Signal‑Routed Temperature Scaling (SRTS‑BCE) is a 10‑parameter, argmax‑preserving calibration method that separates calibration objectives from adaptive capacity. It cross‑fits a correctness‑risk score over six logit statistics and assigns a top‑label BCE temperature to each of three risk groups, generalizing TvA‑TS when K=1. Experiments on fine‑tuned CIFAR‑100 and ViT‑B/16 show that SRTS‑BCE reduces ECE from 1.65 to 0.96 with a small calibration budget, outperforming higher‑capacity SMART+BCE when only 250 examples are available, and revealing a budget‑dependent ranking reversal on Swin‑T.
By Wenhao Liang, Liangwei Nathan Zheng, Lin Yue, Wei Emma Zhang, Mingyu Guo, Olaf Maennel, Weitong Chen
arXiv:2410.18321v3 Announce Type: replace
Abstract: Confidence calibration matters wherever a classifier's probabilities, not just its labels, are consumed downstream. We study Focal Calibration Loss...
By Wenhao Liang, Liangwei Zheng, Wei Zhang, Weitong Chen
arXiv:2606. 20364v1 Announce Type: new Abstract: A companion study established a de-biased, cross-model VLM-as-3D-judge that reliably ranks single-image-to-3D mesh quality where cheap geometry and CLIP proxies fall short.
By Ali Asaria, Tony Salomone, Deep Gandhi
arXiv:2608. 10372v1 Announce Type: new Abstract: Post-hoc calibration aligns a classifier's predicted confidences with its empirical accuracy without retraining.
By Lening Zhao, Qipeng Zhan, Li Shen
arXiv:2512.04305v3 Announce Type: replace
Abstract: Vision-language models (VLMs) such as CLIP are increasingly adapted across decentralized data silos, yet the reliability of their predictions under...
By Mainak Singha, Masih Aminbeidokhti, Paolo Casari, Gianni Franchi, Elisa Ricci, Subhankar Roy
Reliable confidence estimates are essential in semantic segmentation, especially in safety-critical settings where overconfident errors can mislead downstream decisions. Yet modern segmentation models often remain miscalibrated.
arXiv:2608. 03020v1 Announce Type: new Abstract: Parameter-efficient post-training reduces the number of trainable parameters, but still requires repeated end-to-end backpropagation through the frozen backbone.
By Linhan Xia, Rui Liu, Zhaofeng Zhang, Yihao Wang, Binrui Shen, Shengxin Zhu
The paper demonstrates that Mixture-of-Experts (MoE) models can avoid the need for calibration data when selecting which expert channels to load during decoding. Instead of using a calibrated threshold, a top‑k selection strategy—choosing the k highest‑scoring channels per token—achieves comparable or better performance without calibration. Additionally, the authors propose a reader that uses a ternary sketch and low‑rank mapping to recover skipped channels, achieving 98.1% of full‑model accuracy while reading only 17.8% of expert weights and speeding up inference by up to 2.69× compared to optimized vLLM.
By Geunhyoung Kim, Sung Ju Hwang
arXiv:2607. 01902v1 Announce Type: cross Abstract: Reliable confidence estimates are essential in semantic segmentation, especially in safety-critical settings where overconfident errors can mislead downstream decisions.
By Tristan Kirscher (ICube), Kim-Celine Kahl (DKFZ), Balint Kovacs (DKFZ), Maximilian R. Rokuss (DKFZ), Klaus Maier-Hein (DKFZ), Xavier Coubez (ICube), Philippe Meyer (ICube), Sylvain Faisan (ICube)
arXiv:2607. 12928v1 Announce Type: new Abstract: We study the online binary sequential calibration problem.
By Zihan Zhang
Parameter-efficient post-training reduces the number of trainable parameters, but still requires repeated end-to-end backpropagation through the frozen backbone. Every adaptation step therefore needs backward-capable hardware and must store or recompute activations.
arXiv:2609.26839v1 Announce Type: cross
Abstract: Post-hoc probability calibration is usually evaluated under an optimistic assumption: the held-out calibration labels are clean. In many AI deploymen...
By Zeming Liu, Hang Lyu, Jingtao Zhang, Yuan Xie