Solution for OOD-CV Workshop SSB Challenge 2024 (Open-Set Recognition Track)
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909330812436480 |
|---|---|
| author | Feng, Mingxu Chao, Dian Zheng, Peng Yang, Yang |
| author_facet | Feng, Mingxu Chao, Dian Zheng, Peng Yang, Yang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_20277 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Solution for OOD-CV Workshop SSB Challenge 2024 (Open-Set Recognition Track) Feng, Mingxu Chao, Dian Zheng, Peng Yang, Yang Computer Vision and Pattern Recognition Machine Learning 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. |
| title | Solution for OOD-CV Workshop SSB Challenge 2024 (Open-Set Recognition Track) |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2409.20277 |