Open world object detection faces a significant challenge in domain-invariant representation, i.e., implicit non-causal factors. Most domain generalization (DG) methods based on domain adversarial learning (DAL) pay much attention to learn domain-invariant information, but often overlook the potential non-causal factors. We unveil two critical causes: 1) The domain discriminator-based DAL method is subject to the extremely sparse domain label, i.e., assigning only one domain label to each dataset, thus can only associate explicit non-causal factor, which is incredibly limited. 2) The non-causal factors, induced by unidentified data bias, are excessively implicit and cannot be solely discerned by conventional DAL paradigm. Based on these key findings, inspired by the Granular-Ball perspective, we propose an improved DAL method, i.e., GB-DAL. The proposed GB-DAL utilizes Prototype-based Granular Ball Splitting (PGBS) module to generate more dense domains from limited datasets, akin to more fine-grained granular balls, indicating more potential non-causal factors. Inspired by adversarial perturbations akin to non-causal factors, we propose a Simulated Non-causal Factors (SNF) module as a means of data augmentation to reduce the implicitness of non-causal factors, and facilitate the training of GB-DAL. Comparative experiments on numerous benchmarks demonstrate that our method achieves better generalization performance in novel circumstances.

翻译：开放世界目标检测面临领域不变表示（即隐式非因果因素）的重大挑战。大多数基于领域对抗学习（DAL）的领域泛化（DG）方法过于关注学习领域不变信息，却往往忽视潜在的非因果因素。我们揭示了两大关键原因：1）基于领域判别器的DAL方法受限于极度稀疏的领域标签（即每个数据集仅分配一个领域标签），因此只能关联显式非因果因素，其能力极为有限；2）由未识别数据偏差诱导的非因果因素具有过度隐晦性，无法通过传统DAL范式单独辨识。基于这些关键发现，受粒度球视角启发，我们提出改进的DAL方法——GB-DAL。该方法通过原型粒度球划分（PGBS）模块，从有限数据集中生成更密集的领域（类似于更细粒度的粒度球），从而揭示更多潜在非因果因素。受类似非因果因素的对抗扰动启发，我们提出模拟非因果因素（SNF）模块作为数据增强手段，以降低非因果因素的隐晦性，并促进GB-DAL的训练。在多个基准测试上的对比实验表明，本方法在新场景中实现了更优的泛化性能。