Efficient Featurized Image Pyramid Network for Single Shot Detector

By Yanwei Pang, Tiancai Wang, Rao Muhammad Anwer, Fahad Shahbaz Khan, Ling Shao. 2019

106 citations recorded by the source corpus.

Single-stage object detectors have recently gained popularity due to their combined advantage of high detection accuracy and real-time speed. However, while promising results have been achieved by these detectors on standard-sized objects, their performance on small objects is far from satisfactory. To detect very small/large objects, classical pyramid representation can be exploited, where an image pyramid is used to build a feature pyramid (featurized image pyramid), enabling detection across a range of scales. Existing single-stage detectors avoid such a featurized image pyramid representation due to its memory and time complexity. In this paper, we introduce a light-weight architecture to efficiently produce featurized image pyramid in a single-stage detection framework. The resulting multi-scale features are then injected into the prediction layers of the detector using an attention module. The performance of our detector is validated on two benchmarks: PASCAL VOC and MS COCO. For a 300$\times$300 input, our detector operates at 111 frames per second (FPS) on a Titan X GPU, providing state-of-the-art detection accuracy on PASCAL VOC 2007 testset. On the MS COCO testset, our detector achieves state-of-the-art results surpassing all existing single-stage methods in the case of single-scale inference.

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

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.”
Rethinking Coarse-to-Fine Approach in Single Image Deblurring (2021, methodology): “The use of multi-scale images as an input for a single U-Net has also proven to be effective in other tasks such as depth map super-resolution [6] and object detection [21].”
D2Det: Towards High Quality Object Detection and Instance Segmentation (2020, unknown): “into single-stage [35, 42, 40, 29, 27, 4] and two-stage methods [18, 43, 17, 41, 8, 21].”
Learning Rich Features at High-Speed for Single-Shot Object Detection (2019, background): “Most common solutions to this problem include e.g ., large-scale context [10], better feature extraction by deepening the model [10, 18], featurized image pyramids [24] and top-down feature pyramid representation to inject high-level semantics to former layers [18, 35, 37].”
Triply Supervised Decoder Networks for Joint Detection and Segmentation (2018, unknown): “After that, many variants were proposed [10, 23, 44, 55, 37].”
Enriched Feature Guided Refinement Network for Object Detection (2019, methodology): “Among existing single-stage methods, RFBNet [26] and EFIPNet [30] provide overall detection accuracies of 30.”
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].”