G-CNN: An Iterative Grid Based Object Detector

By Mahyar Najibi, Mohammad Rastegari, Larry S. Davis. 2015

199 citations recorded by the source corpus.

We introduce G-CNN, an object detection technique based on CNNs which works without proposal algorithms. G-CNN starts with a multi-scale grid of fixed bounding boxes. We train a regressor to move and scale elements of the grid towards objects iteratively. G-CNN models the problem of object detection as finding a path from a fixed grid to boxes tightly surrounding the objects. G-CNN with around 180 boxes in a multi-scale grid performs comparably to Fast R-CNN which uses around 2K bounding boxes generated with a proposal technique. This strategy makes detection faster by removing the object proposal stage as well as reducing the number of boxes to be processed.

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

Cascade R-CNN: High Quality Object Detection and Instance Segmentation (2019, methodology): “[42], [61] proposed an alternative procedure to localize objects sequentially.”
Cascade R-CNN: Delving Into High Quality Object Detection (2017, neutral): “[37, 27] also attempted to localize objects sequentially.”
Acquisition of Localization Confidence for Accurate Object Detection (2018, background): “G-CNN is proposed in [18] which starts with a multi-scale regular grid over the image and iteratively pushes the boxes in the grid towards the ground-truth.”
Single-Shot Refinement Neural Network for Object Detection (2017, methodology): “After that, numerous effective techniques are proposed to further improve the performance, such as architecture diagram [5, 25, 55], training strategy [31, 41, 48, 50], contextual reasoning [1, 14, 40, 51] and multiple layers exploiting [3, 24, 26, 42].”
Attend Refine Repeat: Active Box Proposal Generation via In-Out Localization (2016, neutral): “Note that active localization schemes have also been previously applied in the object detection literature [4, 13, 14, 17, 30, 39, 42].”
Region Proposal by Guided Anchoring (2019, background): “There have been attempts [8, 9, 23, 31, 33, 34, 1, 2] that apply cascade architecture to reject easy samples at early layers or stages, and regress bounding boxes iteratively for progressive refinement.”
Integrated perception with recurrent multi-task neural networks (2016, methodology): “While these methods [4, 19] are also based on an iterative solution correcting mechanism, our main goal is to improve generalization performance for multiple tasks by sharing the previous predictions across them and learning output correlations.”
Seesaw Loss for Long-Tailed Instance Segmentation (2020, background): “There are also attempts to apply cascade architecture [1, 10, 22, 35, 49] to reﬁne the bounding boxes’ predictions progressively.”
Object Detection With Deep Learning: A Review (2018, background): “finding a path from a fixed grid to boxes tightly surrounding the objects [70].”
SSH: Single Stage Headless Face Detector (2017, methodology): “To solve the localization sub-problem, as in [28, 24, 19], SSH regresses a set of predefined bounding boxes called anchors, to the ground-truth faces.”
Advanced Deep-Learning Techniques for Salient and Category-Specific Object Detection: A Survey (2018, methodology): “Based on such capability, a large amount of the modern object detection approaches [2], [19], [34], [36], [42], [58], [59], [62] can benefit from a simple but effective pretraining phase.”
Object Detection in 20 Years: A Survey (2019, methodology): “provides a new way of performing detection. One recent method is to think of detection as a path planning process that starts from initial grids and ﬁnally converges to the desired ground truth boxes [256]. Another method is to think of detection as an iterative updating process to reﬁne the corners”
PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation (2018, background): “G-CNN [18] designs ﬁlter so that the ﬁlter set is closed under certain rotations ( e.g ., 90-degree rotation) to achieve rotation invariance for those ﬁxed rotations.”
Sparse R-CNN: End-to-End Object Detection with Learnable Proposals (2020, background): “G-CNN [27] can be viewed as a precursor to this group of algorithms.”
Webly Supervised Semantic Segmentation (2017, methodology): “Adopting these SNNs, many fully supervised computer vision methods, such as semantic segmentation [1, 2, 3, 6] and object detection [42], can be easily transformed into a weakly supervised framework, which is in line with our future plan.”
State of the Art in Defect Detection Based on Machine Vision (2021, methodology): “The regression-and classification-based methods mainly include MultiBox [201], AttentionNet [202], G-CNN [203], You Only Look Once (YOLO) [204], the single-shot MultiBox detector (SSD) [205], YOLOv2 [206], RetinaNet [207], YOLOv3 [208], and YOLOv4 [209].”