https://github.com/zengyan-97/x-vlm
공식 코드Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts
DARDet: A Dense Anchor-free Rotated Object Detector in Aerial Images
Discriminative Semantic Feature Pyramid Network with Guided Anchoring for Logo Detection
COMICS: End-to-end Bi-grained Contrastive Learning for Multi-face Forgery Detection
CEDNet: A Cascade Encoder-Decoder Network for Dense Prediction
CEDNet: A Cascade Encoder-Decoder Network for Dense Prediction
HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds
CircleFormer: Circular Nuclei Detection in Whole Slide Images with Circle Queries and Attention
Adaptive Visual Scene Understanding: Incremental Scene Graph Generation
Hierarchical Few-Shot Object Detection: Problem, Benchmark and Method
Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features
FreeAnchor: Learning to Match Anchors for Visual Object Detection
Objects are Different: Flexible Monocular 3D Object Detection
BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving
Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy
Learning Feature Inversion for Multi-class Anomaly Detection under General-purpose COCO-AD Benchmark
Cascade R-CNN: High Quality Object Detection and Instance Segmentation
A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection
Motion-aware Memory Network for Fast Video Salient Object Detection
SpecDETR: A Transformer-based Hyperspectral Point Object Detection Network
CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion
RSAR: Restricted State Angle Resolver and Rotated SAR Benchmark
Recurrent Glimpse-based Decoder for Detection with Transformer
FADE: A Dataset for Detecting Falling Objects around Buildings in Video
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.