Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Boosting Single Positive Multi-label Classification with Generalized Robust Loss
Authors: Yanxi Chen, Chunxiao Li, Xinyang Dai, Jinhuan Li, Weiyu Sun, Yiming Wang, Renyuan Zhang, Tinghe Zhang, Bo Wang
IJCAI 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments show that our approach can significantly improve SPML performance and outperform the vast majority of state-of-the-art methods on all the four benchmarks. Our code is available at https://github.com/yan4xi1/GRLoss. Our contributions can be summarized in four-fold: Experimental level: We demonstrate the superiority of our GR Loss by conducting extensive empirical analysis with performance comparison against state-of-the-art SPML methods across four benchmarks. |
| Researcher Affiliation | Academia | Yanxi Chen , Chunxiao Li , Xinyang Dai , Jinhuan Li , Weiyu Sun , Yiming Wang , Renyuan Zhang , Tinghe Zhang and Bo Wang University of International Business and Economics EMAIL |
| Pseudocode | No | The paper provides mathematical formulations and descriptions of functions, but it does not include a dedicated pseudocode block or algorithm listing. |
| Open Source Code | Yes | Our code is available at https://github.com/yan4xi1/GRLoss. |
| Open Datasets | Yes | We evaluate our proposed GR Loss on four benchmark datasets: Pascal VOC-2012 (VOC) [Everingham and Winn, 2012], MS-COCO-2014(COCO) [Lin et al., 2014], NUS-WIDE(NUS) [Chua et al., 2009], and CUB200-2011(CUB) [Wah et al., 2011]. |
| Dataset Splits | Yes | We first simulate the single-positive label training environments commonly used in SPML [Cole et al., 2021], and replicate their training, validation and testing samples. In these datasets, only one positive label is randomly selected for each training instance, while the validation and test sets remain fully labeled. |
| Hardware Specification | No | The paper mentions employing 'Res Net-50 architecture' and being 'pre-trained on Image Net dataset' but does not specify the hardware (e.g., GPU, CPU models, memory) used to run the experiments. |
| Software Dependencies | No | The paper mentions using a 'Res Net-50 architecture' and refers to hyperparameter settings, but it does not provide specific version numbers for software dependencies such as Python, PyTorch, or CUDA. |
| Experiment Setup | Yes | Each image is resized into 448 × 448, and performed data augmentation by randomly flipping an image horizontally. We initially conduct a search to determine and fix the hyperparameters q2 and q3 in Eq.(14), typically 0.01 and 1, respectively. ... Therefore, we only need to adjust four hyperparameters in (β(T ), α(T )). More details about hyperparameter settings are described in Appendix E.2 of our full version. |