BorderDet: Border Feature for Dense Object Detection

@inproceedings{Qiu2020BorderDetBF,
  title={BorderDet: Border Feature for Dense Object Detection},
  author={Han Qiu and Yuchen Ma and Zeming Li and Songtao Liu and Jian Sun},
  booktitle={ECCV},
  year={2020}
}
  • Han Qiu, Yuchen Ma, Jian Sun
  • Published in ECCV 21 July 2020
  • Computer Science
Dense object detectors rely on the sliding-window paradigm that predicts the object over a regular grid of image. Meanwhile, the feature maps on the point of the grid are adopted to generate the bounding box predictions. The point feature is convenient to use but may lack the explicit border information for accurate localization. In this paper, We propose a simple and efficient operator called Border-Align to extract "border features" from the extreme point of the border to enhance the point… 
HoughNet: Integrating near and long-range evidence for visual detection
TLDR
The effectiveness of HoughNet is validated in other visual detection tasks, namely, video object detection, instance segmentation, 3D object detection and keypoint detection for human pose estimation, and an additional “labels to photo” image generation task, where the integration of the voting module consistently improves performance in all cases.
EPP-Net: Extreme-Point-Prediction-Based Object Detection
TLDR
The proposed EPP-Net provides a new method to detect objects and outperforms state-of-the-art anchor-free detectors and proposes a novel branch to predict the EIoU between the groundtruth and the prediction results.
FCOS: A Simple and Strong Anchor-Free Object Detector
TLDR
A fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to other dense prediction problems such as semantic segmentation, achieving improved detection accuracy.
Generalized Focal Loss V2: Learning Reliable Localization Quality Estimation for Dense Object Detection
TLDR
This paper explores a completely novel and different perspective to perform LQE – based on the learned distributions of the four parameters of the bounding box – and develops a considerably lightweight Distribution-Guided Quality Predictor (DGQP) for reliable LqE based on GFLV1, thus producing GFLv2.
QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection
TLDR
QueryDet is proposed that uses a novel query mechanism to accelerate the inference speed of feature-pyramid based object detectors and can not only harvest the benefit of high-resolution feature maps but also avoid useless computation for the background area.
Implicit Feature Pyramid Network for Object Detection
TLDR
i-FPN is presented, proposing to use an implicit function, recently introduced in deep equilibrium model (DEQ) [2, 4], to model the transformation of FPN and developing a residual-like iteration to updates the hidden states efficiently.
PDNet: Towards Better One-stage Object Detection with Prediction Decoupling
  • Li Yang, Yan Xu, Weiming Hu
  • Computer Science
    IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
  • 2022
TLDR
This paper analyzes the suitable inference positions for object category and boundaries, and proposes a prediction-target-decoupled detector named PDNet to establish a more flexible detection paradigm and is highly efficient as a one-stage framework.
IQDet: Instance-wise Quality Distribution Sampling for Object Detection
TLDR
A dense object detector with an instance-wise sampling strategy, named IQDet, which automatically selects training samples in a probabilistic manner and trains with more high-quality samples, and is completely cost-free in inference time.
Object Detection Made Simpler by Eliminating Heuristic NMS
We show a simple NMS-free, end-to-end object detection framework, of which the network is a minimal modification to a one-stage object detector such as the FCOS detection model [24]. We attain on par
Localization Distillation for Object Detection
TLDR
For the first time, it is shown that logit mimicking can outperform feature imitation and the absence of localization distillation is a critical reason for why logit Mimicking underperforms for years.
...
...

References

SHOWING 1-10 OF 39 REFERENCES
RepPoints: Point Set Representation for Object Detection
TLDR
It is shown that an anchor-free object detector based on RepPoints can be as effective as the state-of-the-art anchor-based detection methods, with 46.5 AP and 67.4 $AP_{50}$ on the COCO test-dev detection benchmark, using ResNet-101 model.
Side-Aware Boundary Localization for More Precise Object Detection
TLDR
This paper proposes an alternative approach, named as Side-Aware Boundary Localization (SABL), where each side of the bounding box is respectively localized with a dedicated network branch, to tackle the difficulty of precise localization in the presence of displacements with large variance.
LocNet: Improving Localization Accuracy for Object Detection
TLDR
This work proposes a novel object localization methodology that makes use of a convolutional neural network architecture that is properly adapted for this task, called LocNet and shows experimentally that LocNet achieves a very significant improvement on the mAP for high IoU thresholds on PASCAL VOC2007 test set.
CenterNet: Keypoint Triplets for Object Detection
TLDR
This paper presents an efficient solution that explores the visual patterns within individual cropped regions with minimal costs, and builds the framework upon a representative one-stage keypoint-based detector named CornerNet, which improves both precision and recall.
Bottom-Up Object Detection by Grouping Extreme and Center Points
TLDR
The proposed method performs on-par with the state-of-the-art region based detection methods, with a bounding box AP of 43.7% on COCO test-dev and extreme point guided segmentation further improves this to 34.6% Mask AP.
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.
Attend Refine Repeat: Active Box Proposal Generation via In-Out Localization
TLDR
This work proposes a new approach to tackle the problem of computing category agnostic bounding box proposals based on an active strategy for generating box proposals that starts from a set of seed boxes, which are uniformly distributed on the image, and then progressively moves its attention on the promising image areas where it is more likely to discover well localized boundingbox proposals.
Deep Regionlets for Object Detection
TLDR
This paper proposes a "region selection network" and a "gating network" that serves as a guidance on where to select regions to learn the features from in Regionlet and achieves comparable state-of-the-art results.
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TLDR
This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%.
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.
...
...