Papers with Code 아카이브
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.
Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation
Exploiting Inherent Class Label: Towards Robust Scribble Supervised Semantic Segmentation
DOEI: Dual Optimization of Embedding Information for Attention-Enhanced Class Activation Maps
Superpixel Boundary Correction for Weakly-Supervised Semantic Segmentation on Histopathology Images
HisynSeg: Weakly-Supervised Histopathological Image Segmentation via Image-Mixing Synthesis and Consistency Regularization
Image Augmentation Agent for Weakly Supervised Semantic Segmentation
Toward Modality Gap: Vision Prototype Learning for Weakly-supervised Semantic Segmentation with CLIP
Prompt Categories Cluster for Weakly Supervised Semantic Segmentation
MoRe: Class Patch Attention Needs Regularization for Weakly Supervised Semantic Segmentation
Revisiting the Integration of Convolution and Attention for Vision Backbone
A Multimodal Approach Combining Structural and Cross-domain Textual Guidance for Weakly Supervised OCT Segmentation
Enhancing Weakly Supervised Semantic Segmentation for Fibrosis via Controllable Image Generation
EP-SAM: Weakly Supervised Histopathology Segmentation via Enhanced Prompt with Segment Anything
DIAL: Dense Image-text ALignment for Weakly Supervised Semantic Segmentation
Pixel-Level Domain Adaptation: A New Perspective for Enhancing Weakly Supervised Semantic Segmentation
Adaptive Patch Contrast for Weakly Supervised Semantic Segmentation
Finding Meaning in Points: Weakly Supervised Semantic Segmentation for Event Cameras
3D Weakly Supervised Semantic Segmentation with 2D Vision-Language Guidance
Knowledge Transfer with Simulated Inter-Image Erasing for Weakly Supervised Semantic Segmentation
Precision matters: Precision-aware ensemble for weakly supervised semantic segmentation
Fine-grained Background Representation for Weakly Supervised Semantic Segmentation
Frozen CLIP: A Strong Backbone for Weakly Supervised Semantic Segmentation
Learning to Detour: Shortcut Mitigating Augmentation for Weakly Supervised Semantic Segmentation
SE3D: A Framework For Saliency Method Evaluation In 3D Imaging
Enhancing Weakly Supervised Semantic Segmentation with Multi-modal Foundation Models: An End-to-End Approach
Weakly-supervised Semantic Segmentation via Dual-stream Contrastive Learning of Cross-image Contextual Information
COIN: Counterfactual inpainting for weakly supervised semantic segmentation for medical images
ToNNO: Tomographic Reconstruction of a Neural Network's Output for Weakly Supervised Segmentation of 3D Medical Images
Tackling Ambiguity from Perspective of Uncertainty Inference and Affinity Diversification for Weakly Supervised Semantic Segmentation
Background Noise Reduction of Attention Map for Weakly Supervised Semantic Segmentation
Rethinking Saliency-Guided Weakly-Supervised Semantic Segmentation
DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation
Modeling the Label Distributions for Weakly-Supervised Semantic Segmentation
DuPL: Dual Student with Trustworthy Progressive Learning for Robust Weakly Supervised Semantic Segmentation
Hunting Attributes: Context Prototype-Aware Learning for Weakly Supervised Semantic Segmentation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.