https://github.com/wvangansbeke/Revisiting-Contrastive-SSL
공식 코드Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Instance Segmentation is a computer vision task that involves identifying and separating individual objects within an image, including detecting the boundaries of each object and assigning a unique label to each object. The goal of instance segmentation is to produce a pixel-wise segmentation map of the image, where each pixel is assigned to a specific object instance.
Image Credit: Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers, CVPR'21
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations
Affinity Derivation and Graph Merge for Instance Segmentation
PolarMask: Single Shot Instance Segmentation with Polar Representation
GCNet: Non-local Networks Meet Squeeze-Excitation Networks and Beyond
FPCC: Fast Point Cloud Clustering based Instance Segmentation for Industrial Bin-picking
SCD: A Stacked Carton Dataset for Detection and Segmentation
BoxSnake: Polygonal Instance Segmentation with Box Supervision
H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detection
H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detection
Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion
Learning to Aggregate Multi-Scale Context for Instance Segmentation in Remote Sensing Images
EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything
Amodal Segmentation through Out-of-Task and Out-of-Distribution Generalization with a Bayesian Model
MOD-UV: Learning Mobile Object Detectors from Unlabeled Videos
Multi-scale Cell Instance Segmentation with Keypoint Graph based Bounding Boxes
Object-Guided Instance Segmentation With Auxiliary Feature Refinement for Biological Images
EmbedMask: Embedding Coupling for One-stage Instance Segmentation
ISDA: Position-Aware Instance Segmentation with Deformable Attention
Strong Instance Segmentation Pipeline for MMSports Challenge
X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion
Universal Segmentation at Arbitrary Granularity with Language Instruction
torchdistill: A Modular, Configuration-Driven Framework for Knowledge Distillation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.