Research map / Label-efficient and robust learning / Noisy labels
Coupled-View Deep Classifier Learning from Multiple Noisy Annotators
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| use CVL coupled-view learning instead of majority voting labels | VGG-like CNN · MNIST-2 | last-epoch accuracy: 29.77 -> 98.60 | Helped |
| use CVL instead of MBEM | VGG-like CNN · MNIST-2 | last-epoch accuracy: 94.65 -> 98.60 | Helped |
| use CVL instead of AggNet | VGG-like CNN · MNIST-1 best accuracy | best accuracy: -0.12 minimal improvement | No clear effect |
| use CVL instead of best baseline | VGG-like CNN · CIFAR10-2 | last-epoch accuracy: 84.05 -> 86.67 | Helped |
| use CVL instead of DL-CL | VGG-16 · LabelMe-AMT | test accuracy: 83.151 -> 86.027 | Helped |
| increase beta_d from 0.5 to 1.4 (ablation) | CVL · CIFAR10-1 | last-epoch accuracy: 69.94 -> 83.85 | Helped |
| increase beta_d from 1.4 to 2.0 (ablation) | CVL · CIFAR10-1 | last-epoch accuracy: 83.85 -> 73.76 | Hurt |
| vary beta_l from 0.5 to 2.0 (ablation) | CVL · CIFAR10-1 | last-epoch accuracy: 83.75 -> 83.76 | No clear effect |
| add co-teaching strategy (ablation) | CVL · CIFAR10-1 | accuracy | Helped |
| add class-weighted loss (ablation) | CVL · CIFAR10-1 | accuracy | Helped |
| add outlier detection (ablation) | CVL · CIFAR10-1 | accuracy | Helped |
Closest papers by meaning
- Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learning (CVPR 2024 · similarity 0.85)
- Noisy Label Calibration for Multi-View Classification (AAAI 2025 · similarity 0.85)
- Pre-Trained Vision-Language Models as Noisy Partial Annotators (AAAI 2025 · similarity 0.84)
- Double-Layer Hybrid-Label Identification Feature Selection for Multi-View Multi-Label Learning (AAAI 2024 · similarity 0.84)
- MLC-NC: Long-Tailed Multi-Label Image Classification Through the Lens of Neural Collapse (AAAI 2025 · similarity 0.84)
- Learning with Open-world Noisy Data via Class-independent Margin in Dual Representation Space (AAAI 2025 · similarity 0.84)
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.