https://github.com/dvlab-research/VisionReasoner
공식 코드VisionReasoner: Unified Visual Perception and Reasoning via Reinforcement Learning
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/dvlab-research/dsig
공식 코드Deep Structured Instance Graph for Distilling Object Detectors
https://github.com/dvlab-research/mask-attention-free-transformer
공식 코드Mask-Attention-Free Transformer for 3D Instance Segmentation
https://github.com/dvlab-research/proposereduce
공식 코드https://github.com/dylanauty/mde-biological-vision-systems
공식 코드Monocular Depth Estimation Using Cues Inspired by Biological Vision Systems
https://github.com/easton-cau/LeafMask
공식 코드https://github.com/easton-cau/SOTR
공식 코드https://github.com/ecker-lab/treelearn
공식 코드https://github.com/eddy6081/pen
공식 코드https://github.com/eden500/Noisy-Labels-Instance-Segmentation
공식 코드Benchmarking Label Noise in Instance Segmentation: Spatial Noise Matters
https://github.com/edm-research/cut-and-splat
공식 코드Cut-and-Splat: Leveraging Gaussian Splatting for Synthetic Data Generation
https://github.com/edwardzhou130/Panoptic-PolarNet
공식 코드Panoptic-PolarNet: Proposal-free LiDAR Point Cloud Panoptic Segmentation
https://github.com/elharroussomar/awesome-panoptic-segmentation
공식 코드https://github.com/emanuelevivoli/awesome-comics-understanding
공식 코드One missing piece in Vision and Language: A Survey on Comics Understanding
https://github.com/ericyi/GSPN
공식 코드GSPN: Generative Shape Proposal Network for 3D Instance Segmentation in Point Cloud
https://github.com/eryixie/planerecnet
공식 코드https://github.com/esa-datalabs/xami-dataset
공식 코드XAMI -- A Benchmark Dataset for Artefact Detection in XMM-Newton Optical Images
https://github.com/esa-datalabs/xami-model
공식 코드XAMI -- A Benchmark Dataset for Artefact Detection in XMM-Newton Optical Images
https://github.com/ethz-asl/autolabel
공식 코드https://github.com/ethz-asl/pvlff
공식 코드https://github.com/eventbasedvision/sevd
공식 코드SEVD: Synthetic Event-based Vision Dataset for Ego and Fixed Traffic Perception
https://github.com/evinpinar/supergb-d
공식 코드SupeRGB-D: Zero-shot Instance Segmentation in Cluttered Indoor Environments
https://github.com/facebookresearch/ContrastiveSceneContexts
공식 코드Exploring Data-Efficient 3D Scene Understanding with Contrastive Scene Contexts
https://github.com/facebookresearch/Generic-Grouping
공식 코드Open-World Instance Segmentation: Exploiting Pseudo Ground Truth From Learned Pairwise Affinity
https://github.com/facebookresearch/Mask2Former
공식 코드Masked-attention Mask Transformer for Universal Image Segmentation
https://github.com/facebookresearch/SlowFast
공식 코드MViTv2: Improved Multiscale Vision Transformers for Classification and Detection
https://github.com/facebookresearch/cutler
공식 코드Cut and Learn for Unsupervised Object Detection and Instance Segmentation
https://github.com/facebookresearch/detectron2
공식 코드https://github.com/facebookresearch/detectron2/tree/main/projects/MViTv2
공식 코드MViTv2: Improved Multiscale Vision Transformers for Classification and Detection
https://github.com/facebookresearch/detectron2/tree/main/projects/ViTDet
공식 코드Exploring Plain Vision Transformer Backbones for Object Detection
https://github.com/facebookresearch/detectron2/tree/master/projects/PointRend
공식 코드https://github.com/facebookresearch/detectron2/tree/master/projects/PointSup
공식 코드https://github.com/facebookresearch/detectron2/tree/master/projects/TensorMask
공식 코드https://github.com/facebookresearch/guideddistillation
공식 코드Guided Distillation for Semi-Supervised Instance Segmentation
https://github.com/facebookresearch/hiera
공식 코드Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles
https://github.com/facebookresearch/maskrcnn-benchmark
공식 코드Is Heuristic Sampling Necessary in Training Deep Object Detectors?
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.