MASON: A Model AgnoStic ObjectNess Framework
This paper proposes a simple, yet very effective method to localize dominant foreground objects in an image, to pixel-level precision. The proposed method 'MASON' (Model-AgnoStic ObjectNess) uses a deep convolutional network to generate category-independent and model-agnostic heat maps for any image. The network is not explicitly trained for the task, and hence, can be used off-the-shelf in tandem with any other network or task. We show that this framework scales to a wide variety of images, and illustrate the effectiveness of MASON in three varied application contexts.
Code (1)
Tasks
modelSimilar Papers 제목 키워드 기반
3D vision-based structural masonry damage detection
The detection of masonry damage is essential for preventing potentially disastrous outcomes. Manual inspection can, however, take a long time and be hazardous to human inspectors. Automation of the inspection process usi…
Multimodal-Enhanced Objectness Learner for Corner Case Detection in Autonomous Driving
Previous works on object detection have achieved high accuracy in closed-set scenarios, but their performance in open-world scenarios is not satisfactory. One of the challenging open-world problems is corner case detecti…
Autonomous DrivingMultimodal Deep LearningObject DetectionSimpler Does It: Generating Semantic Labels with Objectness Guidance
Existing weakly or semi-supervised semantic segmentation methods utilize image or box-level supervision to generate pseudo-labels for weakly labeled images. However, due to the lack of strong supervision, the generated p…
Multi-Task LearningObjectSemantic SegmentationSemi-Supervised Semantic SegmentationContinual Segmentation with Disentangled Objectness Learning and Class Recognition
Most continual segmentation methods tackle the problem as a per-pixel classification task. However, such a paradigm is very challenging, and we find query-based segmenters with built-in objectness have inherent advantage…
Continual LearningSegmentationTowards 3D Objectness Learning in an Open World
Recent advancements in 3D object detection and novel category detection have made significant progress, yet research on learning generalized 3D objectness remains insufficient. In this paper, we delve into learning open-…
3D Object Detection