Research map / Label-efficient and robust learning / Recognition and long-tail
Single-Label Multi-Class Image Classification by Deep Logistic Regression
Qi Dong, Xiatian Zhu, Shaogang Gong
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 |
|---|---|---|---|
| Replace SR with SS-LR | ResNet-32 · CIFAR10 | top-1 accuracy (%): 92.5 -> 93.0 | Improved |
| Replace SR with SS-LR | ResNet-32 · CIFAR100 | top-1 accuracy (%): 68.1 -> 69.1 | Improved |
| Replace SR with SS-LR | ResNet-32 · Tiny200 | top-1 accuracy (%): 50.2 -> 56.0 | Improved |
| Replace SR with SS-LR | WideResNet-28-10 · CIFAR100 | top-1 accuracy (%): 81.0 -> 81.2 | Improved |
| Replace SR with SS-LR | WideResNet-28-10 · Tiny200 | top-1 accuracy (%): 57.4 -> 61.0 | Improved |
| Replace SR with SS-LR | WideResNet-28-10 · CIFAR10 | top-1 accuracy (%): 95.3 -> 96.0 | Improved |
| Replace SR with HS-LR | ResNet-50 · Market-1501 | Rank-1 (%): 83.3 -> 87.1 | Improved |
| Replace SR with HS-LR | ResNet-50 · DukeMTMC | mAP (%): 54.9 -> 60.1 | Improved |
| Replace SR with HS-LR | MobileNet · DukeMTMC | Rank-1 (%): 57.0 -> 63.7 | Improved |
| Replace SR with HS-LR | MobileNet · DukeMTMC | mAP (%): 35.8 -> 42.5 | Improved |
| Replace vanilla LR with HS-LR | ResNet-50 · DeepFashion | per-class accuracy (%): 50.1 -> 59.0 | Improved |
| Replace vanilla LR with SS-LR | ResNet-50 · DeepFashion | per-class mAP (%): 2.5 -> 9.2 | Improved |
Closest papers by meaning
- A no-regret generalization of hierarchical softmax to extreme multi-label classification (NeurIPS 2018 · similarity 0.86)
- On the Learning Property of Logistic and Softmax Losses for Deep Neural Networks (AAAI 2020 · similarity 0.86)
- Multi-Label Learning From Single Positive Labels (CVPR 2021 · similarity 0.85)
- Taming the Sigmoid Bottleneck: Provably Argmaxable Sparse Multi-Label Classification (AAAI 2024 · similarity 0.85)
- Self-Paced Unified Representation Learning for Hierarchical Multi-Label Classification (AAAI 2024 · similarity 0.85)
- Rethinking Self-Distillation: Label Averaging and Enhanced Soft Label Refinement with Partial Labels (ICLR 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.
