๋ณธ๋ฌธ์œผ๋กœ ๊ฑด๋„ˆ๋›ฐ๊ธฐ
buildradar
๋กœ๊ทธ์ธ

keyu-tian/SparK

@keyu-tian

[ICLR'23 Spotlight๐Ÿ”ฅ] ์ปจ๋ณผ๋ฃจ์…˜ ๋„คํŠธ์›Œํฌ ์ตœ์ดˆ์˜ ์„ฑ๊ณต์ ์ธ BERT/MAE ์Šคํƒ€์ผ ์‚ฌ์ „ ํ•™์Šต; "Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling" ๋…ผ๋ฌธ์˜ PyTorch ๊ตฌํ˜„์ฒด

โ†— GitHub์—์„œ ์—ด๊ธฐ
์Šคํƒ€
1,376
ํฌํฌ
85
์–ธ์–ด
Python
๋ผ์ด์„ ์Šค
MIT
๋งˆ์ง€๋ง‰ ํ‘ธ์‹œ
3๋…„ ์ „
Pythondeep-learninginstance-segmentationobject-detectionpytorchself-supervised-learningpretrainingsslbertpre-trained-modelcnnconvolutional-neural-networksmask-rcnniclriclr2023masked-image-modelingmaemasked-autoencoderpretrainconvnetsparse-convolution

๊ด€๋ จ ์ธํ…” (0)

์•„์ง ๊ด€๋ จ ์ธํ…”์ด ์—†์Šต๋‹ˆ๋‹ค

์ด ์ €์žฅ์†Œ๋Š” radar๊ฐ€ ์ถ”์ ํ•˜๋Š” ์–ด๋–ค ์†Œ์Šค์—๋„ ์•„์ง ๋“ฑ์žฅํ•˜์ง€ ์•Š์•˜์Šต๋‹ˆ๋‹ค. ์ˆ˜์ง‘๊ธฐ๋Š” ์˜ˆ์•ฝ์— ๋”ฐ๋ผ ์‹คํ–‰๋ฉ๋‹ˆ๋‹คโ€”โ€”์ด ์ €์žฅ์†Œ๋ฅผ ๋‹ค๋ฃจ๊ฒŒ ๋˜๋ฉด ๋‹ค์‹œ ํ™•์ธํ•˜์„ธ์š”.