Some object detection datasets contain an overwhelming number of easy examples and a small number of hard examples. Automatic selection of these hard examples can make training more effective and efficient. OHEM, or Online Hard Example Mining, is a bootstrapping technique that modifies SGD to sample from examples in a non-uniform way depending on the current loss of each example under consideration. The method takes advantage of detection-specific problem structure in which each SGD mini-batch consists of only one or two images, but thousands of candidate examples. The candidate examples are subsampled according to a distribution that favors diverse, high loss instances.
Source: Training Region-based Object Detectors with Online Hard Example MiningPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Object Detection | 6 | 54.55% |
Instance Segmentation | 1 | 9.09% |
Interactive Segmentation | 1 | 9.09% |
Semantic Segmentation | 1 | 9.09% |
Video Object Segmentation | 1 | 9.09% |
Multi-Task Learning | 1 | 9.09% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |