Papers with Code 아카이브

Instance Segmentation

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법 전체 데이터셋

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/facebookresearch/mvit

공식 코드

MViTv2: Improved Multiscale Vision Transformers for Classification and Detection

https://github.com/facebookresearch/video-nonlocal-net

공식 코드

Non-local Neural Networks

https://github.com/facebookresearch/xcit

공식 코드

XCiT: Cross-Covariance Image Transformers

https://github.com/fanghaook/ovformer

공식 코드

Unified Embedding Alignment for Open-Vocabulary Video Instance Segmentation

https://github.com/fangyanwen1106/RLANet

공식 코드

Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregation

https://github.com/fanq15/FewX

공식 코드

Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation

https://github.com/farnooshar/eigenclustervis

공식 코드

Improving Weakly-supervised Video Instance Segmentation by Leveraging Spatio-temporal Consistency

https://github.com/farnooshar/specuniis

공식 코드

Deep Spectral Improvement for Unsupervised Image Instance Segmentation

https://github.com/farnooshar/specunvis

공식 코드

Deep Spectral Improvement for Unsupervised Image Instance Segmentation

https://github.com/fawnliu/tris

공식 코드

Referring Image Segmentation Using Text Supervision

https://github.com/fcdl94/mma

공식 코드

Modeling Missing Annotations for Incremental Learning in Object Detection

https://github.com/fcjian/loce

공식 코드

Exploring Classification Equilibrium in Long-Tailed Object Detection

https://github.com/felixcaae/crowdsam

공식 코드

Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes

https://github.com/fh2019ustc/polysnake

공식 코드

Recurrent Generic Contour-based Instance Segmentation with Progressive Learning

https://github.com/fieldsoftheworld/ftw-baselines

공식 코드

Fields of The World: A Machine Learning Benchmark Dataset For Global Agricultural Field Boundary Segmentation

https://github.com/fistyee/mixpro

공식 코드

MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer

https://github.com/fiveai/MoCaE

공식 코드

MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection

https://github.com/fmi-basel/RDCNet

공식 코드

RDCNet: Instance segmentation with a minimalist recurrent residual network

https://github.com/foundationvision/uniref

공식 코드

UniRef++: Segment Every Reference Object in Spatial and Temporal Spaces

https://github.com/fpthink/3d-wsis

공식 코드

Learning Inter-Superpoint Affinity for Weakly Supervised 3D Instance Segmentation

https://github.com/frank-xwang/InstanceDiffusion

공식 코드

InstanceDiffusion: Instance-level Control for Image Generation

https://github.com/fraunhoferhhi/soloplanes

공식 코드

Multi-task Planar Reconstruction with Feature Warping Guidance

https://github.com/fudan-zvg/SETR

공식 코드

Vision Transformers: From Semantic Segmentation to Dense Prediction

https://github.com/funkelab/cellulus

공식 코드

Unsupervised Learning of Object-Centric Embeddings for Cell Instance Segmentation in Microscopy Images

https://github.com/g-meghana-reddy/open-world-panoptic-segmentation

공식 코드

Lidar Panoptic Segmentation in an Open World

https://github.com/gabrielhuang/awesome-few-shot-object-detection

공식 코드

A Survey of Self-Supervised and Few-Shot Object Detection

https://github.com/ganlab/ostra

공식 코드

A One Stop 3D Target Reconstruction and multilevel Segmentation Method

https://github.com/gaopengcuhk/Container

공식 코드

Container: Context Aggregation Network

https://github.com/geoaigroup/geoai-ecrs2023

공식 코드

Zero-Shot Refinement of Buildings' Segmentation Models using SAM

https://github.com/georgeretsi/mushroom-pose

공식 코드

Mushroom Segmentation and 3D Pose Estimation from Point Clouds using Fully Convolutional Geometric Features and Implicit Pose Encoding

https://github.com/gfz/weedsgalore

공식 코드

WeedsGalore: A Multispectral and Multitemporal UAV-based Dataset for Crop and Weed Segmentation in Agricultural Maize Fields

https://github.com/giakoumoglou/synco

공식 코드

SynCo: Synthetic Hard Negatives in Contrastive Learning for Better Unsupervised Visual Representations

https://github.com/giddyyupp/coco-minitrain

공식 코드

HoughNet: Integrating near and long-range evidence for visual detection

https://github.com/gist-ailab/Food-Instance-Segmentation

공식 코드

Deep Learning based Food Instance Segmentation using Synthetic Data

https://github.com/gist-ailab/QuBER

공식 코드

High-Quality Unknown Object Instance Segmentation via Quadruple Boundary Error Refinement

https://github.com/gist-ailab/SF-Mask-RCNN

공식 코드

Segmenting Unseen Industrial Components in a Heavy Clutter Using RGB-D Fusion and Synthetic Data

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.