LoD: Loss-difference OOD Detection by Intentionally Label-Noisifying Unlabeled Wild Data
Authors: Chuanxing Geng, Qifei Li, Xinrui Wang, Dong Liang, Songcan Chen, Pong C. Yuen
IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We also provide theoretical foundation for Lo D s viability, and extensive experiments verify its superiority. |
| Researcher Affiliation | Academia | 1College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics 2Department of Computer Science, Hong Kong Baptist University 3MIIT Key Laboratory of Pattern Analysis and Machine Intelligence EMAIL, EMAIL |
| Pseudocode | Yes | Algorithm 1 Lo D OOD Detection Framework |
| Open Source Code | Yes | Our Lo D (https://github.com/Chuanxing Geng/Lo D) framework contains two main modules, i.e., loss-difference OOD filtering module and OOD detector learning module. |
| Open Datasets | Yes | For standard benchmarks, we here follow [Du et al., 2024; Katz-Samuels et al., 2022], and choose CIFAR100 as in-distribution (ID) datasets (Pin). For the outof-distribution (OOD) test datasets (Pout), we use a diverse collection of natural image datasets including SVHN [Netzer et al., 2011], Textures [Cimpoi et al., 2014], Places [Zhou et al., 2017], LSUN-Crop [Yu et al., 2015] and LSUN-Resize [Yu et al., 2015]. ... We here select CIFAR10, CIFAR+10, CIFAR+50, and Tiny Image Net [Vaze et al., 2022] to curate the hard OOD benchmarks, and more details can be found in Appendix B of supplementary materials. |
| Dataset Splits | Yes | Specifically, the ID dataset is split into two equal halves (25,000 images per half), with one half used to mix with an OOD dataset (e.g., SVHN) to create the unlabeled wild data (Pwild). ... the training set of 6 ID classes is divided into two halves (15,000 images per half). One half is used as labeled ID data, while the other half is mixed with the data from 4 OOD classes to create the unlabeled wild data. |
| Hardware Specification | Yes | All experiments are conducted on a single NVIDIA RTX 3090 GPU. |
| Software Dependencies | No | The paper mentions "Wide Res Net [Zagoruyko, 2016]" as the backbone and "stochastic gradient descent" as the optimizer, but it does not specify version numbers for any software libraries or frameworks like PyTorch, TensorFlow, CUDA, etc. |
| Experiment Setup | Yes | For these two modules, we follow [Du et al., 2024; Katz-Samuels et al., 2022] and employ Wide Res Net [Zagoruyko, 2016] with 40 layers and widen factor of 2 as the backbone. Moreover, for the loss-difference OOD filtering module, we use stochastic gradient descent with a momentum of 0.9 as the optimizer, and set the initial learning rate to 0.01. We train for 100 epochs using cosine learning rate decay, a batch size of 128 in which |Btrain in | : |Bwild| = 3 : 1 , and a dropout rate of 0.3. For the OOD detector learning module, similar to [Du et al., 2024], we load a pre-trained ID classifier and add an additional linear layer which utilize the penultimate-layer features of ID classifier for binary classification. The initial learning rate is set to 0.001, and the remaining training configurations are consistent with those of the former module. |