R-FCN++: Towards Accurate Region-Based Fully Convolutional Networks for Object Detection

Li, Zeming; Chen, Yilun; Yu, Gang; Deng, Yansha

doi:10.1609/aaai.v32i1.12265

Cited by 33 publications

(21 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Global context takes the overall structure in the image into account to learn from the scene-level context. Li et al proposed a new pooling method with either row-or column-wise max pooling by introducing a global context module using a separate convolution kernel 28 . Bell et al proposed an insideoutside network (ION) that uses both internal and external information of the ROI 29 .…”

Section: Global Context Informationmentioning

confidence: 99%

High-resolution processing and sigmoid fusion modules for efficient detection of small objects in an embedded system

Kim

Sung

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Recent advances in deep learning realized accurate, robust detection of various types of objects including pedestrians on the road, defect regions in the manufacturing process, human organs in medical images, and dangerous materials passing through the airport checkpoint. Specifically, small object detection implemented as an embedded system is gaining increasing attention for autonomous vehicles, drone reconnaissance, and microscopic imagery. In this paper, we present a light-weight small object detection model using two plug-in modules: (1) high-resolution processing module (HRPM ) and (2) sigmoid fusion module (SFM). The HRPM efficiently learns multi-scale features of small objects using a significantly reduced computational cost, and the SFM alleviates mis-classification errors due to spatial noise by adjusting weights on the lost small object information. Combination of HRPM and SFM significantly improved the detection accuracy with a low amount of computation. Compared with the original YOLOX-s model, the proposed model takes a two-times higher-resolution input image for higher mean average precision (mAP) using 57% model parameters and 71% computation in Gflops. The proposed model was tested using real drone reconnaissance images, and provided significant improvement in detecting small vehicles.

show abstract

Section: Global Context Informationmentioning

confidence: 99%

High-resolution processing and sigmoid fusion modules for efficient detection of small objects in an embedded system

Kim

Sung

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Module (GRAM) and relationships between objects. Local context can be integrated by simply enlarging the proposal size [52], [63] while global context can be incorporated by either global pooling operation [23], [24], [27] or learning with recurrent neural networks (RNN) [2], [22]. Closely related to our GRAM, Wang et al [48] introduce a non-local network to model global contextual information.…”

Section: Global Roi Attentionmentioning

confidence: 99%

Exploring Contextual Relationships for Cervical Abnormal Cell Detection

Liang¹,

Feng²,

Liu³

et al. 2022

Preprint

View full text Add to dashboard Cite

Cervical abnormal cell detection is a challenging task as the morphological discrepancies between abnormal and normal cells are usually subtle. To determine whether a cervical cell is normal or abnormal, cytopathologists always take surrounding cells as references to identify its abnormality. To mimic these behaviors, we propose to explore contextual relationships to boost the performance of cervical abnormal cell detection. Specifically, both contextual relationships between cells and cell-to-global images are exploited to enhance features of each region of interest (RoI) proposals. Accordingly, two modules, dubbed as RoI-relationship attention module (RRAM) and global RoI attention module (GRAM), are developed and their combination strategies are also investigated. We establish a strong baseline by using Double-Head Faster R-CNN with feature pyramid network (FPN) and integrate our RRAM and GRAM into it to validate the effectiveness of the proposed modules. Experiments conducted on a large cervical cell detection dataset reveal that the introduction of RRAM and GRAM both achieves better average precision (AP) than the baseline methods. Moreover, when cascading RRAM and GRAM, our method outperforms the state-of-the-art (SOTA) methods. Furthermore, we also show the proposed feature enhancing scheme can facilitate both image-level and smear-level classification. The code and trained models are publicly available at https://github.com/ CVIU-CSU/CR4CACD.

show abstract

“…It has been found that Faster R‐CNN uses function maps, which is heavy computationally. In a similar work (Li, 2016), authors proposed a region‐based faster convolutional network R‐FCN to save computational resources by the region of interest (ROI) mapping. However, the objects of different scales make it harder for the network to run the detection task efficiently.…”

Section: Related Workmentioning

confidence: 99%

A novel YOLOv4‐modified approach for efficient object detection in satellite imagery

2022

View full text Add to dashboard Cite

Interpreting high-resolution satellite imagery could be an expensive and timeconsuming task for human eyes. Computer Vision and Deep Learning techniques can help to solve this major problem by applying detection algorithms, which can ease the task of analysing such images for the benefit of humans. It can help in changing the way we comprehend and anticipate the economic activity around the world. Such techniques help us to observe the urban development in high security areas such as national and international borders. Constant progressions in improving and making satellites deployment, a cost-effective process to strengthen the networks of satellite orbiting the earth is one of the reasons such tasks can be easily solved with the help of high-resolution images. Current computer vision research works have achieved significant milestones in accuracy and speed but, there are still room for improvements. In this paper, we addressed some of these methods to bring them to a combined pipeline and proposed a set of improvements to further improve the speed and the accuracy of the detections. We proposed a unified framework, which combines several object detection algorithms and the state-of-art architecture of YoloV4 along with the TensorFlow object detection API. This framework can detect small and well as large objects with improved speed and accuracy by using two detectors for different scales. Evaluation ran on these high-resolution images yield mAP of 85.6%

show abstract

R-FCN++: Towards Accurate Region-Based Fully Convolutional Networks for Object Detection

Cited by 33 publications

References 24 publications

High-resolution processing and sigmoid fusion modules for efficient detection of small objects in an embedded system

High-resolution processing and sigmoid fusion modules for efficient detection of small objects in an embedded system

Exploring Contextual Relationships for Cervical Abnormal Cell Detection

A novel YOLOv4‐modified approach for efficient object detection in satellite imagery

Contact Info

Product

Resources

About