https://github.com/zhichenghuang/cmae
공식 코드Contrastive Masked Autoencoders are Stronger Vision Learners
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Contrastive Masked Autoencoders are Stronger Vision Learners
Toward Realistic Camouflaged Object Detection: Benchmarks and Method
Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models
Point Cloud Self-supervised Learning via 3D to Multi-view Masked Autoencoder
GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement
Bayesian Detector Combination for Object Detection with Crowdsourced Annotations
Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination
Deep Omni-supervised Learning for Rib Fracture Detection from Chest Radiology Images
Learning Series-Parallel Lookup Tables for Efficient Image Super-Resolution
RIS-GAN: Explore Residual and Illumination with Generative Adversarial Networks for Shadow Removal
Rethinking Bottleneck Structure for Efficient Mobile Network Design
Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers
AMSP-UOD: When Vortex Convolution and Stochastic Perturbation Meet Underwater Object Detection
Efficient Image Super-Resolution using Vast-Receptive-Field Attention
SOGDet: Semantic-Occupancy Guided Multi-view 3D Object Detection
When SAM2 Meets Video Camouflaged Object Segmentation: A Comprehensive Evaluation and Adaptation
Resonant Scanning Design and Control for Fast Spatial Sampling
CPM R-CNN: Calibrating Point-guided Misalignment in Object Detection
Enhancing Fine-grained Object Detection in Aerial Images via Orthogonal Mapping
M3CAD: Towards Generic Cooperative Autonomous Driving Benchmark
FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding
MOS: Model Synergy for Test-Time Adaptation on LiDAR-Based 3D Object Detection
Simulate Any Radar: Attribute-Controllable Radar Simulation via Waveform Parameter Embedding
Mitigating Hallucinations in Large Vision-Language Models via DPO: On-Policy Data Hold the Key
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.