Papers with Code 아카이브
Instance Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 17
- 평가표
- 36
- 보존된 평가 기록
- 338
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
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/malidib/Craters_MaskRCNN
공식 코드Automated crater shape retrieval using weakly-supervised deep learning
https://github.com/markusschoen/rt-k-net
공식 코드RT-K-Net: Revisiting K-Net for Real-Time Panoptic Segmentation
https://github.com/martinruenz/co-fusion
공식 코드Co-Fusion: Real-time Segmentation, Tracking and Fusion of Multiple Objects
https://github.com/masih4/CryoNuSeg
공식 코드https://github.com/masih4/nuinsseg
공식 코드https://github.com/masqm/Faster-Mean-Shift
공식 코드https://github.com/matjesg/deepflash2
공식 코드Deep-learning in the bioimaging wild: Handling ambiguous data with deepflash2
https://github.com/maudzung/SFA3D
공식 코드https://github.com/maycbj/dit
공식 코드DiT: Efficient Vision Transformers with Dynamic Token Routing
https://github.com/mbzuai-oryx/groundingLMM
공식 코드https://github.com/mc-lan/text4seg
공식 코드https://github.com/mcahny/vps
공식 코드https://github.com/megvii-research/LGD
공식 코드https://github.com/megvii-research/SOLQ
공식 코드https://github.com/megvii-research/pcb
공식 코드Relieving Long-tailed Instance Segmentation via Pairwise Class Balance
https://github.com/megvii-research/us3l-cvpr2023
공식 코드Three Guidelines You Should Know for Universally Slimmable Self-Supervised Learning
https://github.com/meidachen/STPLS3D
공식 코드STPLS3D: A Large-Scale Synthetic and Real Aerial Photogrammetry 3D Point Cloud Dataset
https://github.com/mellody11/less
공식 코드LESS: Label-Efficient and Single-Stage Referring 3D Segmentation
https://github.com/mengyuwang826/segrefiner
공식 코드SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process
https://github.com/merlresearch/radar-detection-transformer
공식 코드RETR: Multi-View Radar Detection Transformer for Indoor Perception
https://github.com/mgendarme/brifiseg
공식 코드https://github.com/mic-dkfz/particleseg3d
공식 코드https://github.com/michaelwwan/noise
공식 코드NOISe: Nuclei-Aware Osteoclast Instance Segmentation for Mouse-to-Human Domain Transfer
https://github.com/mickaelChen/ReDO
공식 코드https://github.com/microsoft/Focal-Transformer
공식 코드Focal Self-attention for Local-Global Interactions in Vision Transformers
https://github.com/microsoft/GLIP
공식 코드GLIPv2: Unifying Localization and Vision-Language Understanding
https://github.com/microsoft/SoftTeacher
공식 코드End-to-End Semi-Supervised Object Detection with Soft Teacher
https://github.com/microsoft/Swin-Transformer
공식 코드Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
https://github.com/microsoft/X-Decoder
공식 코드https://github.com/microsoft/activemlp
공식 코드https://github.com/microsoft/transductive-vos.pytorch
공식 코드https://github.com/microsoft/unilm/tree/master/beit
공식 코드Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks
https://github.com/microsoft/vision-longformer
공식 코드Multi-Scale Vision Longformer: A New Vision Transformer for High-Resolution Image Encoding
https://github.com/miguelag99/efficient-instance-prediction
공식 코드Fast and Efficient Transformer-based Method for Bird's Eye View Instance Prediction
https://github.com/mihirp1998/Slot-TTA
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.