Detection Selection Algorithm: A Likelihood based Optimization Method to Perform Post Processing for Object Detection
Angzhi Fan, Benjamin Ticknor, Yali Amit

TL;DR
This paper introduces the Detection Selection Algorithm (DSA), a likelihood-based post-processing method that improves object detection accuracy by selecting the most probable set of detections considering occlusions and object reconstructions.
Contribution
The paper presents a novel post-processing algorithm that integrates occlusion reasoning and object reconstruction to enhance detection results beyond traditional NMS methods.
Findings
DSA outperforms NMS and Soft-NMS in experiments.
Incorporates occlusion relationships into detection refinement.
Achieves higher likelihood interpretations of object arrangements.
Abstract
In object detection, post-processing methods like Non-maximum Suppression (NMS) are widely used. NMS can substantially reduce the number of false positive detections but may still keep some detections with low objectness scores. In order to find the exact number of objects and their labels in the image, we propose a post processing method called Detection Selection Algorithm (DSA) which is used after NMS or related methods. DSA greedily selects a subset of detected bounding boxes, together with full object reconstructions that give the interpretation of the whole image with highest likelihood, taking into account object occlusions. The algorithm consists of four components. First, we add an occlusion branch to Faster R-CNN to obtain occlusion relationships between objects. Second, we develop a single reconstruction algorithm which can reconstruct the whole appearance of an object given…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Neural Network Applications · Advanced Image and Video Retrieval Techniques · Industrial Vision Systems and Defect Detection
MethodsConvolution · Softmax · RoIPool · Region Proposal Network · Faster R-CNN · Soft-NMS
