Weakly-Supervised Semantic Segmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 10
- 보존된 평가 기록
- 182
The semantic segmentation task is to assign a label from a label set to each pixel in an image. In the case of fully supervised setting, the dataset consists of images and their corresponding pixel-level class-specific annotations (expensive pixel-level annotations). However, in the weakly-supervised setting, the dataset consists of images and corresponding annotations that are relatively easy to obtain, such as tags/labels of objects present in the image.
<span style="color:grey; opacity: 0.6">( Image credit: Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing )</span>
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Rethinking Class Activation Maps for Segmentation: Revealing Semantic Information in Shallow Layers by Reducing Noise
CG-fusion CAM: Online segmentation of laser-induced damage on large-aperture optics
Prompting classes: Exploring the Power of Prompt Class Learning in Weakly Supervised Semantic Segmentation
AME-CAM: Attentive Multiple-Exit CAM for Weakly Supervised Segmentation on MRI Brain Tumor
A Novel Confidence Induced Class Activation Mapping for MRI Brain Tumor Segmentation
Conditional Diffusion Models for Weakly Supervised Medical Image Segmentation
P-NOC: adversarial training of CAM generating networks for robust weakly supervised semantic segmentation priors
Masked Collaborative Contrast for Weakly Supervised Semantic Segmentation
A Self-Training Framework Based on Multi-Scale Attention Fusion for Weakly Supervised Semantic Segmentation
Multi-Granularity Denoising and Bidirectional Alignment for Weakly Supervised Semantic Segmentation
Segment Anything Model (SAM) Enhanced Pseudo Labels for Weakly Supervised Semantic Segmentation
Mitigating Undisciplined Over-Smoothing in Transformer for Weakly Supervised Semantic Segmentation
Segment Anything is A Good Pseudo-label Generator for Weakly Supervised Semantic Segmentation
An Alternative to WSSS? An Empirical Study of the Segment Anything Model (SAM) on Weakly-Supervised Semantic Segmentation Problems
MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation
Coupling Global Context and Local Contents for Weakly-Supervised Semantic Segmentation
High-fidelity Pseudo-labels for Boosting Weakly-Supervised Segmentation
WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation
Removing supervision in semantic segmentation with local-global matching and area balancing
MECPformer: Multi-estimations Complementary Patch with CNN-Transformers for Weakly Supervised Semantic Segmentation
Extracting Class Activation Maps from Non-Discriminative Features as well
USAGE: A Unified Seed Area Generation Paradigm for Weakly Supervised Semantic Segmentation
ReFit: A Framework for Refinement of Weakly Supervised Semantic Segmentation using Object Border Fitting for Medical Images
Exploring Weakly Supervised Semantic Segmentation Ensembles for Medical Imaging Systems
Exploit CAM by itself: Complementary Learning System for Weakly Supervised Semantic Segmentation
Token Contrast for Weakly-Supervised Semantic Segmentation
Self Correspondence Distillation for End-to-End Weakly-Supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation of Ships Using Thermal Imagery
CLIP is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation
Weakly Supervised Semantic Segmentation for Large-Scale Point Cloud
Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation
ISIM: Iterative Self-Improved Model for Weakly Supervised Segmentation
Attention-based Class Activation Diffusion for Weakly-Supervised Semantic Segmentation
Max Pooling with Vision Transformers reconciles class and shape in weakly supervised semantic segmentation
SemFormer: Semantic Guided Activation Transformer for Weakly Supervised Semantic Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.