Towards Fine-grained Large Object Segmentation 1st Place Solution to 3D AI Challenge 2020 -- Instance Segmentation Track

2020-09-10 · Zehui Chen, Qiaofei Li, Feng Zhao

This technical report introduces our solutions of Team 'FineGrainedSeg' for Instance Segmentation track in 3D AI Challenge 2020. In order to handle extremely large objects in 3D-FUTURE, we adopt PointRend as our basic framework, which outputs more fine-grained masks compared to HTC and SOLOv2. Our final submission is an ensemble of 5 PointRend models, which achieves the 1st place on both validation and test leaderboards. The code is available at https://github.com/zehuichen123/3DFuture_ins_seg.

📄 PDF Abstract BibTeX arXiv:2009.04650

Code (1)

zehuichen123/3DFuture_ins_seg 공식 구현 pytorch

Tasks

Instance Segmentation Semantic Segmentation

Methods 이 논문이 사용한 방법론

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Feedforward Network A Feedforward Network, or a Multilayer Perceptron (MLP), is a neural network with solely densely connected layers. This is the classic neural network architecture of the…

Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…

1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…

RoIAlign Region of Interest Align, or RoIAlign, is an operation for extracting a small feature map from each RoI in detection and segmentation based tasks. It removes the harsh…

RPN A Region Proposal Network, or RPN, is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained…

FPN 설명 없음

PointRend 설명 없음

PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object Understanding

2018-12-06 · CVPR 2019 6 · Kaichun Mo, Shilin Zhu, Angel X. Chang, Li Yi 외

We present PartNet: a consistent, large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information. Our dataset consists of 573,585 part instances over 26,671 3D models …

3D Instance Segmentation 3D Semantic Segmentation Benchmarking Instance Segmentation+2

Fine-grained Metrics for Point Cloud Semantic Segmentation

2024-07-31 · Zhuheng Lu, Ting Wu, Yuewei Dai, Weiqing Li 외

Two forms of imbalances are commonly observed in point cloud semantic segmentation datasets: (1) category imbalances, where certain objects are more prevalent than others; and (2) size imbalances, where certain objects o…

Point Cloud Segmentation Segmentation Semantic Segmentation

Technical Report for the ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge: Pretraining-Diverse Ensemble of Foundation Vision Encoders for Robust Outdoor Scene Understanding

2026-06-22 · Boyan Wang, Yongxi Huang, Wenjing Li, Tianrui Hui 외 arxiv

This report presents our solution for the ICRA 2026 GOOSE 2D Fine-Grained Semantic Segmentation Challenge, which requires parsing unstructured outdoor scenes from four camera platforms into 56 fine-grained categories. Ou…

Semantic Segmentation Scene Understanding

High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity

2024-10-14 · ICLR 2025 2 · Qian Yu, Peng-Tao Jiang, Hao Zhang, Jinwei Chen 외

In the realm of high-resolution (HR), fine-grained image segmentation, the primary challenge is balancing broad contextual awareness with the precision required for detailed object delineation, capturing intricate detail…

Denoising Dichotomous Image Segmentation Image Generation Image Segmentation+3

Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union

2023-09-26 · NeurIPS 2023 11

Semantic segmentation datasets often exhibit two types of imbalance: \textit{class imbalance}, where some classes appear more frequently than others and \textit{size imbalance}, where some objects occupy more pixels than…