This report provides a detailed description of the method we explored and proposed in the OSR Challenge at the OOD-CV Workshop during ECCV 2024. The challenge required identifying whether a test sample belonged to the semantic classes of a classifier's training set, a task known as open-set recognition (OSR). Using the Semantic Shift Benchmark (SSB) for evaluation, we focused on ImageNet1k as the in-distribution (ID) dataset and a subset of ImageNet21k as the out-of-distribution (OOD) dataset.To address this, we proposed a hybrid approach, experimenting with the fusion of various post-hoc OOD detection techniques and different Test-Time Augmentation (TTA) strategies. Additionally, we evaluated the impact of several base models on the final performance. Our best-performing method combined Test-Time Augmentation with the post-hoc OOD techniques, achieving a strong balance between AUROC and FPR95 scores. Our approach resulted in AUROC: 79.77 (ranked 5th) and FPR95: 61.44 (ranked 2nd), securing second place in the overall competition.

翻译：本报告详细阐述了我们在ECCV 2024 OOD-CV研讨会开放集识别挑战赛中探索并提出的方法。该挑战赛要求判断测试样本是否属于分类器训练集的语义类别，这一任务被称为开放集识别。我们使用语义偏移基准进行评估，重点关注将ImageNet1k作为分布内数据集，并将ImageNet21k的一个子集作为分布外数据集。为此，我们提出了一种混合方法，尝试融合多种后验OOD检测技术与不同的测试时增强策略。此外，我们还评估了多种基础模型对最终性能的影响。我们性能最佳的方法将测试时增强与后验OOD技术相结合，在AUROC和FPR95分数之间取得了良好的平衡。我们的方法最终取得了AUROC: 79.77（排名第5）和FPR95: 61.44（排名第2）的成绩，在总排名中位列第二。