Hyperspectral anomaly detection via memory‐augmented autoencoders

Zhao, Zhe; Sun, Bangyong

doi:10.1049/cit2.12116

Cited by 13 publications

(5 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The UNet [17] is the most commonly used network structure and its special encoder-decoder structure shows excellent performance in the segmentation tasks. The improved versions of the UNet have also been proposed by introducing a residual module or a skip connection into the convolution operation to supplement the information loss in the reconstruction process [20][21][22] and using the attention modules at different locations in the network to help focus on more important features [23][24][25][26][27]. The NestedUNet [28] is a special structure that uses the dense skip connections across multiple scales to extract features, but it involves the complicated computation.…”

Section: Convolutional Neural Network Based Segmentation Methodsmentioning

confidence: 99%

Short‐term and long‐term memory self‐attention network for segmentation of tumours in 3D medical images

Wen

Zhou

Tao

et al. 2023

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

Tumour segmentation in medical images (especially 3D tumour segmentation) is highly challenging due to the possible similarity between tumours and adjacent tissues, occurrence of multiple tumours and variable tumour shapes and sizes. The popular deep learning‐based segmentation algorithms generally rely on the convolutional neural network (CNN) and Transformer. The former cannot extract the global image features effectively while the latter lacks the inductive bias and involves the complicated computation for 3D volume data. The existing hybrid CNN‐Transformer network can only provide the limited performance improvement or even poorer segmentation performance than the pure CNN. To address these issues, a short‐term and long‐term memory self‐attention network is proposed. Firstly, a distinctive self‐attention block uses the Transformer to explore the correlation among the region features at different levels extracted by the CNN. Then, the memory structure filters and combines the above information to exclude the similar regions and detect the multiple tumours. Finally, the multi‐layer reconstruction blocks will predict the tumour boundaries. Experimental results demonstrate that our method outperforms other methods in terms of subjective visual and quantitative evaluation. Compared with the most competitive method, the proposed method provides Dice (82.4% vs. 76.6%) and Hausdorff distance 95% (HD95) (10.66 vs. 11.54 mm) on the KiTS19 as well as Dice (80.2% vs. 78.4%) and HD95 (9.632 vs. 12.17 mm) on the LiTS.

show abstract

Section: Convolutional Neural Network Based Segmentation Methodsmentioning

confidence: 99%

Short‐term and long‐term memory self‐attention network for segmentation of tumours in 3D medical images

Wen

Zhou

Tao

et al. 2023

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

“…Then, the pixels with significant reconstruction errors are more likely to be anomalies. Still, if AE is fully trained, it is easy to reconstruct the anomaly, resulting in lower detection accuracy [36]. In order for the model to learn the structure information of the input HSI, Lu et al [37] embedded manifold learning into the AE structure, and the global and local reconstruction errors are employed in representing the anomaly level of pixels.…”

Section: Introductionmentioning

confidence: 99%

Frequency‐to‐spectrum mapping GAN for semisupervised hyperspectral anomaly detection

Wang

Gao

et al. 2023

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

Most unsupervised or semisupervised hyperspectral anomaly detection (HAD) methods train background reconstruction models in the original spectral domain. However, due to the noise and spatial resolution limitations, there may be a lack of discrimination between backgrounds and anomalies. This makes it easy for the autoencoder to capture the low‐level features shared between the two, thereby increasing the difficulty of separating anomalies from the backgrounds, which runs counter to the purpose of HAD. To this end, the authors map the original spectrums to the fractional Fourier domain (FrFD) and reformulate it as a mapping task in which restoration errors are employed to distinguish background and anomaly. This study proposes a novel frequency‐to‐spectrum mapping generative adversarial network for HAD. Specifically, the depth separable features of backgrounds and anomalies are enhanced in the FrFD. Due to the semisupervised approach, FTSGAN needs to learn the embedded features of the backgrounds, thus mapping and restoring them from the FrFD to the original spectral domain. This strategy effectively prevents the model from focussing on the numerical equivalence of input and output, and restricts the ability of FTSGAN to restore anomalies. The comparison and analysis of the experiments verify that the proposed method is competitive.

show abstract

“…This distinction serves as an effective method for detecting anomalies [20]. Zhao and Sun [21] proposed a memory-augmented auto-encoder for hyperspectral anomaly detection, where the latent representation from the auto-encoder is used to retrieve the most relevant matrix items in a memory matrix.…”

Section: Introductionmentioning

confidence: 99%

Anomaly Detection of Remote Sensing Images Based on the Channel Attention Mechanism and LRX

et al. 2023

View full text Add to dashboard Cite

Anomaly detection of remote sensing images has gained significant attention in remote sensing image processing due to their rich spectral information. The Local RX (LRX) algorithm, derived from the Reed–Xiaoli (RX) algorithm, is a hyperspectral anomaly detection method that focuses on identifying anomalous pixels in hyperspectral images by exploiting local statistics and background modeling. However, it is still susceptible to the noises in the Hyperspectral Images (HSIs), which limits its detection performance. To address this problem, a hyperspectral anomaly detection algorithm based on channel attention mechanism and LRX is proposed in this paper. The HSI is feed into the auto-encoder network that is constrained by the channel attention module to generate a more representative reconstructed image that better captures the characteristics of different land covers and has less noises. The channel attention module in the auto-encoder network aims to explore the effective spectral bands corresponding to different land covers. Subsequently, the LRX algorithm is utilized for anomaly detection on the reconstructed image obtained from the auto-encoder network with the channel attention mechanism, which avoids the influence of noises on the anomaly detection results and improves the anomaly detection performance. The experiments are conducted on three HSIs to verify the performance of the proposed method. The proposed hyperspectral anomaly detection method achieves higher Area Under Curve (AUC) values of 0.9871, 0.9916 and 0.9642 on HYDICE urban dataset, AVIRIS aircraft dataset and Salinas Valley dataset, respectively, compared with other six methods. The experimental results demonstrate that the proposed algorithm has better anomaly detection performance than LRX and other algorithms.

show abstract

Hyperspectral anomaly detection via memory‐augmented autoencoders

Cited by 13 publications

References 57 publications

Short‐term and long‐term memory self‐attention network for segmentation of tumours in 3D medical images

Short‐term and long‐term memory self‐attention network for segmentation of tumours in 3D medical images

Frequency‐to‐spectrum mapping GAN for semisupervised hyperspectral anomaly detection

Anomaly Detection of Remote Sensing Images Based on the Channel Attention Mechanism and LRX

Contact Info

Product

Resources

About