Seeing without Looking: Contextual Rescoring of Object Detections for AP Maximization

Negrinho, Renato; Aguiar, Pedro M. Q.

doi:10.1109/cvpr42600.2020.01462

Cited by 20 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the greedy merging strategy is sub-optimal, which may lead to false detections. To remedy this, contextual information [44] and a graph neural network can be employed to better re-score the confidence of the detection bounding boxes.…”

Section: Discussionmentioning

confidence: 99%

An Enhanced Insect Pest Counter Based on Saliency Map and Improved Non-Maximum Suppression

Guo

Wang

Xiao

et al. 2021

Insects

View full text Add to dashboard Cite

Accurately counting the number of insect pests from digital images captured on yellow sticky traps remains a challenge in the field of insect pest monitoring. In this study, we develop a new approach to counting the number of insect pests using a saliency map and improved non-maximum suppression. Specifically, as the background of a yellow sticky trap is simple and the insect pest object is small, we exploit a saliency map to construct a region proposal generator including saliency map building, activation region formation, background–foreground classifier, and tune-up boxes involved in region proposal generation. For each region proposal, a convolutional neural network (CNN) model is used to classify it as a specific insect pest class, resulting in detection bounding boxes. By considering the relationship between detection bounding boxes, we thus develop an improved non-maximum suppression to sophisticatedly handle the redundant detection bounding boxes and obtain the insect pest number through counting the handled detection bounding boxes, each of which covers one insect pest. As this insect pest counter may miscount insect pests that are close to each other, we further integrate the widely used Faster R-CNN with the mentioned insect pest counter to construct a dual-path network. Extensive experimental simulations show that the two proposed insect pest counters achieve significant improvement in terms of F1 score against the state-of-the-art object detectors as well as insect pest detection methods.

show abstract

Section: Discussionmentioning

confidence: 99%

An Enhanced Insect Pest Counter Based on Saliency Map and Improved Non-Maximum Suppression

Guo

Wang

Xiao

et al. 2021

Insects

View full text Add to dashboard Cite

show abstract

“…Pyra-midBox [4] created a brand-new context anchor to supervise the semi-supervised learning of high-level contextual features. By rescoring the confidences of a detection after post-processing the output of a random detector, Pato et al [30] propose a technique for incorporating context in object detection.…”

Section: Context Informationmentioning

confidence: 99%

Drone-View Detection of YOLO via Tandem Cross Self-Attention and Contextual-Aware Module

fang,

Xing,

feng

et al. 2024

Preprint

View full text Add to dashboard Cite

Unmanned Aerial Vehicle (UAV) target detection involves automatically labeling objects captured during flight based on meaningful features. Compared to tra ditional images, aerial images have a higher viewpoint and often contain small objects and clustered features. Recent studies have demonstrated the advantages of deep learning in recognizing UAV images. However, early methods often had overlapping convolutional layers, which render the original contextual informa tion irrelevant. Besides, the imbalanced distribution of objects in the UAV field of view is prone to introduce the biases in detector attention, which will weaken the model training. This paper proposes an improved YOLOv5 framework for extracting multiple contextual information and enhancing dense region in UAV target detection. First, a context-aware module is introduced into DarkNet so that the multiple contextual information can be integrated skillfully. Addition ally, we propose a novel context semantic fusion approach, which contributes to integrate the varying expansion rates and deformable convolutions. This method effectively expands the perception field and enhances the precision of object boundaries. Finally, a concatenated cross self-attention operation is designed on high-resolution images to focus on dense regions and extract contextual infor mation from each pixel. Experimental results show improvements with average precision (AP50) of 5.9% and 3.89% on the VisDrone and UAVDT datasets, respectively. The findings demonstrate superior performance of the proposed method in UAV detection tasks and its potential application prospects.

show abstract

“…Fu et al modeled and inferred the inherent semantics and spatial layout relationship between objects and retained the spatial information as much as possible when extracting the semantic features of small objects [20]. Pato et al proposed a rescoring algorithm based on contextual rescoring, which used RNNs (Recurrent Neural Networks) and self-attention mechanisms to transfer information between candidate regions and generate contextual representation, and used the obtained context information to perform a secondary evaluation of the detection results [21].…”

Section: Contextual Learningmentioning

confidence: 99%

SV-FPN: Small Object Feature Enhancement and Variance-Guided RoI Fusion for Feature Pyramid Networks

et al. 2022

View full text Add to dashboard Cite

Small object detection is one of the research difficulties in object detection, and Feature Pyramid Networks (FPN) is a common feature extractor in deep learning; thus, improving the results of small object detection based on FPN is of great significance in this field. In this paper, SV-FPN is proposed for a small object detection task, which consists of Small Object Feature Enhancement (SOFE) and Variance-guided Region of Interest Fusion (VRoIF). When using FPN as a feature extractor, an SOFE module is designed to enhance the finer-resolution level feature maps from which the small object features are extracted. VRoIF takes the variance of RoI features as the data driver to learn the completeness of several RoI features from different feature layers, which avoids wasting information and introducing noise. Ablation experiments on three public datasets (KITTI, PASCAL VOC 07+12 and MS COCO 2017) demonstrate the effectiveness of SV-FPN, and the mean Average Precision (mAP) of SV-FPN in the three datasets achieves 41.5%, 53.9% and 38.3%, respectively.

show abstract

Seeing without Looking: Contextual Rescoring of Object Detections for AP Maximization

Cited by 20 publications

References 19 publications

An Enhanced Insect Pest Counter Based on Saliency Map and Improved Non-Maximum Suppression

An Enhanced Insect Pest Counter Based on Saliency Map and Improved Non-Maximum Suppression

Drone-View Detection of YOLO via Tandem Cross Self-Attention and Contextual-Aware Module

SV-FPN: Small Object Feature Enhancement and Variance-Guided RoI Fusion for Feature Pyramid Networks

Contact Info

Product

Resources

About