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 existing baselines such as Learn Then Test, Conformal Risk Control, and morphological dilation-based methods. We provide versions of the algorithm with asymptotic and finite sample guarantees.

We identify mechanisms through which normalizing flows can simultaneously increase likelihood for all structured images.

LICD has 577 features and labels. The dataset provides several ML research opportunities; we discuss two demonstration experiments.

Unfortunately,optimizing anetworkusingthe desired evaluation metric, such asF1-Score, istypically not feasible.

Most existing point cloud detection models require large-scale, densely annotated datasets. They typically underperform in domain adaptation settings, due to geometry shifts caused by different physical environments or LiDAR sensor configurations. Therefore, itischallenging butvaluable tolearn transferable features between a labeled source domain and a novel target domain, without any access to target labels. To tackle this problem, we introduce the framework of 3DContrastiveCo-training (3D-CoCo) with two technical contributions. First, 3D-CoCo is inspired by our observation that the bird-eye-view (BEV) features are more transferable than low-levelgeometry features.