Optimal Decisions from Probabilistic Models: The Intersection-over-Union Case
A probabilistic model allows us to reason about the world and make statistically optimal decisions using Bayesian decision theory. However, in practice the intractability of the decision problem forces us to adopt simplistic loss functions such as the 0/1 loss or Hamming loss and as result we make poor decisions through MAP estimates or through low-order marginal statistics. In this work we investigate optimal decision making for more realistic loss functions. Specifically we consider the popular intersection-over-union (IoU) score used in image segmentation benchmarks and show that it results in a hard combinatorial decision problem. To make this problem tractable we propose a statistical approximation to the objective function, as well as an approximate algorithm based on parametric linear programming. We apply the algorithm on three benchmark datasets and obtain improved intersection-over-union scores compared to maximum-posterior-marginal decisions. Our work points out the difficulties of using realistic loss functions with probabilistic computer vision models.
Code (0)
등록된 구현이 없습니다.
Tasks
Decision MakingImage SegmentationSemantic SegmentationSimilar Papers 제목 키워드 기반
Gaussian Bounding Boxes and Probabilistic Intersection-over-Union for Object Detection
Most object detection methods use bounding boxes to encode and represent the object shape and location. In this work, we explore a fuzzy representation of object regions using Gaussian distributions, which provides an im…
Objectobject-detectionObject DetectionUnion-over-Intersections: Object Detection beyond Winner-Takes-All
This paper revisits the problem of predicting box locations in object detection architectures. Typically, each box proposal or box query aims to directly maximize the intersection-over-union score with the ground truth, …
AllInstance SegmentationObjectobject-detection+4Probabilistic Entity Representation Model for Reasoning over Knowledge Graphs
Logical reasoning over Knowledge Graphs (KGs) is a fundamental technique that can provide efficient querying mechanism over large and incomplete databases. Current approaches employ spatial geometries such as boxes to le…
Knowledge Graph EmbeddingKnowledge GraphsLogical ReasoningThe Lovász-Softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks
The Jaccard index, also referred to as the intersection-over-union score, is commonly employed in the evaluation of image segmentation results given its perceptual qualities, scale invariance - which lends appropriate re…
Image SegmentationSegmentationSemantic SegmentationThe Lovász-Softmax Loss: A Tractable Surrogate for the Optimization of the Intersection-Over-Union Measure in Neural Networks
The Jaccard index, also referred to as the intersection-over-union score, is commonly employed in the evaluation of image segmentation results given its perceptual qualities, scale invariance - which lends appropriate re…
Image SegmentationSegmentationSemantic Segmentation