Research map / Label-efficient and robust learning / Noisy labels
Learning From Noisy Web Data With Category-Level Supervision
Li Niu, Qingtao Tang, Ashok Veeraraghavan, Ashutosh Sabharwal
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add category-level hybrid semantic supervision and jointly train the classifier with semantic VAE | WSCI · AwA2, CUB, and SUN Attribute | accuracy (%): 86.41 -> 91.14; 75.02 -> 77.34; 40.56 -> 42.26 | Improved |
| Add category-level information using a semantic VAE, rather than a detached plain VAE without category-level information (ablation) | WSCI · AwA2, CUB, and SUN Attribute | accuracy (%): 86.15 -> 88.88; 74.17 -> 76.28; 37.91 -> 41.23 | Improved |
| Jointly leverage category-level supervision in the classifier and semantic VAE, rather than use separate classification flows (ablation) | WSCI · AwA2, CUB, and SUN Attribute | accuracy (%): 88.88 -> 91.14; 76.28 -> 77.34; 41.23 -> 42.26 | Improved |
| Add visual encoding to the hybrid semantic representation (ablation) | WSCI · AwA2, CUB, and SUN Attribute | accuracy (%): 90.52 -> 91.14; 76.86 -> 77.34; 41.97 -> 42.26 | Improved |
| Add attribute vectors to the hybrid semantic representation (ablation) | WSCI · AwA2, CUB, and SUN Attribute | accuracy (%): 89.56 -> 91.14; 76.61 -> 77.34; 41.03 -> 42.26 | Improved |
| Use WSCI rather than Xiao et al. | SUN Attribute · s(201) and s(401) | accuracy (%): 39.85 -> 41.79; 39.00 -> 41.47 | Improved |
Closest papers by meaning
- Learning From Web Data With Self-Organizing Memory Module (CVPR 2020 · similarity 0.85)
- Robust Weak Supervision with Variational Auto-Encoders (ICML 2023 · similarity 0.85)
- Capturing Label Characteristics in VAEs (ICLR 2021 · similarity 0.84)
- CurriculumNet: Weakly Supervised Learning from Large-Scale Web Images (ECCV 2018 · similarity 0.84)
- Learning with Marginalized Corrupted Features and Labels Together (AAAI 2016 · similarity 0.84)
- A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data (ICLR 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
