Efficacy of Pixel-Level OOD Detection for Semantic Segmentation
The detection of out of distribution samples for image classification has been widely researched. Safety critical applications, such as autonomous driving, would benefit from the ability to localise the unusual objects causing the image to be out of distribution. This paper adapts state-of-the-art methods for detecting out of distribution images for image classification to the new task of detecting out of distribution pixels, which can localise the unusual objects. It further experimentally compares the adapted methods on two new datasets derived from existing semantic segmentation datasets using PSPNet and DeeplabV3+ architectures, as well as proposing a new metric for the task. The evaluation shows that the performance ranking of the compared methods does not transfer to the new task and every method performs significantly worse than their image-level counterparts.
Code (0)
등록된 구현이 없습니다.
Tasks
Autonomous DrivingGeneral Classificationimage-classificationImage ClassificationOut of Distribution (OOD) DetectionSemantic SegmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentation
Recent advancements in dense out-of-distribution (OOD) detection have primarily focused on scenarios where the training and testing datasets share a similar domain, with the assumption that no domain shift exists between…
DASNet: Reducing Pixel-level Annotations for Instance and Semantic Segmentation
Pixel-level annotation demands expensive human efforts and limits the performance of deep networks that usually benefits from more such training data. In this work we aim to achieve high quality instance and semantic seg…
SegmentationSemantic SegmentationSEA: Bridging the Gap Between One- and Two-stage Detector Distillation via SEmantic-aware Alignment
We revisit the one- and two-stage detector distillation tasks and present a simple and efficient semantic-aware framework to fill the gap between them. We address the pixel-level imbalance problem by designing the catego…
Instance Segmentationobject-detectionObject DetectionSemantic SegmentationBottom-up Instance Segmentation using Deep Higher-Order CRFs
Traditional Scene Understanding problems such as Object Detection and Semantic Segmentation have made breakthroughs in recent years due to the adoption of deep learning. However, the former task is not able to localise o…
Instance SegmentationObjectobject-detectionObject Detection+3SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation
Open-vocabulary semantic segmentation strives to distinguish pixels into different semantic groups from an open set of categories. Most existing methods explore utilizing pre-trained vision-language models, in which the …
DecoderOpen Vocabulary Semantic SegmentationOpen-Vocabulary Semantic SegmentationSegmentation+1