Conformal Prediction Sets for Instance Segmentation
Current instance segmentation models achieve high performance on average predictions, but lack principled uncertainty quantification: their outputs are not calibrated, and there is no guarantee that a predicted mask is close to the ground truth. To address this limitation, we introduce a conformal prediction algorithm to generate adaptive confidence sets for instance segmentation. Given an image and a pixel coordinate query, our algorithm generates a confidence set of instance predictions for that pixel, with a provable guarantee for the probability that at least one of the predictions has high Intersection-Over-Union (IoU) with the true object instance mask. We apply our algorithm to instance segmentation examples in agricultural field delineation, cell segmentation, and vehicle detection. Empirically, we find that our prediction sets vary in size based on query difficulty and attain the target coverage, outperforming baselines (naive best parameter and morphological dilation-based methods). We provide versions of the algorithm with asymptotic and finite sample guarantees. Our work is the first to capture structural uncertainty in instance segmentation by constructing confidence sets of diverse segmentation predictions.
Code (0)
등록된 구현이 없습니다.
Tasks
Instance SegmentationCell SegmentationSimilar Papers 제목 키워드 기반
Performance of Conformal Prediction in Capturing Aleatoric Uncertainty
Conformal prediction is a model-agnostic approach to generating prediction sets that cover the true class with a high probability. Although its prediction set size is expected to capture aleatoric uncertainty, there is a…
Instance Segmentation GNNs for One-Shot Conformal Tracking at the LHC
3D instance segmentation remains a challenging problem in computer vision. Particle tracking at colliders like the LHC can be conceptualized as an instance segmentation task: beginning from a point cloud of hits in a par…
3D Instance SegmentationInstance SegmentationSegmentationSemantic SegmentationReliable Prediction Errors for Deep Neural Networks Using Test-Time Dropout
While the use of deep learning in drug discovery is gaining increasing attention, the lack of methods to compute reliable errors in prediction for Neural Networks prevents their application to guide decision making in do…
Conformal PredictionDecision MakingDrug DiscoveryPrediction+1Anatomically-aware conformal prediction for medical image segmentation with random walks
The reliable deployment of deep learning in medical imaging requires uncertainty quantification that provides rigorous error guarantees while remaining anatomically meaningful. Conformal prediction (CP) is a powerful dis…
Medical Image SegmentationConformal Set-based Human-AI Complementarity with Multiple Experts
Decision support systems are designed to assist human experts in classification tasks by providing conformal prediction sets derived from a pre-trained model. This human-AI collaboration has demonstrated enhanced classif…