Learning to Calibrate for Reliable Visual Fire Detection
- URL: http://arxiv.org/abs/2502.09872v1
- Date: Fri, 14 Feb 2025 02:45:16 GMT
- Title: Learning to Calibrate for Reliable Visual Fire Detection
- Authors: Ziqi Zhang, Xiuzhuang Zhou, Xiangyang Gong,
- Abstract summary: Fire is characterized by its sudden onset and destructive power, making early fire detection crucial for ensuring human safety and protecting property.
Deep learning models often exhibit a tendency toward overconfidence, and most existing works focus primarily on enhancing classification performance.
We propose transforming the Expected Error (ECE), a metric for measuring uncertainty, into a differentiable ECE loss function.
This loss is then combined with the cross-entropy loss to guide the training process of multi-class fire detection models.
- Score: 8.483524700407157
- License:
- Abstract: Fire is characterized by its sudden onset and destructive power, making early fire detection crucial for ensuring human safety and protecting property. With the advancement of deep learning, the application of computer vision in fire detection has significantly improved. However, deep learning models often exhibit a tendency toward overconfidence, and most existing works focus primarily on enhancing classification performance, with limited attention given to uncertainty modeling. To address this issue, we propose transforming the Expected Calibration Error (ECE), a metric for measuring uncertainty, into a differentiable ECE loss function. This loss is then combined with the cross-entropy loss to guide the training process of multi-class fire detection models. Additionally, to achieve a good balance between classification accuracy and reliable decision, we introduce a curriculum learning-based approach that dynamically adjusts the weight of the ECE loss during training. Extensive experiments are conducted on two widely used multi-class fire detection datasets, DFAN and EdgeFireSmoke, validating the effectiveness of our uncertainty modeling method.
Related papers
- Enhancing Training Data Attribution for Large Language Models with Fitting Error Consideration [74.09687562334682]
We introduce a novel training data attribution method called Debias and Denoise Attribution (DDA)
Our method significantly outperforms existing approaches, achieving an averaged AUC of 91.64%.
DDA exhibits strong generality and scalability across various sources and different-scale models like LLaMA2, QWEN2, and Mistral.
arXiv Detail & Related papers (2024-10-02T07:14:26Z) - Selective Learning: Towards Robust Calibration with Dynamic Regularization [79.92633587914659]
Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance.
We introduce Dynamic Regularization (DReg) which aims to learn what should be learned during training thereby circumventing the confidence adjusting trade-off.
arXiv Detail & Related papers (2024-02-13T11:25:20Z) - OpenNet: Incremental Learning for Autonomous Driving Object Detection
with Balanced Loss [3.761247766448379]
The proposed method can obtain better performance than that of the existing methods.
The Experimental results upon the CODA dataset show that the proposed method can obtain better performance than that of the existing methods.
arXiv Detail & Related papers (2023-11-25T06:02:50Z) - EvCenterNet: Uncertainty Estimation for Object Detection using
Evidential Learning [26.535329379980094]
EvCenterNet is a novel uncertainty-aware 2D object detection framework.
We employ evidential learning to estimate both classification and regression uncertainties.
We train our model on the KITTI dataset and evaluate it on challenging out-of-distribution datasets.
arXiv Detail & Related papers (2023-03-06T11:07:11Z) - A New Knowledge Distillation Network for Incremental Few-Shot Surface
Defect Detection [20.712532953953808]
This paper proposes a new knowledge distillation network, called Dual Knowledge Align Network (DKAN)
The proposed DKAN method follows a pretraining-finetuning transfer learning paradigm and a knowledge distillation framework is designed for fine-tuning.
Experiments have been conducted on the incremental Few-shot NEU-DET dataset and results show that DKAN outperforms other methods on various few-shot scenes.
arXiv Detail & Related papers (2022-09-01T15:08:44Z) - Ranking-Based Physics-Informed Line Failure Detection in Power Grids [66.0797334582536]
Real-time and accurate detecting of potential line failures is the first step to mitigating the extreme weather impact and activating emergency controls.
Power balance equations nonlinearity, increased uncertainty in generation during extreme events, and lack of grid observability compromise the efficiency of traditional data-driven failure detection methods.
This paper proposes a Physics-InformEd Line failure Detector (FIELD) that leverages grid topology information to reduce sample and time complexities and improve localization accuracy.
arXiv Detail & Related papers (2022-08-31T18:19:25Z) - Improving robustness of jet tagging algorithms with adversarial training [56.79800815519762]
We investigate the vulnerability of flavor tagging algorithms via application of adversarial attacks.
We present an adversarial training strategy that mitigates the impact of such simulated attacks.
arXiv Detail & Related papers (2022-03-25T19:57:19Z) - A Loss Curvature Perspective on Training Instability in Deep Learning [28.70491071044542]
We study the evolution of the loss Hessian across many classification tasks in order to understand the effect curvature of the loss has on the training dynamics.
Inspired by the conditioning perspective, we show that learning rate warmup can improve training stability just as much as batch normalization.
arXiv Detail & Related papers (2021-10-08T20:25:48Z) - How Robust are Randomized Smoothing based Defenses to Data Poisoning? [66.80663779176979]
We present a previously unrecognized threat to robust machine learning models that highlights the importance of training-data quality.
We propose a novel bilevel optimization-based data poisoning attack that degrades the robustness guarantees of certifiably robust classifiers.
Our attack is effective even when the victim trains the models from scratch using state-of-the-art robust training methods.
arXiv Detail & Related papers (2020-12-02T15:30:21Z) - Robust Pre-Training by Adversarial Contrastive Learning [120.33706897927391]
Recent work has shown that, when integrated with adversarial training, self-supervised pre-training can lead to state-of-the-art robustness.
We improve robustness-aware self-supervised pre-training by learning representations consistent under both data augmentations and adversarial perturbations.
arXiv Detail & Related papers (2020-10-26T04:44:43Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.