On Calibrating Semantic Segmentation Models: Analyses and An Algorithm
We study the problem of semantic segmentation calibration. Lots of solutions have been proposed to approach model miscalibration of confidence in image classification. However, to date, confidence calibration research on semantic segmentation is still limited. We provide a systematic study on the calibration of semantic segmentation models and propose a simple yet effective approach. First, we find that model capacity, crop size, multi-scale testing, and prediction correctness have impact on calibration. Among them, prediction correctness, especially misprediction, is more important to miscalibration due to over-confidence. Next, we propose a simple, unifying, and effective approach, namely selective scaling, by separating correct/incorrect prediction for scaling and more focusing on misprediction logit smoothing. Then, we study popular existing calibration methods and compare them with selective scaling on semantic segmentation calibration. We conduct extensive experiments with a variety of benchmarks on both in-domain and domain-shift calibration and show that selective scaling consistently outperforms other methods.
Code (1)
Tasks
image-classificationImage ClassificationPredictionSegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
Domain Adaptive Medical Image Segmentation via Adversarial Learning of Disease-Specific Spatial Patterns
In medical imaging, the heterogeneity of multi-centre data impedes the applicability of deep learning-based methods and results in significant performance degradation when applying models in an unseen data domain, e.g. a…
Domain AdaptationImage SegmentationLesion SegmentationMedical Image Segmentation+3Attention to Refine through Multi-Scales for Semantic Segmentation
This paper proposes a novel attention model for semantic segmentation, which aggregates multi-scale and context features to refine prediction. Specifically, the skeleton convolutional neural network framework takes in mu…
Semantic SegmentationRecalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks
In a wide range of semantic segmentation tasks, fully convolutional neural networks (F-CNNs) have been successfully leveraged to achieve state-of-the-art performance. Architectural innovations of F-CNNs have mainly been …
image-classificationImage ClassificationSegmentationSemantic SegmentationSFC: Shared Feature Calibration in Weakly Supervised Semantic Segmentation
Image-level weakly supervised semantic segmentation has received increasing attention due to its low annotation cost. Existing methods mainly rely on Class Activation Mapping (CAM) to obtain pseudo-labels for training se…
Pseudo LabelSegmentationSemantic SegmentationWeakly supervised Semantic Segmentation+1Open-Vocabulary Segmentation with Semantic-Assisted Calibration
This paper studies open-vocabulary segmentation (OVS) through calibrating in-vocabulary and domain-biased embedding space with generalized contextual prior of CLIP. As the core of open-vocabulary understanding, alignment…
AttributeOpen Vocabulary Semantic Segmentation