Instance Segmentation

36개 벤치마크 · 논문 2,537편 · 이 태스크의 논문 보기 →

Benchmarks

Most implemented

MMDetection: Open MMLab Detection Toolbox and Benchmark

2019-06-17 · 구현 142개

Swin Transformer: Hierarchical Vision Transformer using Shifted Windows

2021-03-25 · 구현 80개

YOLACT: Real-time Instance Segmentation

2019-04-04 · 구현 48개

Deep High-Resolution Representation Learning for Visual Recognition

2019-08-20 · 구현 42개

Deep High-Resolution Representation Learning for Human Pose Estimation

2019-02-25 · 구현 39개

Papers

GTR: Gated Token Recurrence for Efficient Dense Prediction

2026-09-23 · Zhe Feng, Longfei Liu, Wei Liu, Kai Chen 외 hf

Self-attention-based vision backbones perform well on dense prediction, but the quadratic computational cost of global softmax attention limits their efficiency as image resolution increases. We introduce Gated Token Rec…

Monocular Depth Estimation Instance Segmentation Semantic Segmentation Pose Estimation

Accelerated Decoding of Centroid Positional Encoding for Instance Segmentation

2026-09-15 · Carmelo Scribano, Filippo Muzzini, Nedyalko Prisadnikov, Mohammad Mahdi 외 arxiv

Beyond model inference, the decoding stage, which converts raw network outputs into task-level representations, constitutes a significant portion of the execution cost. Despite its practical impact, prediction decoding h…

Instance Segmentation

Channel-Wise and Token-Aware Post-Training Quantization for Visual State Space Duality

2026-09-15 · Jonghyeon Lim, Changhoon Yim arxiv

State space models (SSMs), particularly Mamba, have emerged as efficient alternatives to attention-based architectures and have been extended to vision through ViM, VMamba, and Visual State Space Duality (VSSD). Yet the …

Semantic Segmentation Instance Segmentation Object Detection

TAPe+ML: A Compact Structured Representation for Multi-Task Computer Vision

2026-09-15 · Sergey Kurinov, Alexey Upatov hf

We present TAPe+ML v3, a compact computer vision system based on TAPe (Theory of Active Perception), a structured representation that encodes relations among perceptual elements before recognition. Instead of operating d…

Instance Segmentation Image Classification Object Localization Object Detection

CedarCypress3D: an annotated UAV-LiDAR dataset of individual trees in planted cedar and cypress forests

2026-08-31 · Katsuto Shimizu, Fumiaki Kitahara, Tomohiro Nishizono, Hideki Saito 외 arxiv

Individual tree measurements derived from Light Detection and Ranging (LiDAR) mounted on Unmanned Aerial Vehicles (UAV) provide valuable information for forest inventory, ecosystem monitoring, and sustainable forest mana…

Instance Segmentation Semantic Segmentation Point Clouds

QCell: Recombining and Aligning Cell Queries for Overlapping Instance Segmentation

2026-08-29 · Yaroslav Prytula, Anton Popov, Dmytro Fishman hf

Instance segmentation of overlapping cells in microscopy remains challenging due to semi-transparent structures that produce weak boundaries and mixed visual evidence in overlap regions. Existing methods address this thr…

Instance Segmentation Cell Segmentation

전체 2,537편 보기 →