Spatial Semantic Regularisation for Large Scale Object Detection

by   Damian Mrowca, et al.

Large scale object detection with thousands of classes introduces the problem of many contradicting false positive detections, which have to be suppressed. Class-independent non-maximum suppression has traditionally been used for this step, but it does not scale well as the number of classes grows. Traditional non-maximum suppression does not consider label- and instance-level relationships nor does it allow an exploitation of the spatial layout of detection proposals. We propose a new multi-class spatial semantic regularisation method based on affinity propagation clustering, which simultaneously optimises across all categories and all proposed locations in the image, to improve both the localisation and categorisation of selected detection proposals. Constraints are shared across the labels through the semantic WordNet hierarchy. Our approach proves to be especially useful in large scale settings with thousands of classes, where spatial and semantic interactions are very frequent and only weakly supervised detectors can be built due to a lack of bounding box annotations. Detection experiments are conducted on the ImageNet and COCO dataset, and in settings with thousands of detected categories. Our method provides a significant precision improvement by reducing false positives, while simultaneously improving the recall.


page 8

page 13

page 14

page 15

page 16

page 18

page 20

page 22


Hierarchical Structure and Joint Training for Large Scale Semi-supervised Object Detection

Generic object detection is one of the most fundamental and important pr...

Transformer-based Multi-Instance Learning for Weakly Supervised Object Detection

Weakly Supervised Object Detection (WSOD) enables the training of object...

Visual and Semantic Knowledge Transfer for Large Scale Semi-supervised Object Detection

Deep CNN-based object detection systems have achieved remarkable success...

Multi-stage Object Detection with Group Recursive Learning

Most of existing detection pipelines treat object proposals independentl...

Learning Detection with Diverse Proposals

To predict a set of diverse and informative proposals with enriched repr...

NOTE-RCNN: NOise Tolerant Ensemble RCNN for Semi-Supervised Object Detection

The labeling cost of large number of bounding boxes is one of the main c...

Rank of Experts: Detection Network Ensemble

The recent advances of convolutional detectors show impressive performan...

Please sign up or login with your details

Forgot password? Click here to reset