Research map / Label-efficient and robust learning / Recognition and long-tail
A Sequential Set Generation Method for Predicting Set-Valued Outputs
Tian Gao, Jie Chen, Vijil Chenthamarakshan, Michael Witbrock
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 |
|---|---|---|---|
| use a CNN lambda-optimizer instead of the sigmoid-network multi-label method | SSG · YEAST | mF1: 0.430 -> 0.658 | Improved |
| use a CNN lambda-optimizer instead of the sigmoid-network multi-label method | SSG · SCENE | mF1: 0.455 -> 0.605 | Improved |
| use an RNN lambda-optimizer instead of the sigmoid-network multi-label method | SSG · YEAST | mF1: 0.430 -> 0.402 | Hurt |
| use an RNN lambda-optimizer instead of the sigmoid-network multi-label method | SSG · SCENE | mF1: 0.455 -> 0.378 | Hurt |
| use a CNN lambda-optimizer instead of fixed position-specific penalties (ablation) | SSG-S · Task 1 | mF1: 0.19 -> 0.70 | Improved |
| use a CNN lambda-optimizer instead of an RNN lambda-optimizer (ablation) | SSG · Task 1 | mF1: 0.42 -> 0.70 | Improved |
| use an RNN lambda-optimizer instead of fixed position-specific penalties (ablation) | SSG-S · Task 1 | mF1: 0.19 -> 0.42 | Improved |
| use a CNN lambda-optimizer instead of fixed position-specific penalties (ablation) | SSG-S · Task 2 | mED: 8.10 -> 2.00 | Improved |
| use an RNN lambda-optimizer instead of fixed position-specific penalties (ablation) | SSG-S · Task 2 | mED: 8.10 -> 3.75 | Improved |
| use a CNN lambda-optimizer instead of an RNN lambda-optimizer (ablation) | SSG · Task 2 | mED: 3.75 -> 2.00 | Improved |
| use a CNN lambda-optimizer instead of the sigmoid-network multi-label method | SSG · Task 1 | mF1: 0.64 -> 0.70 | Improved |
Closest papers by meaning
- Maximizing Subset Accuracy with Recurrent Neural Networks in Multi-label Classification (NeurIPS 2017 · similarity 0.87)
- Enhancing Multi-Label Classification via Dynamic Label-Order Learning (AAAI 2024 · similarity 0.84)
- Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning (NeurIPS 2025 · similarity 0.83)
- Multi-Label Open Set Recognition (NeurIPS 2024 · similarity 0.83)
- Incremental Sequence Classification with Temporal Consistency (NeurIPS 2025 · similarity 0.82)
- Divide and Conquer: Learning Label Distribution with Subtasks (ICML 2025 · similarity 0.82)
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.
