Working with scale: 2nd place solution to Product Detection in Densely Packed Scenes [Technical Report]
This work addresses product detection for retail applications but is incremental, focusing on reproducibility and verification of existing methods.
The paper tackles product detection in densely packed scenes by verifying previous findings through re-experimenting with object detection models, achieving 2nd place in a CVPR 2020 challenge, with results based on Faster-RCNN and RetinaNet models and simple tricks like anchor scale adjustment and image tiling.
This report describes a 2nd place solution of the detection challenge which is held within CVPR 2020 Retail-Vision workshop. Instead of going further considering previous results this work mainly aims to verify previously observed takeaways by re-experimenting. The reliability and reproducibility of the results are reached by incorporating a popular object detection toolbox - MMDetection. In this report, I firstly represent the results received for Faster-RCNN and RetinaNet models, which were taken for comparison in the original work. Then I describe the experiment results with more advanced models. The final section reviews two simple tricks for Faster-RCNN model that were used for my final submission: changing default anchor scale parameter and train-time image tiling. The source code is available at https://github.com/tyomj/product_detection.