Reducing false positives for object detection

Cheng, Bowen

Permalink

https://hdl.handle.net/2142/106175 Copy

Description

Title

Reducing false positives for object detection

Author(s)

Cheng, Bowen

Issue Date

2019-10-16

Director of Research (if dissertation) or Advisor (if thesis)

Huang, Thomas S.

Department of Study

Electrical & Computer Eng

Discipline

Electrical & Computer Engr

Degree Granting Institution

University of Illinois at Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

• Object Detection
• Deep Learning

Abstract

In this thesis, we analyze failure cases of state-of-the-art detectors and observe that most hard false positives result from classification instead of localization and they have a large negative impact on the performance of object detectors. We conjecture three factors that lie behind hard false positives, and we confirm the conjecture with experiments that prove the following: (1) Shared feature representation is not optimal due to the mismatched goals of feature learning for classification and localization; (2) large receptive field for different scales leads to redundant context information for small objects; (3) multi-task learning helps, yet optimization of the multi-task loss may prove sub-optimal for individual tasks. We demonstrate the potential power of detector classification by a simple, effective, and widely applicable Decoupled Classification Refinement (DCR) network. In particular, DCR places a separate classification network in parallel with the localization network (base detector). With ROI pooling placed on the early stage of the classification network, we enforce an adaptive receptive field in DCR. During training, DCR samples hard false positives from the base detector and trains a strong classifier to refine classification results. During testing, DCR refines all boxes from the base detector. Experiments show competitive results on PASCAL VOC and COCO without any bells and whistles. Our codes are available at: https://github.com/bowenc0221/Decoupled-Classification-Refinement.

Graduation Semester

2019-12

Type of Resource

text

Permalink

http://hdl.handle.net/2142/106175

Copyright and License Information

Copyright 2019 Bowen Cheng

Owning Collections