https://github.com/martin-bayon/tednet
공식 코드TEDNet: Twin Encoder Decoder Neural Network for 2D Camera and LiDAR Road Detection
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
TEDNet: Twin Encoder Decoder Neural Network for 2D Camera and LiDAR Road Detection
Scene relighting with illumination estimation in the latent space on an encoder-decoder scheme
Automatic Foot Ulcer Segmentation Using an Ensemble of Convolutional Neural Networks
CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation
SAR-UNet: Small Attention Residual UNet for Explainable Nowcasting Tasks
Adjacent Context Coordination Network for Salient Object Detection in Optical Remote Sensing Images
RGB-T Semantic Segmentation with Location, Activation, and Sharpening
Multi-Content Complementation Network for Salient Object Detection in Optical Remote Sensing Images
Texture-Semantic Collaboration Network for ORSI Salient Object Detection
Differentiable Phylogenetics via Hyperbolic Embeddings with Dodonaphy
VDSM: Unsupervised Video Disentanglement with State-Space Modeling and Deep Mixtures of Experts
TTA-Nav: Test-time Adaptive Reconstruction for Point-Goal Navigation under Visual Corruptions
LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions
Efficient Video Action Detection with Token Dropout and Context Refinement
p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay
StageInteractor: Query-based Object Detector with Cross-stage Interaction
The Impact of Positional Encoding on Length Generalization in Transformers
LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
Wavelet-based Mamba with Fourier Adjustment for Low-light Image Enhancement
Long Movie Clip Classification with State-Space Video Models
Adversarial robustness of VAEs through the lens of local geometry
Deep Optimized Multiple Description Image Coding via Scalar Quantization Learning
Multi-scale Self-calibrated Network for Image Light Source Transfer
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.