D2Det: Towards High Quality Object Detection and Instance Segmentation

By Jiale Cao, Hisham Cholakkal, Rao Muhammad Anwer, Fahad Shahbaz Khan, Yanwei Pang, Ling Shao. 2020

278 citations recorded by the source corpus.

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.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Incremental Object Detection via Meta-Learning (2020, neutral): “Extending our methodology to single stage detectors [57], [58], [59] and incremental versions of related problem settings such as action recognition [60], object counting [61] and instance segmentation [62] are interesting and important research directions.”
DetectoRS: Detecting Objects with Recursive Feature Pyramid and Switchable Atrous Convolution (2020, unknown): “, [5,7,8,10,26,27, 29,34,62,75].”
Scaled-YOLOv4: Scaling Cross Stage Partial Network (2020, methodology): “Through analysis of state-of-the-art object detectors [1, 3, 6, 26, 35, 40, 44], we found that CSPDarknet53, which is the backbone of YOLOv4 [1], matches almost all optimal architecture features obtained by network architecture search technique [27].”
A review of convolutional neural networks in computer vision (2024, unknown): “Cao suggested a novel two-stage detector, D2Det (Cao et al. 2020), in 2020, that can handle the difficulties of precise localization and accurate classification at the same time.”
Forest R-CNN: Large-Vocabulary Long-Tailed Object Detection and Instance Segmentation (2020, background): “ries, respectively. 2 RELATED WORK ObjectDetectionandInstanceSegmentation.Objectdetection, which plays an important role in various vision applications, has been actively investigated in past decades [4, 6, 7, 23, 32, 34, 40, 41]. With deep learning, two mainstream frameworks, i.e., single-stage det”
SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation (2020, methodology): “Here, we compare our method with some two-stage [14,27,18,9,21,31,23,8,4] and single-stage [54,2,46,11] methods on COCO test-dev set.”