DHARI Report to EPIC-Kitchens 2020 Object Detection Challenge
Kaide Li, Bingyan Liao, Laifeng Hu, Yaonong Wang

TL;DR
This report details a robust object detection method for EPIC-Kitchens, utilizing advanced data augmentation, feature extraction, and sampling techniques to improve mean Average Precision on challenging datasets.
Contribution
It introduces novel data augmentation and sampling strategies, along with improved feature extraction methods, to enhance object detection performance in egocentric kitchen environments.
Findings
Significant mAP improvement on EPIC-Kitchens datasets
Effective data augmentation with duck filling and mix-up techniques
Enhanced feature extraction with GRE-FPN and Hard IoU-imbalance Sampler
Abstract
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.
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 · COVID-19 diagnosis using AI · Advanced Image and Video Retrieval Techniques
MethodsStochastic Weight Averaging
