Relaxed Softmax: Efficient Confidence Auto-Calibration for Safe Pedestrian Detection
By Lukás Neumann, Andrew Zisserman, Andrea Vedaldi. 2018
92 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Safety, Robustness & Interpretability
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Dacheng Tao
- Chunhua Shen
- Xiaogang Wang
- Ming-Hsuan Yang
- Andrew Zisserman
- Andrea Vedaldi
- Trevor Darrell
In Safety, Robustness & Interpretability
- Patrick Pérez
- Zsolt Kira
- Mattia Segu
- Hongxia Jin
- Yilin Shen
- Yen-Chang Hsu
- E.J. Candes
- Antonio Loquercio
Citations in the corpus
- A General Framework for Uncertainty Estimation in Deep Learning (2019, background): “Given the paramount importance of safety, autonomous driving research has allocated a lot of attention to the problem of uncertainty estimation, from both the perception [18], [19] and the control side [13], [14].”
- Mask Scoring R-CNN (2019, background): “[29] proposed Relaxed Softmax to predict temperature scaling factor value in standard softmax for safety-critical pedestrian detection.”
- Addressing Failure Prediction by Learning Model Confidence (2019, background): “In tasks closely related to failure prediction, other approaches also identified the issue of MCP regarding high confidence predictions [17, 30, 26, 28, 13, 40].”
- Generalized ODIN: Detecting Out-of-Distribution Image Without Learning From Out-of-Distribution Data (2020, background): “The g(x) in Equation 5 can be immediately viewed as a learned temperature scaling function discussed in [28] and a concurrent report [37].”
- Classification with Valid and Adaptive Coverage (2020, background): “A different but related line of work focuses on post-processing the output of black-box classification algorithms to produce more accurate probability estimates [6, 11, 15, 16, 22, 27, 28], although without achieving prediction sets with provable finite-sample coverage.”
- Multivariate Confidence Calibration for Object Detection (2020, methodology): “In other words, we do not modify the learning objective of a detector and thus our work is orthogonal to ongoing research in regularization methods for calibration [15, 22, 18].”