A Tri-Layer Plugin to Improve Occluded Detection

10/18/2022
by   Guanqi Zhan, et al.
3

Detecting occluded objects still remains a challenge for state-of-the-art object detectors. The objective of this work is to improve the detection for such objects, and thereby improve the overall performance of a modern object detector. To this end we make the following four contributions: (1) We propose a simple 'plugin' module for the detection head of two-stage object detectors to improve the recall of partially occluded objects. The module predicts a tri-layer of segmentation masks for the target object, the occluder and the occludee, and by doing so is able to better predict the mask of the target object. (2) We propose a scalable pipeline for generating training data for the module by using amodal completion of existing object detection and instance segmentation training datasets to establish occlusion relationships. (3) We also establish a COCO evaluation dataset to measure the recall performance of partially occluded and separated objects. (4) We show that the plugin module inserted into a two-stage detector can boost the performance significantly, by only fine-tuning the detection head, and with additional improvements if the entire architecture is fine-tuned. COCO results are reported for Mask R-CNN with Swin-T or Swin-S backbones, and Cascade Mask R-CNN with a Swin-B backbone.

READ FULL TEXT

page 6

page 7

page 10

page 16

page 17

page 18

page 19

page 22

research
09/09/2019

CBNet: A Novel Composite Backbone Network Architecture for Object Detection

In existing CNN based detectors, the backbone network is a very importan...
research
03/16/2020

PS-RCNN: Detecting Secondary Human Instances in a Crowd via Primary Object Suppression

Detecting human bodies in highly crowded scenes is a challenging problem...
research
11/28/2022

Object Permanence in Object Detection Leveraging Temporal Priors at Inference Time

Object permanence is the concept that objects do not suddenly disappear ...
research
08/06/2023

Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects

Camouflaged object detection (COD) is the challenging task of identifyin...
research
04/27/2020

The Problem of Fragmented Occlusion in Object Detection

Object detection in natural environments is still a very challenging tas...
research
09/01/2016

Grid Loss: Detecting Occluded Faces

Detection of partially occluded objects is a challenging computer vision...
research
03/01/2020

MonoPair: Monocular 3D Object Detection Using Pairwise Spatial Relationships

Monocular 3D object detection is an essential component in autonomous dr...

Please sign up or login with your details

Forgot password? Click here to reset