Pavia University Benchmark (Hyperspectral Image Classification)

33 rows 28 with code listed 12 metrics Dataset page

Hyperspectral Image Classification is a task in the field of remote sensing and computer vision. It involves the classification of pixels in hyperspectral images into different classes based on their spectral signature. Hyperspectral images contain information about the reflectance of objects in hundreds of narrow, contiguous wavelength bands, making them useful for a wide range of applications, including mineral mapping, vegetation analysis, and urban land-use mapping. The goal of this task is to accurately identify and classify different types of objects in the image, such as soil, vegetation, water, and buildings, based on their spectral properties.

The archive carries no text for this table; the description above is the archive's text for the task Hyperspectral Image Classification. archive 2025-07-28

Over time archive 2025-07-28

Metric Extra training data

The chart needs JavaScript; the table below carries every value.

Direction inferred from the metric name, not from the archive: Overall Accuracy (higher is better). Not inferred (points only, no best-so-far line): OA@15perclass, AA@200, Kappa@200, OA@200, AA@5%perclass, Kappa@1%, Kappa@5%perclass, OA@5%perclass, AA@1%perclass, Kappa@1%perclass, OA@1%perclass. Points are placed at the row's paper date; 33 of 33 rows carry one.

Results archive 2025-07-28

Archive rows end at the archive snapshot, 2025-07-28: no result published after that date is in this table. Rank is the archive's row order at that snapshot; not re-ranked here. Metric values are the archive's strings. Column headers sort the table in your browser; each row keeps its archive rank.

															Paper	Code		Ran Syntology	Report
1	RPNet-RF	95.60												–	Paper	Code	2023	linked, not harvested	report
2	TC-GAN	93.20±0.59												–	Paper	–	2022	no code linked	report
3	HyLITE	91.28												–	Paper	Code	2023	linked, not harvested	report
4	DCFSL	90.71±0.56												–	Paper	Code	2022	linked, not harvested	report
5	IFRF	88.38												–	Paper	–	2013	no code linked	report
6	S-DMM	88.30±1.03												–	Paper	Code	2019	linked, not harvested	report
7	RPNet	84.92												–	Paper	Code	2018	linked, not harvested	report
8	3D VS-CNN	81.63±1.81												–	Paper	–	2020	no code linked	report
9	2D-CNN	77.53±1.50												–	Paper	Code	2015	linked, not harvested	report
10	CA-GAN	76.81±0.91												–	Paper	–	2020	no code linked	report
11	HSI-BERT	75.31±1.59												–	Paper	–	2019	no code linked	report
12	3D-CNN	75.24±0.84												–	Paper	Code	2017	linked, not harvested	report
13	JigsawHSI		100.00											–	Paper	Code	2022	linked, not harvested	report
14	STNet		100											–	Paper	Code	2025	linked, not harvested	report
15	WCNet		100											–	Paper	Code	2025	linked, not harvested	report
16	SpectralNET		99.99%											–	Paper	Code	2021	linked, not harvested	report
17	Deep Matrix Capsules		99.99%											–	Paper	Code	2023	linked, not harvested	report
18	KANet		99.99											–	Paper	Code	2025	linked, not harvested	report
19	SGDSCNet		99.99											–	Paper	Code	2025	linked, not harvested	report
20	MVNet		99.98											–	Paper	Code	2025	linked, not harvested	report
21	EKGNet		99.98											–	Paper	Code	2025	linked, not harvested	report
22	SSDGL		99.97%					0.9996						–	Paper	Code	2021	linked, not harvested	report
23	FSKNet		99.96%											–	Paper	Code	2022	linked, not harvested	report
24	A2S2K-ResNet		99.85											–	Paper	Code	2020	linked, not harvested	report
25	FPGA		99.81%	99.83	0.9974	99.81								–	Paper	Code	2020	linked, not harvested	report
26	CVSSN		99.68±0.06%				99.52±0.17%		0.9957±0.0009	99.68±0.06%				–	Paper	Code	2022	linked, not harvested	report
27	A-SPN		99.65%											–	Paper	Code	2021	linked, not harvested	report
28	WCRN		99.43%											–	Paper	Code	2018	linked, not harvested	report
29	St-SS-pGRU		98.44%											–	Paper	Code	2018	linked, not harvested	report
30	AMS-M2ESL		98.09±0.30%								97.86±0.47%	0.9747±0.0039	98.09±0.30%	–	Paper	Code	2023	linked, not harvested	report
31	BASSNet		97.48%											–	Paper	Code	2016	linked, not harvested	report
32	DeepHyperX 3D CNN		96.71											–	Paper	Code	2019	linked, not harvested	report
33	CNN-MRF		96.18											–	Paper	Code	2017	linked, not harvested	report

All 33 rows shown. 33 link to a paper page on this site; 0 are marked as using additional training data in the archive. No GitHub stars are tracked; "Code" is the first repository the archive lists for the row. The archive carries no row tags, review links or community-submitted rows for this table; none are shown. archive 2025-07-28

Syntology Ran reads "N of M ran · U unverified": of the M code samples Syntology harvested from repositories linked to that row's paper (joined by arXiv id), N executed on a synthesized input and the other U = M−N are unverified (harvested, no recorded run). It counts code from repositories linked to that row's paper, not this result: the row's number was not reproduced and nothing here is a correctness claim. The other cell texts mean no graph line for the row: "linked, not harvested" (the archive links code, Syntology has not harvested it), "no code linked" (no code link in the archive), "not matched" (the row's paper URL matched no paper on this site). 0 rows have a graph line, from 0 distinct papers; 0 rows (0 papers) have at least one sample that ran. Counting each paper once: Syntology ran 0 of 0 samples; 0 unverified. Separately, 0 of those 0 are pointer-only (licence): the site points at that code rather than redistributing it, a licence property recorded for ran and unverified samples alike; each cell's tooltip carries the row's own pointer-only count. Read from the graph 2026-09-24. Per-sample status is on the paper page.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections