D2Det: Towards High Quality Object Detection and Instance Segmentation

We propose a novel two-stage detection method, D2Det, that collectively addresses both precise localization and accurate classification. For precise localization, we introduce a dense local regression that predicts multiple dense box offsets for an object proposal. Different from traditional regression and keypoint-based localization employed in two-stage detectors, our dense local regression is not limited to a quantized set of keypoints within a fixed region and has the ability to regress position-sensitive real number dense offsets, leading to more precise localization. The dense local regression is further improved by a binary overlap prediction strategy that reduces the influence of background region on the final box regression. For accurate classification, we introduce a discriminative RoI pooling scheme that samples from various sub-regions of a proposal and performs adaptive weighting to obtain discriminative features. On MS COCO test-dev, our D2Det outperforms existing two-stage methods, with a single-model performance of 45.4 AP, using ResNet101 backbone. When using multi-scale training and inference, D2Det obtains AP of 50.1. In addition to detection, we adapt D2Det for instance segmentation, achieving a mask AP of 40.2 with a two-fold speedup, compared to the state-of-the-art. We also demonstrate the effectiveness of our D2Det on airborne sensors by performing experiments for object detection in UAV images (UAVDT dataset) and instance segmentation in satellite images (iSAID dataset). Source code is available at https://github.com/JialeCao001/D2Det.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Object Detection COCO test-dev D2Det (ResNet-101-DCN, multi-scale test) box AP 50.1 # 61
AP50 69.4 # 43
AP75 54.9 # 40
APS 32.7 # 34
APM 52.7 # 44
APL 62.1 # 43
Hardware Burden None # 1
Operations per network pass None # 1
Instance Segmentation COCO test-dev D2Det (ResNet-101, single-scale test) mask AP 40.2 # 37
AP50 61.5 # 17
AP75 43.7 # 12
APS 21.7 # 16
APM 43.0 # 13
APL 54.0 # 16


No methods listed for this paper. Add relevant methods here