https://github.com/VSainteuf/utae-paps
공식 코드Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Flood extent forecasting is the task of predicting a binary 2D flood extent map (water vs no water), given input drivers and forcings. The focus is specifically on the impact and extent modeling, such that e.g. atmosphere state (such as precipitation) may be assumed as inputs, to disentangle the impact modeling from upstream challenges such as weather forecasting. This is complementary to time series forecasting of river streamflow and runoff, as well as post-hoc mapping of floods. For related work, data & benchmarks, see https://arxiv.org/abs/2409.18591.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Panoptic Segmentation of Satellite Image Time Series with Convolutional Temporal Attention Networks
MaxViT-UNet: Multi-Axis Attention for Medical Image Segmentation
Off to new Shores: A Dataset & Benchmark for (near-)coastal Flood Inundation Forecasting
MaxViT-UNet: Multi-Axis Attention for Medical Image Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.