https://github.com/keyu-tian/spark
공식 코드Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling
G-CAME: Gaussian-Class Activation Mapping Explainer for Object Detectors
FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision
Physics-Informed Ensemble Representation for Light-Field Image Super-Resolution
Dual Mutual Learning Network with Global-local Awareness for RGB-D Salient Object Detection
Machine vision for vial positioning detection toward the safe automation of material synthesis
VCISR: Blind Single Image Super-Resolution with Video Compression Synthetic Data
RFUAV: A Benchmark Dataset for Unmanned Aerial Vehicle Detection and Identification
MEVID: Multi-view Extended Videos with Identities for Video Person Re-Identification
Online Continual Learning: A Systematic Literature Review of Approaches, Challenges, and Benchmarks
M2-Net: Multi-stages Specular Highlight Detection and Removal in Multi-scenes
Probabilistic Anchor Assignment with IoU Prediction for Object Detection
Efficient Frequency Domain-based Transformers for High-Quality Image Deblurring
MSSNet: Multi-Scale-Stage Network for Single Image Deblurring
Rethinking Centered Kernel Alignment in Knowledge Distillation
Hyperspectral Image Super-Resolution with Spectral Mixup and Heterogeneous Datasets
Improving Video Instance Segmentation by Light-weight Temporal Uncertainty Estimates
Understanding Gaussian Attention Bias of Vision Transformers Using Effective Receptive Fields
Probing Multimodal Large Language Models for Global and Local Semantic Representations
ImaginaryNet: Learning Object Detectors without Real Images and Annotations
Fine-Grained Pillar Feature Encoding Via Spatio-Temporal Virtual Grid for 3D Object Detection
Tackling Clutter in Radar Data -- Label Generation and Detection Using PointNet++
HMANet: Hybrid Multi-Axis Aggregation Network for Image Super-Resolution
Towards Open-World Object-based Anomaly Detection via Self-Supervised Outlier Synthesis
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.