DHARI Report to EPIC-Kitchens 2020 Object Detection Challenge
This work addresses object detection in kitchen environments, but it is incremental as it builds on existing techniques for a specific challenge.
The authors tackled object detection in the EPIC-Kitchens challenge by introducing data augmentation and feature extraction methods, resulting in significant improvements in mean Average Precision (mAP) on both seen and unseen test sets.
In this report, we describe the technical details of oursubmission to the EPIC-Kitchens Object Detection Challenge.Duck filling and mix-up techniques are firstly introduced to augment the data and significantly improve the robustness of the proposed method. Then we propose GRE-FPN and Hard IoU-imbalance Sampler methods to extract more representative global object features. To bridge the gap of category imbalance, Class Balance Sampling is utilized and greatly improves the test results. Besides, some training and testing strategies are also exploited, such as Stochastic Weight Averaging and multi-scale testing. Experimental results demonstrate that our approach can significantly improve the mean Average Precision (mAP) of object detection on both the seen and unseen test sets of EPICKitchens.