https://github.com/tobiasriedlinger/gradient-metrics-od
공식 코드Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Gradient-Based Quantification of Epistemic Uncertainty for Deep Object Detectors
Multiscale style transfer based on a Laplacian pyramid for traditional Chinese painting
A benchmark dataset for deep learning-based airplane detection: HRPlanes
Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks
Spatial and Frequency Domain Adaptive Fusion Network for Image Deblurring
Image Restoration by Iterative Denoising and Backward Projections
Multi-Class Cell Detection Using Spatial Context Representation
Large Scale Radio Frequency Wideband Signal Detection & Recognition
Evaluating Supervision Levels Trade-Offs for Infrared-Based People Counting
Spectral Tensor Train Parameterization of Deep Learning Layers
Lightweight LiDAR-Camera 3D Dynamic Object Detection and Multi-Class Trajectory Prediction
Lightweight LiDAR-Camera 3D Dynamic Object Detection and Multi-Class Trajectory Prediction
StyleDyRF: Zero-shot 4D Style Transfer for Dynamic Neural Radiance Fields
DatasetEquity: Are All Samples Created Equal? In The Quest For Equity Within Datasets
A Look Into News Avoidance Through AWRS: An Avoidance-Aware Recommender System
YCB-LUMA: YCB Object Dataset with Luminance Keying for Object Localization
Beyond Classification: Definition and Density-based Estimation of Calibration in Object Detection
Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection
Gradient-based Maximally Interfered Retrieval for Domain Incremental 3D Object Detection
HyperMODEST: Self-Supervised 3D Object Detection with Confidence Score Filtering
UncertaintyTrack: Exploiting Detection and Localization Uncertainty in Multi-Object Tracking
Robustness Enhancement of Object Detection in Advanced Driver Assistance Systems (ADAS)
A Novel Encoder-Decoder Network with Guided Transmission Map for Single Image Dehazing
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.