논문

One Click per Cell Type Suffices

One Click per Cell Type Suffices: Training-free Group Interaction for Cell Instance Segmentation

On the Collapse of Generative Paths

On the Collapse of Generative Paths: A Criterion and Correction for Diffusion Steering

EraseLoRa

MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal

TRACE(구 DiffEGG)

Your Diffusion Model is Secretly an Instance Edge Detector (구 Diffusion-Driven Edge Generation for Unsupervised Instance Segmentation and Beyond )

ISAC

Training-Free Instance-to-Semantic Attention Control for Improving Multi-Instance Generation

ELECT

EARLY TIMESTEP ZERO-SHOT CANDIDATE SELECTION FOR INSTRUCTION-GUIDED IMAGE EDITING

COIN

Toward Annotation-Free Cell Instance Segmentation via Confidence Score-Guided Instance Distillation

DHR

Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation

TTD

Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias

MARS

Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation

RS+EPM

RecurSeed and EdgePredictMix: Pseudo-Label Refinement Learning for Weakly Supervised Semantic Segmentation across Single- and Multi-Stage Frameworks

Puzzle-CAM

Improved localization via matching partial and full features