https://github.com/youngsean/nids-net
공식 코드Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation
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.
Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation
Mean Shift Mask Transformer for Unseen Object Instance Segmentation
Exploring The Role of Mean Teachers in Self-supervised Masked Auto-Encoders
SHViT: Single-Head Vision Transformer with Memory Efficient Macro Design
FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation
Regularized Densely-connected Pyramid Network for Salient Instance Segmentation
Spherical Mask: Coarse-to-Fine 3D Point Cloud Instance Segmentation with Spherical Representation
Surgical-DeSAM: Decoupling SAM for Instrument Segmentation in Robotic Surgery
LAVT: Language-Aware Vision Transformer for Referring Image Segmentation
Rapid Automated Mapping of Clouds on Titan With Instance Segmentation
Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation
Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts
Instance As Identity: A Generic Online Paradigm for Video Instance Segmentation
DVIS++: Improved Decoupled Framework for Universal Video Segmentation
E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation
A Feasible Framework for Arbitrary-Shaped Scene Text Recognition
RefineMask: Towards High-Quality Instance Segmentation with Fine-Grained Features
CEDNet: A Cascade Encoder-Decoder Network for Dense Prediction
CEDNet: A Cascade Encoder-Decoder Network for Dense Prediction
OpenMaskDINO3D : Reasoning 3D Segmentation via Large Language Model
Boundary-aware Contrastive Learning for Semi-supervised Nuclei Instance Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.