ALFA: Agglomerative Late Fusion Algorithm for Object Detection
This work addresses the challenge of enhancing object detection performance for computer vision applications by effectively fusing outputs from multiple detectors, representing an incremental improvement over existing fusion methods.
The paper tackles the problem of improving object detection accuracy by proposing ALFA, a novel late fusion algorithm that combines predictions from multiple detectors using agglomerative clustering, achieving state-of-the-art results on PASCAL VOC datasets with up to 32% lower error than the best individual detectors.
We propose ALFA - a novel late fusion algorithm for object detection. ALFA is based on agglomerative clustering of object detector predictions taking into consideration both the bounding box locations and the class scores. Each cluster represents a single object hypothesis whose location is a weighted combination of the clustered bounding boxes. ALFA was evaluated using combinations of a pair (SSD and DeNet) and a triplet (SSD, DeNet and Faster R-CNN) of recent object detectors that are close to the state-of-the-art. ALFA achieves state of the art results on PASCAL VOC 2007 and PASCAL VOC 2012, outperforming the individual detectors as well as baseline combination strategies, achieving up to 32% lower error than the best individual detectors and up to 6% lower error than the reference fusion algorithm DBF - Dynamic Belief Fusion.