Xiaojin Zhu, Yixuan Li, Xuefeng Du, Yiyou Sun
We lifted 6 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 |
|---|---|---|
| deeplearning-wisc/dream-ood | canonical | 1 of 3 |
| copy not recorded | — | 3 of 3 |
| Function | Status | Where it lives |
|---|---|---|
| cosine_annealing | Ran | this paper's copy was not recorded; identical code first harvested from lygjwy/dos pointer only · get_code("05eda95f9800a1e9") |
| chunk | Ran | this paper's copy was not recorded; identical code first harvested from vicgalle/stable-diffusion-aesthetic-gradients pointer only · get_code("8241c0562bc710fd") |
| get_class_names | Ran | deeplearning-wisc/dream-ood/scripts/dream_ood.py pointer only (licence: NOASSERTION) · get_code("10dfa7de61b0b5db") |
| numpy_to_pil | Ran | this paper's copy was not recorded; identical code first harvested from vicgalle/stable-diffusion-aesthetic-gradients pointer only · get_code("1e63d588563eb90a") |
| rand_bbox | Not yet run | deeplearning-wisc/dream-ood/scripts/train_gene_in100.py pointer only (licence: NOASSERTION) · get_code("d34a085d71b8f4b5") |
| recursion_change_bn | Not yet run | deeplearning-wisc/dream-ood/scripts/train_ood_det_in100.py pointer only (licence: NOASSERTION) · get_code("0cc8a17c73df40ee") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Utilizing auxiliary outlier datasets to regularize the machine learning model has demonstrated promise for out-of-distribution (OOD) detection and safe prediction. Due to the labor intensity in data collection and cleaning, automating outlier data generation has been a long-desired alternative. Despite the appeal, generating photorealistic outliers in the high dimensional pixel space has been an open challenge for the field. To tackle the problem, this paper proposes a new framework DREAM-OOD, which enables imagining photo-realistic outliers by way of diffusion models, provided with only the in-distribution (ID) data and classes. Specifically, DREAM-OOD learns a text-conditioned latent space based on ID data, and then samples outliers in the low-likelihood region via the latent, which can be decoded into images by the diffusion model. Different from prior works [18,98], DREAM-OOD enables visualizing and understanding the imagined outliers, directly in the pixel space. We conduct comprehensive quantitative and qualitative studies to understand the efficacy of DREAM-OOD, and show that training with the samples generated by DREAM-OOD can benefit OOD detection performance. Code is publicly available at https://github.com/deeplearning-wisc/dream-ood. 37th Conference on Neural Information Processing Systems (NeurIPS 2023).
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2309.13415")
get_code_for_paper("2309.13415")
have("2309.13415")
Connect an agent — have() is free.