Corpus ID: 232478650

Anchor Pruning for Object Detection

@article{Bonnaerens2021AnchorPF,
  title={Anchor Pruning for Object Detection},
  author={Maxim Bonnaerens and Matthias Freiberger and Joni Dambre},
  journal={ArXiv},
  year={2021},
  volume={abs/2104.00432}
}
This paper proposes anchor pruning for object detection in one-stage anchor-based detectors. While pruning techniques are widely used to reduce the computational cost of convolutional neural networks, they tend to focus on optimizing the backbone networks where often most computations are. In this work we demonstrate an additional pruning technique, specifically for object detection: anchor pruning. With more efficient backbone networks and a growing trend of deploying object detectors on… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 39 REFERENCES
Anchor Box Optimization for Object Detection
TLDR
This paper proposes to dynamically learn the anchor shapes, which allows the anchors to automatically adapt to the data distribution and the network learning capability, and achieves significant improvement over the baseline methods on several benchmark datasets. Expand
Focal Loss for Dense Object Detection
TLDR
This paper proposes to address the extreme foreground-background class imbalance encountered during training of dense detectors by reshaping the standard cross entropy loss such that it down-weights the loss assigned to well-classified examples, and develops a novel Focal Loss, which focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training. Expand
Multiple Anchor Learning for Visual Object Detection
TLDR
A Multiple Instance Learning (MIL) approach that selects anchors and jointly optimizes the two modules of a CNN-based object detector, referred to as Multiple Anchor Learning (MAL), which improves the baseline RetinaNet with significant margins on the commonly used MS-COCO object detection benchmark and achieves new state-of-the-art detection performance compared with recent methods. Expand
Dynamic Anchor Feature Selection for Single-Shot Object Detection
TLDR
A dynamic feature selection operation to select new pixels in a feature map for each refined anchor received from the ARM, and a bidirectional feature fusion module by combining features from early and deep layers to enhance the representation ability of selected feature pixels. Expand
You Only Look Once: Unified, Real-Time Object Detection
TLDR
Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork. Expand
Feature Pyramid Networks for Object Detection
TLDR
This paper exploits the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost and achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles. Expand
Single-Shot Refinement Neural Network for Object Detection
TLDR
This paper proposes a novel single-shot based detector, called RefineDet, that achieves better accuracy than two-stage methods and maintains comparable efficiency of one- stage methods. Expand
Region Proposal by Guided Anchoring
TLDR
This paper presents an alternative scheme, named Guided Anchoring, which leverages semantic features to guide the anchoring, and jointly predicts the locations where the center of objects of interest are likely to exist as well as the scales and aspect ratios at different locations. Expand
FreeAnchor: Learning to Match Anchors for Visual Object Detection
TLDR
A learning-to-match (LTM) method to break IoU restriction, allowing objects to match anchors in a flexible manner, validating the general applicability of learnable object-feature matching mechism for visual object detection. Expand
Cascade R-CNN: Delving Into High Quality Object Detection
TLDR
A simple implementation of the Cascade R-CNN is shown to surpass all single-model object detectors on the challenging COCO dataset, and experiments show that it is widely applicable across detector architectures, achieving consistent gains independently of the baseline detector strength. Expand
...
1
2
3
4
...