, we propose a condition-guided adaptation framework that is empowered by a special attentive progressive adversarial training (APAT) mechanism and a novel self-training policy. The APAT strategy progressively performs condition-specific alignment and attentive global feature matching. The new self-training scheme exploits the adversarial ambivalences of easy and hard adaptation regions and the correlations among target sub-domains effectively. We evaluate our method (DCAA) on various adaptation scenarios where the target images vary in weather conditions. The comparisons against baselines and the state-of-the-art approaches demonstrate the superiority of DCAA over the competitors.
