Enriched Feature Guided Refinement Network for Object Detection

By Jing Nie, Rao Muhammad Anwer, Hisham Cholakkal, Fahad Shahbaz Khan, Yanwei Pang, Ling Shao. 2019

81 citations recorded by the source corpus.

We propose a single-stage detection framework that jointly tackles the problem of multi-scale object detection and class imbalance. Rather than designing deeper networks, we introduce a simple yet effective feature enrichment scheme to produce multi-scale contextual features. We further introduce a cascaded refinement scheme which first instills multi-scale contextual features into the prediction layers of the single-stage detector in order to enrich their discriminative power for multi-scale detection. Second, the cascaded refinement scheme counters the class imbalance problem by refining the anchors and enriched features to improve classification and regression. Experiments are performed on two benchmarks: PASCAL VOC and MS COCO. For a 320×320 input on the MS COCO test-dev, our detector achieves state-of-the-art single-stage detection accuracy with a COCO AP of 33.2 in the case of single-scale inference, while operating at 21 milliseconds on a Titan XP GPU. For a 512×512 input on the MS COCO test-dev, our approach obtains an absolute gain of 1.6% in terms of COCO AP, compared to the best reported single-stage results[5]. Source code and models are available at: https://github.com/Ranchentx/EFGRNet.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Bridging the Gap Between Anchor-Based and Anchor-Free Detection via Adaptive Training Sample Selection (2019, background): “Thereafter, plenty of works are presented to boost its performance in different aspects, such as fusing context information from different layers [24, 12, 69], training from scratch [50, 73], introducing new loss function [33, 6], anchor refinement and matching [66, 67], architecture redesign [21, 2”
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.”
YOLOv4: Optimal Speed and Accuracy of Object Detection (2020, background): “Enriched Feature Guided Refinement Network for Object Detection [57] EFGRNet VGG-16 320 47.”
OW-DETR: Open-world Detection Transformer (2021, background): “Several works have investigated the problem of standard object detection [2, 11, 13, 19, 25, 26, 29, 31].”
D2Det: Towards High Quality Object Detection and Instance Segmentation (2020, unknown): “3 EFGRNet [38] ResNet101 512× 512 39.”
Effective Fusion Factor in FPN for Tiny Object Detection (2020, methodology): “Nie [21] introduces a feature enrichment scheme to generate multi-scale contextual features, HRNet [27] performs multi-scale fusion through repeated cross parallel convolution to enhance feature expression, and Libra-RCNN [23] uses the fusion results of all feature layers to reduce the unbalance bet”
CSPNet: A New Backbone that can Enhance Learning Capability of CNN (2019, unknown): “8 EFGRNet [24] VGG16 [31] 320×320 48 33.”