Global Leaderboard Ranking (Indian Pines)

์—˜๋กœ์ด๋žฉ์˜ Hyperspectral Image Classification์€ ๊ธฐ์กด ๊ธ€๋กœ๋ฒŒ(SOTA) ๊ธฐ๋ก์„ ๊ฒฝ์‹ ํ•˜๋ฉฐ 1์œ„์— ๋“ฑ์žฌ๋˜์—ˆ์Šต๋‹ˆ๋‹ค. ELROILABโ€™s Hyperspectral Image Classification has achieved the top rank (1st place) by surpassing existing global State-of-the-Art (SOTA) records.

Rank Model Name Accuracy Organization Status
๐Ÿฅ‡ 1st SC-DBNET(ELROILAB) 97.84% ELROILAB Current SOTA
๐Ÿฅˆ 2nd PRNET-RF 90.23% Academic (Ref.) -
๐Ÿฅ‰ 3rd HYLITE 89.80% Academic (Ref.) -

ELROILAB: SOTA #1 Ranking in Hyperspectral Image Classification

[SOTA #1 Ranking] Indian Pines Hyperspectral Classification

SOTA Badge Accuracy Badge hyperspectral image classification

ELROILAB: Hyperspectral Image Classification Ranked 1st(SOTA) on Indian Pines Benchmark

License Notice: ๋ณธ ๋ชจ๋ธ์˜ ์†Œ์œ ๊ถŒ์€ (์ฃผ)์—˜๋กœ์ด๋žฉ์— ์žˆ์œผ๋ฉฐ, ์ƒ์—…์  ์ด์šฉ ๋ฐ ๋ฌด๋‹จ ๋ฐฐํฌ๋ฅผ ๊ธˆํ•ฉ๋‹ˆ๋‹ค. (The ownership of this model belongs to ELROILAB Co., Ltd. Commercial use and unauthorized distribution are strictly prohibited.) (Proprietary License)

[KOREAN]

์—˜๋กœ์ด๋žฉ(ELROILAB)์€ ๋น„์ •ํ˜• ์ด๋ฌผ์„ ๊ฒ€์ถœํ•˜๋Š” AI ์ดˆ๋ถ„๊ด‘(AI Hyperspectral) ์›์ฒœ ๊ธฐ์ˆ ์„ ๋ณด์œ ํ•˜๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค. ๋ณธ ๋ชจ๋ธ ์นด๋“œ๋Š” ์—˜๋กœ์ด๋žฉ ์ž์ฒด ๊ฒ€์ฆ ๋ฐ์ดํ„ฐ๋ฅผ ๊ธฐ๋ฐ˜์œผ๋กœ ํ•œ ์„ฑ๋Šฅ ์ง€ํ‘œ๋ฅผ ๋‹ด๊ณ  ์žˆ์Šต๋‹ˆ๋‹ค.

ํ•ต์‹ฌ ์„ฑ๋Šฅ (Performance)

์—˜๋กœ์ด๋žฉ, ์ž์‚ฌ ์ดˆ๋ถ„๊ด‘ ์ด๋ฏธ์ง€ ๋ถ„๋ฅ˜๋ชจ๋ธ "SC-DBNET: AN EFFICIENT SPECTRAL-CONDITIONED DUAL-BRANCH NET FOR HSI CLASSIFICATION" ์„ธ๊ณ„ ์ตœ๊ณ ๊ถŒ์œ„์˜ ์ง€๊ตฌ๊ณผํ•™ ๋ฐ ์›๊ฒฉ ํƒ์‚ฌ ํ•™์ˆ  ๋Œ€ํšŒ IGARSS 2026์— ์ตœ์ข… ์ฑ„ํƒ ๋˜์—ˆ์Šต๋‹ˆ๋‹ค. ๊ธ€๋กœ๋ฒŒ AI ํ—ˆ๋ธŒ์ธ Hugging Face์˜ ๊ณต์‹ ๊ทœ๊ฒฉ์— ๋”ฐ๋ผ ๋“ฑ์žฌ๋œ ์—˜๋กœ์ด๋žฉ์˜ ์ž์ฒด ๊ฒ€์ฆ ๊ฒฐ๊ณผ์ž…๋‹ˆ๋‹ค.

  • ์ฃผ์š” ์ˆ˜์น˜: Hyperspectral Image Classification 97.84%(Overall Accuracy ๊ธฐ์ค€), SOTA Ranking 1์œ„ ๋‹ฌ์„ฑ
  • ๊ฒ€์ฆ ๊ธฐ์ค€: Indian Pines (์ธ๋””์–ธ ํŒŒ์ธ์ฆˆ) ๋ฐ์ดํ„ฐ์…‹ ๊ธฐ์ค€ ํ‘œ์ค€์‹œํ—˜ ๋ฒค์น˜๋งˆํฌ

๊ธฐ์ˆ ์  ์ฐจ๋ณ„์  (SOTA Evidence)

์—˜๋กœ์ด๋žฉ์˜ AI๋Š” "๋ฌผ์งˆ ๊ณ ์œ ์˜ ๋ถ„๊ด‘ ํŠน์„ฑ(Spectral Signature)์„ ์ฝ๋Š” ์ดˆ๋ถ„๊ด‘(Hyperspectral)"์„ ๋ถ„์„ํ•˜์—ฌ 97.84%(์„ธ๊ณ„์ตœ๊ณ ์ˆ˜์ค€) ์ดˆ๋ถ„๊ด‘ ์ด๋ฏธ์ง€ ๋ถ„๋ฅ˜ ์„ฑ๋Šฅ์„ ๋ณด์—ฌ์ค๋‹ˆ๋‹ค.

[ENGLISH]

ELROILAB holds proprietary AI Hyperspectral technology capable of detecting irregular foreign objects. This Model Card contains performance metrics based on ELROILABโ€™s internal validation data.

Key Performance

ELROILABโ€™s proprietary hyperspectral image classification model, "SC-DBNet: An Efficient Spectral-Conditioned Dual-Branch Net for HSI Classification," has been officially accepted for IGARSS 2026, the worldโ€™s most prestigious conference in geoscience and remote sensing. The following performance indicators have been officially registered on Hugging Face, the global AI hub, in accordance with its standard specifications.

  • Primary Metric: 97.84% (Overall Accuracy) in Hyperspectral Image Classification, Achieved 1st Place in SOTA Rankings
  • Benchmark: Standard test performed on the Indian Pines dataset

Technical Differentiation (SOTA Evidence)

ELROILABโ€™s AI analyzes "Spectral Signatures," the unique material properties captured through hyperspectral imaging, delivering world-class classification performance with an accuracy of 97.84%.


[๋น„์ฆˆ๋‹ˆ์Šค ๋ฌธ์˜ ๋ฐ ์ƒ์„ธ ๋ฆฌํฌํŠธ ์š”์ฒญ, INQUIRY & REPORT REQUEST]

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Evaluation results