RMLANet: Random Multi-Level Attention Network for Shadow Detection

Jie, Leiping; Zhang, Hui

doi:10.1109/icme52920.2022.9860013

Cited by 7 publications

(1 citation statement)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A BER below 5 indicates a very strong correlation. Notably, state-of-the-art models tailored for shadow detection typically achieve a BER around 3 for SBU [27][28][29] and between 1 and 2 for ISTD [27][28][29]. Despite not being specifically designed for shadow detection, our choice of architecture, UnetPlusPlus and EfficientNet-b5, performed reasonably well, particularly achieving a BER of 1.8 for ISTD.…”

Section: Cross-dataset Evaluationmentioning

confidence: 90%

A Comparative Study of Physically Accurate Synthetic Shadow Datasets in Agricultural Settings with Human Activity

Huang,

Fernandez-Beltran,

García-Mateos

2024

Sensors

View full text Add to dashboard Cite

Shadow, a natural phenomenon resulting from the absence of light, plays a pivotal role in agriculture, particularly in processes such as photosynthesis in plants. Despite the availability of generic shadow datasets, many suffer from annotation errors and lack detailed representations of agricultural shadows with possible human activity inside, excluding those derived from satellite or drone views. In this paper, we present an evaluation of a synthetically generated top-down shadow segmentation dataset characterized by photorealistic rendering and accurate shadow masks. We aim to determine its efficacy compared to real-world datasets and assess how factors such as annotation quality and image domain influence neural network model training. To establish a baseline, we trained numerous baseline architectures and subsequently explored transfer learning using various freely available shadow datasets. We further evaluated the out-of-domain performance compared to the training set of other shadow datasets. Our findings suggest that AgroSegNet demonstrates competitive performance and is effective for transfer learning, particularly in domains similar to agriculture.

show abstract