Attend Refine Repeat: Active Box Proposal Generation via In-Out Localization

Gidaris, Spyridon; Komodakis, Nikos

doi:10.5244/c.30.90

Cited by 66 publications

(67 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The multi-region detector [9] introduced iterative bounding box regression, where a R-CNN is applied several times, to produce better bounding boxes. CRAFT [33] and AttractioNet [10] used a multi-stage procedure to generate accurate proposals, and forwarded them to a Fast-RCNN. [19,25] embedded the classic cascade architecture of [31] in object detection networks.…”

Section: Related Workmentioning

confidence: 99%

Cascade R-CNN: Delving Into High Quality Object Detection

Cai

Vasconcelos

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

5,035

2,558

View full text Add to dashboard Cite

In object detection, an intersection over union (IoU) threshold is required to define positives and negatives. An object detector, trained with low IoU threshold, e.g. 0.5, usually produces noisy detections. However, detection performance tends to degrade with increasing the IoU thresholds. Two main factors are responsible for this: 1) overfitting during training, due to exponentially vanishing positive samples, and 2) inference-time mismatch between the IoUs for which the detector is optimal and those of the input hypotheses. A multi-stage object detection architecture, the Cascade R-CNN, is proposed to address these problems. It consists of a sequence of detectors trained with increasing IoU thresholds, to be sequentially more selective against close false positives. The detectors are trained stage by stage, leveraging the observation that the output of a detector is a good distribution for training the next higher quality detector. The resampling of progressively improved hypotheses guarantees that all detectors have a positive set of examples of equivalent size, reducing the overfitting problem. The same cascade procedure is applied at inference, enabling a closer match between the hypotheses and the detector quality of each stage. A simple implementation of the Cascade R-CNN is shown to surpass all single-model object detectors on the challenging COCO dataset. Experiments also show that the Cascade R-CNN is widely applicable across detector architectures, achieving consistent gains independently of the baseline detector strength. The code will be made available at https://github.com/zhaoweicai/cascade-rcnn.

show abstract

Section: Related Workmentioning

confidence: 99%

Cascade R-CNN: Delving Into High Quality Object Detection

Cai

Vasconcelos

2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

5,035

2,558

View full text Add to dashboard Cite

show abstract

“…The multi-region detector of [17] introduced iterative bounding box regression, where a R-CNN is applied several times to produce successively more accurate bounding boxes. [18], [19], [60] used a multi-stage procedure to generate accurate proposals, which are forwarded to an accurate model (e.g. Fast R-CNN).…”

Section: Related Workmentioning

confidence: 99%

“…In the literature, there have been efforts to increase the quality of hypotheses, e.g. by iterative bounding box regression [18], [19] or better RPN design [2], [37], and some efforts to increase the quality of the object detector, e.g. by using the integral loss on a set of IoU thresholds [63].…”

Section: Challenges To High Quality Detectionmentioning

confidence: 99%

Cascade R-CNN: High Quality Object Detection and Instance Segmentation

Cai

Vasconcelos

2021

IEEE Trans. Pattern Anal. Mach. Intell.

1,082

616

View full text Add to dashboard Cite

In object detection, the intersection over union (IoU) threshold is frequently used to define positives/negatives. The threshold used to train a detector defines its quality. While the commonly used threshold of 0.5 leads to noisy (low-quality) detections, detection performance frequently degrades for larger thresholds. This paradox of high-quality detection has two causes: 1) overfitting, due to vanishing positive samples for large thresholds, and 2) inference-time quality mismatch between detector and test hypotheses. A multi-stage object detection architecture, the Cascade R-CNN, composed of a sequence of detectors trained with increasing IoU thresholds, is proposed to address these problems. The detectors are trained sequentially, using the output of a detector as training set for the next. This resampling progressively improves hypotheses quality, guaranteeing a positive training set of equivalent size for all detectors and minimizing overfitting. The same cascade is applied at inference, to eliminate quality mismatches between hypotheses and detectors. An implementation of the Cascade R-CNN without bells or whistles achieves state-of-the-art performance on the COCO dataset, and significantly improves high-quality detection on generic and specific object detection datasets, including VOC, KITTI, CityPerson, and WiderFace. Finally, the Cascade R-CNN is generalized to instance segmentation, with nontrivial improvements over the Mask R-CNN. To facilitate future research, two implementations are made available at https://github.com/zhaoweicai/cascade-rcnn (Caffe) and https://github.com/zhaoweicai/Detectron-Cascade-RCNN (Detectron). person: 1.00 person: 1.00 person: 0.99 person: 0.99 person: 0.87 person: 0.82 person: 0.77 person: 0.70 person: 0.64 person: 0.63 person: 0.56 frisbee: 1.00 frisbee: 1.00 frisbee: 0.99 frisbee: 0.97 (a) Detection of u = 0.5 person: 1.00 person: 0.99 person: 0.96 person: 0.94 person: 0.55 frisbee: 0.99 frisbee: 0.99 frisbee: 0.99 frisbee: 0.93

show abstract

“…The RPN in multi-stage object detectors [2][3] [7] which selects regions of interests can be viewed as the hard spatial attention. In AttractioNet [39], an active box proposal generation strategy is proposed to progressively focus on the promising image areas for region proposals, behaving like an attention mechanism. These works are hard spatial attention for box selection.…”

Section: B Attention For Visual Recognitionmentioning

confidence: 99%

HAR-Net: Joint Learning of Hybrid Attention for Single-Stage Object Detection

Wang

2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Object detection has been a challenging task in computer vision. Although significant progress has been made in object detection with deep neural networks, the attention mechanism is far from development. In this paper, we propose the hybrid attention mechanism for single-stage object detection. First, we present the modules of spatial attention, channel attention and aligned attention for single-stage object detection. In particular, stacked dilated convolution layers with symmetrically fixed rates are constructed to learn spatial attention. The channel attention is proposed with the cross-level group normalization and squeezeand-excitation module. Aligned attention is constructed with organized deformable filters. Second, the three kinds of attention are unified to construct the hybrid attention mechanism. We then embed the hybrid attention into Retina-Net and propose the efficient single-stage HAR-Net for object detection. The attention modules and the proposed HAR-Net are evaluated on the COCO detection dataset. Experiments demonstrate that hybrid attention can significantly improve the detection accuracy and the HAR-Net can achieve the state-of-the-art 45.8% mAP, outperform existing single-stage object detectors.

show abstract

Attend Refine Repeat: Active Box Proposal Generation via In-Out Localization

Cited by 66 publications

References 39 publications

Cascade R-CNN: Delving Into High Quality Object Detection

Cascade R-CNN: Delving Into High Quality Object Detection

Cascade R-CNN: High Quality Object Detection and Instance Segmentation

HAR-Net: Joint Learning of Hybrid Attention for Single-Stage Object Detection

Contact Info

Product

Resources

About