Dual‐branch mutual assistance network for salient object detection

Yao, Zhaojian; Wang, Luping

doi:10.1002/int.22654

Cited by 3 publications

(1 citation statement)

References 45 publications

(60 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is designed to accurately detect small objects (objects under 32 pixels × 32 pixels) with few visible features in the image [20]. In real scenarios, due to a large number of small objects, small object detection has broad application prospects and plays an essential role in many felds such as autonomous driving, smart medical care, defect detection, and aerial image analysis [21][22][23]. When faced with the problem that small objects are challenging to detect, many methods diferent from feature pyramid networks have emerged, and these methods have also achieved specifc results.…”

Section: Deep Object Detectorsmentioning

confidence: 99%

ALFPN: Adaptive Learning Feature Pyramid Network for Small Object Detection

Chen

Wang

Ruan

et al. 2023

International Journal of Intelligent Systems

View full text Add to dashboard Cite

Object detection has become a crucial technology in intelligent vision systems, enabling automatic detection of target objects. While most detectors perform well on open datasets, they often struggle with small-scale objects. This is due to the traditional top-down feature fusion methods that weaken the semantic and location information of small objects, leading to poor classification performance. To address this issue, we propose a novel feature pyramid network, the adaptive learnable feature pyramid network (ALFPN). Our approach features an adaptive feature inspection that incorporates learnable fusion coefficients in the fusion of different levels of feature layers, aiding the network in learning features with less noise. In addition, we construct a context-aligned supervisor that adjusts the feature maps fused at different levels to avoid scaling-related offset effects. Our experiments demonstrate that our method achieves state-of-the-art results and is highly robust for the small object detection on the TT-100K, PASCAL VOC, and COCO datasets. These findings indicate that a model’s ability to extract discriminant features is positively correlated with its performance in detecting small objects.

show abstract