Large-Scale Object Detection in the Wild from Imbalanced Multi-Labels
This work addresses challenges in large-scale object detection for general and sophisticated scenarios, offering an incremental improvement over existing methods.
The paper tackles label-related problems in the Open Images dataset, such as multi-label issues and extreme label imbalance, by proposing a concurrent softmax and soft-sampling method with hybrid training scheduler, resulting in a 3.34-point improvement to 60.90 mAP for a single model and 67.17 mAP for ensembling.
Training with more data has always been the most stable and effective way of improving performance in deep learning era. As the largest object detection dataset so far, Open Images brings great opportunities and challenges for object detection in general and sophisticated scenarios. However, owing to its semi-automatic collecting and labeling pipeline to deal with the huge data scale, Open Images dataset suffers from label-related problems that objects may explicitly or implicitly have multiple labels and the label distribution is extremely imbalanced. In this work, we quantitatively analyze these label problems and provide a simple but effective solution. We design a concurrent softmax to handle the multi-label problems in object detection and propose a soft-sampling methods with hybrid training scheduler to deal with the label imbalance. Overall, our method yields a dramatic improvement of 3.34 points, leading to the best single model with 60.90 mAP on the public object detection test set of Open Images. And our ensembling result achieves 67.17 mAP, which is 4.29 points higher than the best result of Open Images public test 2018.