Research map / Label-efficient and robust learning / Recognition and long-tail
Perception and Semantic Aware Regularization for Sequential Confidence Calibration
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 |
|---|---|---|---|
| Add perception- and semantic-similar sequence regularization | TRBA · English STR benchmark | ECE: 0.92 -> 0.36 | Helped |
| Add perception- and semantic-similar sequence regularization | TRBC · English STR benchmark | ECE: 2.73 -> 0.47 | Helped |
| Add perception- and semantic-similar sequence regularization | TRBA · English STR benchmark | accuracy: 85.51 -> 86.45 | Helped |
| Add perception- and semantic-similar sequence regularization | U2-Tfm · AISHELL-1 | accuracy: 58.81 -> 57.36 | Hurt |
| Add perception- and semantic-similar sequence regularization | U2-Tfm · AISHELL-1 | ECE: 22.75 -> 2.21 | Helped |
| Add hardness-ranking adaptive calibration (ablation) | PSSR on TRBA · English STR benchmark | ECE: 0.74 -> 0.36 | Helped |
| Add hardness-ranking adaptive calibration (ablation) | PSSR on TRBC · English STR benchmark | ECE: 1.19 -> 0.47 | Helped |
| Increase the proportion of perceptually similar sequences in the regularization set (ablation) | PSSR · English STR benchmark, TRBC | calibration performance | Helped |
| Increase the proportion of perceptually similar sequences in the regularization set (ablation) | PSSR · English STR benchmark, TRBA | calibration performance | Mixed |
Closest papers by meaning
- Understanding and Mitigating Miscalibration in Prompt Tuning for Vision-Language Models (ICML 2025 · similarity 0.87)
- Pre-Trained Vision-Language Models as Noisy Partial Annotators (AAAI 2025 · similarity 0.86)
- Open-Vocabulary Calibration for Fine-tuned CLIP (ICML 2024 · similarity 0.86)
- Vision-Language Models are Strong Noisy Label Detectors (NeurIPS 2024 · similarity 0.85)
- Concept-Aware Batch Sampling Improves Language-Image Pretraining (CVPR 2026 · similarity 0.85)
- Non-autoregressive Sequence-to-Sequence Vision-Language Models (CVPR 2024 · similarity 0.85)
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.