Improving Object Localization with Fitness NMS and Bounded IoU Loss

Tychsen-Smith, Lachlan; Petersson, Lars

doi:10.1109/cvpr.2018.00719

Cited by 198 publications

(93 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…At last, one can observe that the performance of CenterNet is also competitive with the two-stage approaches, e.g., the single-scale testing AP of CenterNet511-52 is comparable to the two-stage approach Fitness R-CNN [41] (41.6% vs. 41.8%) and that of CenterNet511-104 is comparable to D-RFCN + SNIP [38] (44.9% vs. 45.7%), respectively. Nevertheless, it should be mentioned that twostage approaches usually use larger resolution input images (e.g., ∼ 1000 × 600), which significantly improves the detection accuracy especially for small objects.…”

Section: Comparisons With State-of-the-art Detectorsmentioning

confidence: 97%

CenterNet: Keypoint Triplets for Object Detection

Duan

Bai

Xie

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

2,509

1,092

View full text Add to dashboard Cite

In object detection, keypoint-based approaches often suffer a large number of incorrect object bounding boxes, arguably due to the lack of an additional look into the cropped regions. This paper presents an efficient solution which explores the visual patterns within each cropped region with minimal costs. We build our framework upon a representative one-stage keypoint-based detector named Corner-Net. Our approach, named CenterNet, detects each object as a triplet, rather than a pair, of keypoints, which improves both precision and recall. Accordingly, we design two customized modules named cascade corner pooling and center pooling, which play the roles of enriching information collected by both top-left and bottom-right corners and providing more recognizable information at the central regions, respectively. On the MS-COCO dataset, CenterNet achieves an AP of 47.0%, which outperforms all existing one-stage detectors by at least 4.9%. Meanwhile, with a faster inference speed, CenterNet demonstrates quite comparable performance to the top-ranked two-stage detectors. Code is available at https://github.com/ Duankaiwen/CenterNet.

show abstract

Section: Comparisons With State-of-the-art Detectorsmentioning

confidence: 97%

CenterNet: Keypoint Triplets for Object Detection

Duan

Bai

Xie

et al. 2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

2,509

1,092

View full text Add to dashboard Cite

show abstract

“…There are several methods focusing on correcting the classification score for the detection box, which have a similar goal to our method. Tychsen-Smith et al [36] proposed Fitness NMS that corrected the detection score using the IoU between the detected bounding boxes and their ground truth. It formulates box IoU prediction as a classification task.…”

Section: Detection Score Correctionmentioning

confidence: 99%

Mask Scoring R-CNN

Huang

Gong

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

978

541

View full text Add to dashboard Cite

Letting a deep network be aware of the quality of its own predictions is an interesting yet important problem. In the task of instance segmentation, the confidence of instance classification is used as mask quality score in most instance segmentation frameworks. However, the mask quality, quantified as the IoU between the instance mask and its ground truth, is usually not well correlated with classification score. In this paper, we study this problem and propose Mask Scoring R-CNN which contains a network block to learn the quality of the predicted instance masks. The proposed network block takes the instance feature and the corresponding predicted mask together to regress the mask IoU. The mask scoring strategy calibrates the misalignment between mask quality and mask score, and improves instance segmentation performance by prioritizing more accurate mask predictions during COCO AP evaluation. By extensive evaluations on the COCO dataset, Mask Scoring R-CNN brings consistent and noticeable gain with different models, and outperforms the state-of-the-art Mask R-CNN. We hope our simple and effective approach will provide a new direction for improving instance segmentation. The source code of our method is available at https:// github.com/zjhuang22/maskscoring_rcnn.

show abstract

“…Theoretically, the more pairs we sample, the more accurate the approximation is, while the computational cost is heavier. We adopt a variant of bounded iou loss [29] to optimize the shape prediction, without computing the target. The loss is defined in Eq.…”

Section: Trainingmentioning

confidence: 99%

Region Proposal by Guided Anchoring

Wang

Chen

Yang

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

589

302

View full text Add to dashboard Cite

Region anchors are the cornerstone of modern object detection techniques. State-of-the-art detectors mostly rely on a dense anchoring scheme, where anchors are sampled uniformly over the spatial domain with a predefined set of scales and aspect ratios. In this paper, we revisit this foundational stage. Our study shows that it can be done much more effectively and efficiently. Specifically, we present an alternative scheme, named Guided Anchoring, which leverages semantic features to guide the anchoring. The proposed method 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. On top of predicted anchor shapes, we mitigate the feature inconsistency with a feature adaption module. We also study the use of high-quality proposals to improve detection performance. The anchoring scheme can be seamlessly integrated into proposal methods and detectors. With Guided Anchoring, we achieve 9.1% higher recall on MS COCO with 90% fewer anchors than the RPN baseline. We also adopt Guided Anchoring in Fast R-CNN, Faster R-CNN and RetinaNet, respectively improving the detection mAP by 2.2%, 2.7% and 1.2%. Code will be available at https: //github.com/open-mmlab/mmdetection.

show abstract

Improving Object Localization with Fitness NMS and Bounded IoU Loss

Cited by 198 publications

References 17 publications

CenterNet: Keypoint Triplets for Object Detection

CenterNet: Keypoint Triplets for Object Detection

Mask Scoring R-CNN

Region Proposal by Guided Anchoring

Contact Info

Product

Resources

About