paper-with-me

Papers

On Calibrating Semantic Segmentation Models: Analyses and An Algorithm

2022-12-22 · CVPR 2023 1 · Dongdong Wang, Boqing Gong, Liqiang Wang

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.

📄 PDF Abstract BibTeX arXiv:2212.12053

Code (1)

dwang181/selectivecal 공식 구현 pytorch

Tasks

image-classificationImage ClassificationPredictionSegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Domain Adaptive Medical Image Segmentation via Adversarial Learning of Disease-Specific Spatial Patterns

2020-01-25 · Hongwei Li, Timo Loehr, Anjany Sekuboyina, Jian-Guo Zhang 외

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+3

Attention to Refine through Multi-Scales for Semantic Segmentation

2018-07-09 · Shiqi Yang, Gang Peng

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 Segmentation

Recalibrating Fully Convolutional Networks with Spatial and Channel 'Squeeze & Excitation' Blocks

2018-08-23 · Abhijit Guha Roy, Nassir Navab, Christian Wachinger

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 Segmentation

SFC: Shared Feature Calibration in Weakly Supervised Semantic Segmentation

2024-01-22 · Xinqiao Zhao, Feilong Tang, Xiaoyang Wang, Jimin Xiao

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+1

Open-Vocabulary Segmentation with Semantic-Assisted Calibration

2023-12-07 · CVPR 2024 1 · Yong liu, Sule Bai, Guanbin Li, Yitong Wang 외

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