Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation from 2D Supervision https://arxiv.org/abs/2303.03361 AutoFocusFormer: Image Segmentation off the Grid https://arxiv.org/abs/2304.12406v1 MP-Former: Mask-Piloted Transformer for Image Segmentation https://arxiv.org/abs/2303.07336 https://github.com/idea-research/mp-former Explicit Visual Prompting for Low-Level Structure Segmentations https://arxiv.org/abs/2303.10883 https://github.com/nifangbaage/explicit-visual-prompt Focused and Collaborative Feedback Integration for Interactive Image Segmentation https://arxiv.org/abs/2303.11880 https://github.com/veizgyauzgyauz/fcfi FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation https://arxiv.org/abs/2303.17225v1 https://github.com/bytedance/FreeSeg Zero-shot Referring Image Segmentation with Global-Local Context Features https://arxiv.org/abs/2303.17811v1 https://github.com/seonghoon-yu/zero-shot-ris Meta Compositional Referring Expression Segmentation https://arxiv.org/abs/2304.04415v1 MED-VT: Multiscale Encoder-Decoder Video Transformer with Application to Object Segmentation https://arxiv.org/abs/2304.05930v1 細(xì)分：3D分割 EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision https://arxiv.org/abs/2303.15440v1 https://github.com/JiahuiLei/EFEM 細(xì)分：全景分割 You Only Segment Once: Towards Real-Time Panoptic Segmentation https://arxiv.org/abs/2303.14651v1 https://github.com/hujiecpp/yoso 細(xì)分：實例分割 DynaMask: Dynamic Mask Selection for Instance Segmentation https://arxiv.org/abs/2303.07868 https://github.com/lslrh/dynamask DoNet: Deep De-overlapping Network for Cytology Instance Segmentation https://arxiv.org/abs/2303.14373v1 https://github.com/DeepDoNet/DoNet FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation https://arxiv.org/abs/2303.08594 https://github.com/junjiehe96/fastinst SIM: Semantic-aware Instance Mask Generation for Box-Supervised Instance Segmentation https://arxiv.org/abs/2303.08578 https://github.com/lslrh/sim Mask-free OVIS: Open-Vocabulary Instance Segmentation without Manual Mask Annotations https://arxiv.org/abs/2303.16891v1 https://github.com/Vibashan/Maskfree-OVIS The Devil is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation https://arxiv.org/abs/2303.15062v1 https://github.com/clovaai/PointWSSIS 細(xì)分：語義分割 IFSeg: Image-free Semantic Segmentation via Vision-Language Model https://arxiv.org/abs/2303.14396v1 https://github.com/alinlab/ifseg Continual Semantic Segmentation with Automatic Memory Sample Selection https://arxiv.org/abs/2304.05015v1 Federated Incremental Semantic Segmentation https://arxiv.org/abs/2304.04620v1 https://github.com/jiahuadong/fiss Delivering Arbitrary-Modal Semantic Segmentation https://arxiv.org/abs/2303.01480 https://github.com/jamycheung/DELIVER Foundation Model Drives Weakly Incremental Learning for Semantic Segmentation https://arxiv.org/pdf/2302.14250.pdf Mask3D: Pre-training 2D Vision Transformers by Learning Masked 3D Priors https://arxiv.org/pdf/2302.14746.pdf Generative Semantic Segmentation https://arxiv.org/abs/2303.11316 https://github.com/fudan-zvg/gss Reliability in Semantic Segmentation: Are We on the Right Track? https://arxiv.org/abs/2303.11298 https://github.com/naver/relis Both Style and Distortion Matter: Dual-Path Unsupervised Domain Adaptation for Panoramic Semantic Segmentation https://arxiv.org/abs/2303.14360v1 Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation https://arxiv.org/abs/2303.11203 https://github.com/l1997i/lim3d Instant Domain Augmentation for LiDAR Semantic Segmentation https://arxiv.org/abs/2303.14378v1 Leveraging Hidden Positives for Unsupervised Semantic Segmentation https://arxiv.org/abs/2303.15014v1 https://github.com/hynnsk/hp Delving into Shape-aware Zero-shot Semantic Segmentation https://arxiv.org/abs/2304.08491v1 https://github.com/liuxinyv/sazs DiGA: Distil to Generalize and then Adapt for Domain Adaptive Semantic Segmentation https://arxiv.org/abs/2304.02222v1 https://github.com/fy-vision/diga Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation https://arxiv.org/pdf/2303.01276.pdf https://github.com/xiaoyao3302/CCVC Token Contrast for Weakly-Supervised Semantic Segmentation https://arxiv.org/pdf/2303.01267.pdf https://github.com/rulixiang/ToCo Novel Class Discovery for 3D Point Cloud Semantic Segmentation https://arxiv.org/abs/2303.11610 https://github.com/luigiriz/nops MSeg3D: Multi-modal 3D Semantic Segmentation for Autonomous Driving https://arxiv.org/abs/2303.08600 https://github.com/jialeli1/lidarseg3d 3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds https://arxiv.org/abs/2304.00690v1 https://github.com/xiaoaoran/semanticstf 細(xì)分：交互式分割 Interactive Segmentation as Gaussian Process Classification https://arxiv.org/pdf/2302.14578