MALNISI-Infused Graph Construction and Weighted Contrastive Loss based GAT for Unsupervised Representation Learning in HSI
Organizations: Machine Intelligence Unit, Indian Statistical Institute, Kolkata, West Bengal 700108, India · Siksha ’O’ Anusandhan, Bhubaneswar, Odisha 751030, India · Computer Vision and Pattern Recognition Unit, Indian Statistical Institute, Kolkata, West Bengal 700108, India · International Institute of Information Technology, Bhubaneswar, Odisha 751003, India
Abstract
Hyperspectral images (HSI) possess discriminating spectral characteristics with respect to land utilization due to high-dimensional information. Recently, unsupervised representation learning using graph neural networks has unveiled these utilization-specific complex spectral relations. This article has three main contributions. First, it proposes an index, the Mean Absolute Local Neighborhood Inverse Spectral Index (MALNISI), which measures the similarity between two pixels based on their neighborhood information. The index is used to construct a weighted adjacency matrix, giving the HSI a graph structure. Second, it proposes an upgraded Graph Attention Network that learns compact latent representations of hyperspectral data from the constructed graph. In this network, an enhanced multi-head attention mechanism incorporates the MALNISI weights as an auxiliary feature to emphasize learned attention between neighboring pixels. To alleviate over-smoothing and preserve fine-grained spectral details, the architecture integrates residual connections, skip projections, and feature normalization, which together enhance representation capability, stabilize learning, and accelerate convergence. Third, it proposes a weighted contrastive loss function that incorporates neighborhood-aware MALNISI between connected pixels, encouraging strongly connected pixels in the high-dimensional space to remain close in the latent space, and weakly connected pixels to stay apart. The resulting discriminative low-dimensional embeddings are then clustered using spectral clustering. Experimental analysis on six benchmark HSI datasets demonstrates the efficiency and necessity of the three aforementioned contributions, and the comparative study highlights superior performance over fourteen state-of-the-art approaches.
Figures & tables
| Category | Methods | Mechanism | Key Advantages | Limitations |
|---|---|---|---|---|
| Linear Reduction | PCA, LDA | Linear projection to reduce spectral redundancy. | Computationally simple; fast execution. | Fails to capture non-linear structures. |
| Centroid-Based | -means, FCM | Iterative refinement of cluster centers. | Intuitive; incoorporates explainability. | Assumes spherical cluster shapes. |
| Density-Based | DBSCAN, CFSFDP | Identification of clusters as high-density regions. | Finds arbitrary shapes; robust to noise. | Struggles with the curse of dimensionality. |
| Graph-Based | FSCAG, SGCNR, BGPC, SAPC | Pixel-to-anchor adjacency and bipartite graph projection. | Near-linear scalability; captures connectivity. | Quality depends on anchor selection/kernels. |
| Subspace-Based | EnSC, SSC-BP, HESSC, SGLSC, EGFSC | Representation as a union of low-dimensional subspaces. | Handles spectral variability and spatial edges. | Sensitive to manual graph design and noise. |
| Deep Learning | DCN, DSCRLE, DSCFS | End-to-end non-linear feature extraction via AEs/CNNs. | High discriminative power; non-linear modeling. | Often suffers from fragmented feature integration. |
| Challenges in SOTA | Proposed Solution (MALNISI-GAT Network) |
|---|---|
| Spectral Noise Interference | Integrates noise-robust MALNISI in initial graph construction. |
| Spatially Distributed Spectrally Similar Regions | Graph networks have transitive feature aggregation across multiple layers that strongly pull same-category pixels. |
| Complex & Non-Compact Data | Weighted contrastive loss forces to maintain spectrally consistency while embedding. |
| Dataset | Sensor | Location | Image Size | Bands | Categories | Data Type |
|---|---|---|---|---|---|---|
| Indian Pines (IndianP) [ 38 ] | AVIRIS | Indiana, USA | 200 | 16 | Agricultural | |
| Pavia University (PaviaU) [ 38 ] | ROSIS | Pavia, Italy | 103 | 9 | Urban | |
| Salinas [ 38 ] | AVIRIS | Salinas Valley, CA, USA | 204 | 16 | Agricultural | |
| HongHu [ 39 ] | Nano-Hyperspec | Honghu, Hubei, China | 270 | 22 | Agricultural | |
| Botswana [ 38 ] | Hyperion | Okavango Delta, Botswana | 145 | 14 | Wetland / Vegetation | |
| Kennedy Space Center (KSC) [ 38 ] | AVIRIS | Florida, USA | 176 | 13 | Wetland / Vegetation |
| Type | Meric | Purpose | Range | Optimal |
| Direction | ||||
| Overall Accuracy (OA) | Overall correct assignment of pixels to corresponding true group | |||
| Average Accuracy (AA) | Mean group-wise accuracy with dominant-group bias mitigation | |||
| Normalized Mutual Information (NMI) | Similarity between clustering assignments and true group from an information-theoretic perspective with by chance agreement | |||
| External Index | Adjusted Rand Index (ARI) | Pairwise similarity between clustering assignments and true group from an information-theoretic perspective | ||
| Adjusted Mutual Information (AMI) | Clustering consistency and structural correspondence between predicted and true group with by chance agreement reduction |
| Dataset | External Index | Internal Index | Efficiency | |||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| OA | AA | NMI | ARI | AMI | FMI | Homogeneity | Completeness | Kappa | Purity | DB | SH | CH | Dunn | Total Inference Time (s) | Inference Time / Sample (s) | Peak Memory (MB) | FLOPS / Sample | |
| IndianP | 80.49 | 57.41 | 0.7818 | 0.7143 | 0.7811 | 0.7534 | 0.7559 | 0.8095 | 0.7767 | 0.8049 | 1.8208 | 0.206 | 736.7607 | 0.0358 | 5.1013 | 2.4263e-4 | 29.54 | 5.13e+07 |
| PaviaU | 90.61 | 74.76 | 0.9206 | 0.9446 | 0.9205 | 0.9587 | 0.8815 | 0.9633 | 0.8753 | 0.9061 | 1.8759 | 0.169 | 3371.7265 | 0.0515 | 6.0811 | 2.932e-5 | 81.59 | 3.77e+08 |
| Salinas | 86.69 | 95.74 | 0.9279 | 0.7124 | 0.9279 | 0.745 | 0.9201 | 0.9359 | 0.8533 | 0.8669 | 1.0451 | 0.4112 | 7823.4914 | 0.0182 | 22.3054 | 2.0076e-4 | 155.14 | 1.43e+09 |
| HongHu | 84.46 | 62.11 | 0.7964 | 0.9066 | 0.7963 | 0.9259 | 0.7891 | 0.8038 | 0.8049 | 0.8446 | 1.865 | 0.1494 | 15159.9469 | - | 7.3074 | 2.1793e-4 | 1409.52 | 1.30e+11 |
| Botswana | 80.7 | 74.02 | 0.8214 | 0.7039 | 0.8198 | 0.7287 | 0.8022 | 0.8414 | 0.7904 | 0.807 | 1.469 | 0.3249 | 492.2974 | 0.0323 | 2.6438 | 7.00e-6 | 9.75 | 1.33e+05 |
| Datasets | Metrics | FSCAG [ 22 ] | SGCNR [ 4 ] | HESSC [ 25 ] | NCSC [ 27 ] | SGLSC [ 26 ] | S 3 AGC [ 34 ] | DSCRLE [ 33 ] | BGPC [ 11 ] | SAPC [ 12 ] | EGFSC [ 2 ] | Proposed SD | t-statistic | p-value |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| IndianP | OA | 36.13 | 35.75 | 34.08 | 58.65 | 59.50 | 49.94 | 47.80 | 43.85 | 55.88 | 70.08 | 80.49 0.0728 | 315.75 | 3.02e-10 |
| AA | 37.82 | 35.35 | 35.12 | 49.46 | 54.25 | 42.25 | 39.88 | 41.84 | 52.39 | 55.74 | 57.41 0.0683 | 50.65 | 4.55e-07 | |
| Kappa | 0.2955 | 0.2889 | 0.2866 | 0.5346 | 0.5522 | 0.4317 | 0.3996 | 0.3782 | 0.4959 | 0.6580 | 0.7767 0.0009 | 303.93 | 3.52e-10 | |
| NMI | 0.4513 | 0.4463 | 0.4133 | 0.5911 | 0.6190 | 0.5157 | 0.4779 | 0.5020 | 0.5403 | 0.6910 | 0.7818 0.0019 | 105.28 | 2.44e-08 | |
| Purity | 0.5187 | 0.5261 | 0.5042 | 0.6404 | 0.7058 | 0.5548 | 0.5270 | 0.5530 | 0.5933 | 0.7517 | 0.8049 0.0007 | 159.41 | 4.64e-09 | |
| PaviaU | OA | 49.34 | 57.45 | 45.03 | 54.88 | 62.45 | 53.38 | 68.46 | 74.05 | 63.94 | 75.76 | 90.61 1.5697 | 17.15 | 3.39e-05 |
| Method | OA | Kappa | NMI | Purity |
|---|---|---|---|---|
| -means [ 19 ] | 64.56 | 0.6205 | 0.7416 | 0.6456 |
| H-GMM [ 40 ] | 66.41 | 0.6416 | 0.7493 | 0.6641 |
| FSEC [ 41 ] | 68.20 | 0.6579 | 0.8324 | 0.6820 |
| EnSC [ 24 ] | 65.64 | 0.6331 | 0.6886 | 0.6564 |
| SSC-BP [ 23 ] | 70.91 | 0.6875 | 0.7316 | 0.7091 |
| DSCFS [ 28 ] | 82.39 | 0.8113 | 0.8358 | 0.8239 |
Unsupervised Representation Learning
Unsupervised representation learning discovers useful, structured features from data without relying on task labels.
See all 76 papers