Object Detection Based on Region Decomposition and Assembly

Authors: Seung-Hwan Bae8094-8101

AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We integrate the R-DAD into several feature extractors, and prove the distinct performance improvement on PASCAL07/12 and MSCOCO18 compared to the recent convolutional detectors.
Researcher Affiliation Academia Seung-Hwan Bae Computer Vision Lab., Department of Computer Science and Engineering Incheon National University, 119 Academy-ro, Yeonsu-gu, Incheon, 22012, Korea shbae@inu.ac.kr
Pseudocode No The paper describes the method using equations and text, but does not provide a formal pseudocode or algorithm block.
Open Source Code No The paper does not provide any explicit statements about open-sourcing code or links to a code repository.
Open Datasets Yes We train and evaluate our R-DAD on standard detection benchmark datasets: PASCAL VOC07/12 (Everingham et al. 2015) and MSCOCO18 (Lin et al. 2014) datasets.
Dataset Splits Yes We train both detectors with the VOC07trainval (VOC07, 5011 images) and VOC12trainval sets (VOC07++12, 11540 images).
Hardware Specification Yes We implement all the detectors using the Caffe on a PC with a single TITAN Xp GPU without parallel and distributed training.
Software Dependencies No The paper mentions using 'Caffe' but does not provide specific version numbers for Caffe or any other software dependencies.
Experiment Setup Yes We use a learning rate µ = 1e 3 for 50k iterations, and µ = 1e 4 for the next 20k iterations on VOC07 evaluation. For VOC12 evaluation, we train a detector with µ = 1e 3 for 70k iterations, and continue it for 50k iterations with µ = 1e 4. For MSCOCO evaluation, we use µ = 1e 4 and µ = 1e 5 for the first 700k and the next 500k iterations.