The high dimensionality of hyperspectral images often results in the degradation of clustering performance. Due to the powerful ability of potential feature extraction and nonlinear representation, deep clustering algorithms have become a hot topic in hyperspectral remote sensing. Different tasks often need different features. However, the current deep clustering algorithms generally separate feature extraction from clustering, which results in the extracted features that are not constrained by clustering tasks. Therefore, the features extracted by these algorithms may not be suitable for clustering. To address this issue, we adopt intraclass distance as a constraint condition and proposed an intraclass distance constrained deep clustering algorithm for hyperspectral images. The proposed algorithm propagates the clustering error back to the feature mapping process of the autoencoder network, so as to realize the constraint of clustering objective on feature extraction and make the extracted features more suitable for clustering tasks. In addition, the proposed algorithm simultaneously completes network optimization and clustering, which is more efficient. Experimental results demonstrate the intense competitiveness of the proposed algorithm in comparison with state-of-the-art clustering methods for hyperspectral images.

Intersection over Union (IoU) is an important function in object detection based on deep learning. But, there is a gap between the used distance losses and this metric value of maximizing. This paper improves the IoU function based on IoU. Redesigned the neural network structure, and used the PASCAL VOC2012 dataset. The structure model of the neural network is compare with others in the accuracy of object detection. Experimental results show that our method can achieve good results in object detection. The approach provides a new idea for object detection.

Calibration remains a practical barrier for steady-state visual evoked potential (SSVEP) brain–computer interfaces. Task-related component analysis (TRCA) is accurate when several labelled trials per class are available, but its performance degrades when calibration is reduced to one trial and the test block follows a change in recording conditions. We asked whether a fixed modification of ensemble TRCA (eTRCA) could reduce this loss without any per-subject hyperparameter tuning. The proposed SST-eTRCA appends a three-sample delayed copy of each channel, z-scores observations before covariance accumulation, and pools 80 class filters into one projection. On the public 35-subject Tsinghua benchmark (40 classes, six posterior channels), it reached 95.6% with one calibration trial per class versus 93.4% for eTRCA (1400 decisions; McNemar p = 1.5E-5), and 95.0% versus 91.8% without extra calibration. The advantage was largest at 1 s (68.9% versus 63.9%). Under leave-one-subject-out, SST-eTRCA and eTRCA were indistinguishable (83.6% each), and self-training changed accuracy by only 0.1 points (p = 0.75). The gain is therefore specific to within-participant block shift, not to cross-subject transfer. These results define a narrow but useful operating range: a fixed, reproducible decoder for reducing recalibration across blocks, with the negative self-training result serving as a reliability check.

The high dimensionality of hyperspectral images often results in the degradation of clustering performance. Due to the powerful ability of deep feature extraction and non-linear feature representation, the clustering algorithm based on deep learning has become a hot research topic in the field of hyperspectral remote sensing. However, most deep clustering algorithms for hyperspectral images utilize deep neural networks as feature extractor without considering prior knowledge constraints that are suitable for clustering. To solve this problem, we propose an intra-class distance constrained deep clustering algorithm for high-dimensional hyperspectral images. The proposed algorithm constrains the feature mapping procedure of the auto-encoder network by intra-class distance so that raw images are transformed from the original high-dimensional space to the low-dimensional feature space that is more conducive to clustering. Furthermore, the related learning process is treated as a joint optimization problem of deep feature extraction and clustering. Experimental results demonstrate the intense competitiveness of the proposed algorithm in comparison with state-of-the-art clustering methods of hyperspectral images.