融合测试时增强与后处理检测，提升开放集识别性能。
Solution for OOD-CV Workshop SSB Challenge 2024 (Open-Set Recognition Track)
- 结合测试时增强与多种后处理OOD检测方法
- AUROC达79.77（第5名），FPR95为61.44（第2名）
- 适合关注开放集识别实际应用的研究者
本报告详细描述了我们在ECCV 2024年OOD-CV研讨会的开放集识别（OSR）挑战赛中探索与提出的方法。挑战任务是判断测试样本是否属于分类器训练集的语义类别。我们以语义漂移基准（SSB）为评估标准，采用ImageNet1k作为分布内（ID）数据集，ImageNet21k的一个子集作为分布外（OOD）数据集。为此，我们提出一种混合方法，实验了多种后处理OOD检测技术与不同测试时增强（TTA）策略的融合，并评估了多个基础模型对最终性能的影响。最佳方法结合了测试时增强与后处理技术，在AUROC与FPR95之间取得良好平衡。最终结果为AUROC: 79.77（排名第5），FPR95: 61.44（排名第2），整体排名第二。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。