Trimps speed hack6/12/2023 ![]() ![]() Search, add ROIPooling after inception_5, input size 786(max 1280), Googlenet, fast-rcnn, pretrained on the 1000 classes, selective Validation mAP is 54.6Ĭombined multiple models with the region proposals of cascaded RPN, 57.3% mAP on Val2.Ģ models on 2 proposals without category information: Ī combination of 6 models with selective regressionĬategory aggregation + Co-occurrence refinement with single model on single proposal: +(SS)Ī combination of 6 models without regressionĬategory aggregation + Co-occurrence refinement with single model on single proposal: +(RPN)Ī simple strategy to merge the three results, 38.7% MAP on validation NeoNet ensemble with bounding box regression. Italics = authors requested entry not participate in competition Object detection (DET) Task 1a: Object detection with provided training data Ordered by number of categories won Grey background = authors chose not to reveal the method White background = authors are willing to reveal the method ![]() Yellow background = winner in this task according to this metric authors are willing to reveal the method Large Scale Visual Recognition Challenge 2015 (ILSVRC2015)
0 Comments
Leave a Reply. |