paper-with-me

Papers

Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation

2022-03-21 · CVPR 2022 1 · Zhiyuan Liang, Tiancai Wang, Xiangyu Zhang, Jian Sun, Jianbing Shen

Sparsely annotated semantic segmentation (SASS) aims to train a segmentation network with coarse-grained (i.e., point-, scribble-, and block-wise) supervisions, where only a small proportion of pixels are labeled in each image. In this paper, we propose a novel tree energy loss for SASS by providing semantic guidance for unlabeled pixels. The tree energy loss represents images as minimum spanning trees to model both low-level and high-level pair-wise affinities. By sequentially applying these affinities to the network prediction, soft pseudo labels for unlabeled pixels are generated in a coarse-to-fine manner, achieving dynamic online self-training. The tree energy loss is effective and easy to be incorporated into existing frameworks by combining it with a traditional segmentation loss. Compared with previous SASS methods, our method requires no multistage training strategies, alternating optimization procedures, additional supervised data, or time-consuming post-processing while outperforming them in all SASS settings. Code is available at https://github.com/megvii-research/TreeEnergyLoss.

📄 PDF Abstract BibTeX arXiv:2203.10739

Code (1)

megvii-research/treeenergyloss 공식 구현 pytorch

Tasks

SegmentationSemantic Segmentation

Similar Papers 제목 키워드 기반

Tree-based Semantic Losses: Application to Sparsely-supervised Large Multi-class Hyperspectral Segmentation

2025-06-26 · Junwen Wang, Oscar MacCormac, William Rochford, Aaron Kujawa 외

Hyperspectral imaging (HSI) shows great promise for surgical applications, offering detailed insights into biological tissue differences beyond what the naked eye can perceive. Refined labelling efforts are underway to t…

Co-mining: Self-Supervised Learning for Sparsely Annotated Object Detection

2020-12-03 · Tiancai Wang, Tong Yang, Jiale Cao, Xiangyu Zhang

Object detectors usually achieve promising results with the supervision of complete instance annotations. However, their performance is far from satisfactory with sparse instance annotations. Most existing methods for sp…

MULTI-VIEW LEARNINGObjectobject-detectionObject Detection+2

LLM-Assisted Semantic Guidance for Sparsely Annotated Remote Sensing Object Detection

2025-09-21 · Wei Liao, Chunyan Xu, Chenxu Wang, Zhen Cui arxiv

Sparse annotation in remote sensing object detection poses significant challenges due to dense object distributions and category imbalances. Although existing Dense Pseudo-Label methods have demonstrated substantial pote…

Object Detection

SASFormer: Transformers for Sparsely Annotated Semantic Segmentation

2022-12-05 · Hui Su, Yue Ye, Wei Hua, Lechao Cheng 외

Semantic segmentation based on sparse annotation has advanced in recent years. It labels only part of each object in the image, leaving the remainder unlabeled. Most of the existing approaches are time-consuming and ofte…

SegmentationSemantic SegmentationvalidWeakly supervised Semantic Segmentation

Semantic Segmentation of Neuronal Bodies in Fluorescence Microscopy Using a 2D+3D CNN Training Strategy with Sparsely Annotated Data

2020-08-31 · Filippo Maria Castelli, Matteo Roffilli, Giacomo Mazzamuto, Irene Costantini 외

Semantic segmentation of neuronal structures in 3D high-resolution fluorescence microscopy imaging of the human brain cortex can take advantage of bidimensional CNNs, which yield good results in neuron localization but l…

Missing LabelsSemantic SegmentationSurface Reconstruction