We lifted 5 functions out of this paper's own repositories and ran 4 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| inar-design/patt | canonical | 4 of 5 |
| Function | Status | Where it lives |
|---|---|---|
| ResNet18 | Ran | inar-design/patt/models/resnet.py code served (permissive licence) · get_code("c1c5637c9970cab6") |
| ResNet34 | Ran | inar-design/patt/models/resnet.py code served (permissive licence) · get_code("8de82e83c702450c") |
| ResNet50 | Ran | inar-design/patt/models/resnet_imagenet.py code served (permissive licence) · get_code("07c04376ec2f148f") |
| miller_recurrence | Ran | inar-design/patt/loss/proco.py code served (permissive licence) · get_code("87171ac55803dbfd") |
| tinyimages300k_dataloaders | Not yet run | inar-design/patt/dataset/tinyimages_300k.py code served (permissive licence) · get_code("0ddb7c161e4f4ff3") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Current out-of-distribution (OOD) detection methods typically assume balanced in-distribution (ID) data, while most real-world data follow a long-tailed distribution. Previous approaches to long-tailed OOD detection often involve balancing the ID data by reducing the semantics of head classes. However, this reduction can severely affect the classification accuracy of ID data. The main challenge of this task lies in the severe lack of features for tail classes, leading to confusion with OOD data. To tackle this issue, we introduce a novel Prioritizing Attention to Tail (PATT) method using augmentation instead of reduction. Our main intuition involves using a mixture of von Mises-Fisher (vMF) distributions to model the ID data and a temperature scaling module to boost the confidence of ID data. This enables us to generate infinite contrastive pairs, implicitly enhancing the semantics of ID classes while promoting differentiation between ID and OOD data. To further strengthen the detection of OOD data without compromising the classification performance of ID data, we propose feature calibration during the inference phase. By extracting an attention weight from the training set that prioritizes the tail classes and reduces the confidence in OOD data, we improve the OOD detection capability. Extensive experiments verified that our method outperforms the current state-of-the-art methods on various benchmarks.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2408.06742")
get_code_for_paper("2408.06742")
have("2408.06742")
Connect an agent — have() is free.