Redefining Normal: A Novel Object-Level Approach for Multi-Object Novelty Detection
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909429921742848 |
|---|---|
| author | Salehi, Mohammadreza Apostolikas, Nikolaos Gavves, Efstratios Snoek, Cees G. M. Asano, Yuki M. |
| author_facet | Salehi, Mohammadreza Apostolikas, Nikolaos Gavves, Efstratios Snoek, Cees G. M. Asano, Yuki M. |
| contents | In the realm of novelty detection, accurately identifying outliers in data without specific class information poses a significant challenge. While current methods excel in single-object scenarios, they struggle with multi-object situations due to their focus on individual objects. Our paper suggests a novel approach: redefining `normal' at the object level in training datasets. Rather than the usual image-level view, we consider the most dominant object in a dataset as the norm, offering a perspective that is more effective for real-world scenarios. Adapting to our object-level definition of `normal', we modify knowledge distillation frameworks, where a student network learns from a pre-trained teacher network. Our first contribution, DeFeND(Dense Feature Fine-tuning on Normal Data), integrates dense feature fine-tuning into the distillation process, allowing the teacher network to focus on object-level features with a self-supervised loss. The second is masked knowledge distillation, where the student network works with partially hidden inputs, honing its ability to deduce and generalize from incomplete data. This approach not only fares well in single-object novelty detection but also considerably surpasses existing methods in multi-object contexts. The implementation is available at: https://github.com/SMSD75/Redefining_Normal_ACCV24/tree/main |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_11148 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Redefining Normal: A Novel Object-Level Approach for Multi-Object Novelty Detection Salehi, Mohammadreza Apostolikas, Nikolaos Gavves, Efstratios Snoek, Cees G. M. Asano, Yuki M. Computer Vision and Pattern Recognition In the realm of novelty detection, accurately identifying outliers in data without specific class information poses a significant challenge. While current methods excel in single-object scenarios, they struggle with multi-object situations due to their focus on individual objects. Our paper suggests a novel approach: redefining `normal' at the object level in training datasets. Rather than the usual image-level view, we consider the most dominant object in a dataset as the norm, offering a perspective that is more effective for real-world scenarios. Adapting to our object-level definition of `normal', we modify knowledge distillation frameworks, where a student network learns from a pre-trained teacher network. Our first contribution, DeFeND(Dense Feature Fine-tuning on Normal Data), integrates dense feature fine-tuning into the distillation process, allowing the teacher network to focus on object-level features with a self-supervised loss. The second is masked knowledge distillation, where the student network works with partially hidden inputs, honing its ability to deduce and generalize from incomplete data. This approach not only fares well in single-object novelty detection but also considerably surpasses existing methods in multi-object contexts. The implementation is available at: https://github.com/SMSD75/Redefining_Normal_ACCV24/tree/main |
| title | Redefining Normal: A Novel Object-Level Approach for Multi-Object Novelty Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2412.11148 |