Article

HEADHUNTER: Training-Free Annotated Dataset Synthesis via Self-Guided Diffusion Transformer Attention Head Selection

2026-06-29

Abstract excerpt

Pixel-level annotation remains a major bottleneck for semantic segmentation, motivating methods that synthesize image-label pairs directly from generative models. Prior synthetic dataset generators typically obtain pseudo-labels from cross-attention maps or learned decoders over generative features; however, recent text-to-image (T2I) models increasingly use multimodal diffusion transformers (MM-DiTs), where conce...

Topics

Open a Topic to create a Post that cites this publication.

Radiomics and Machine Learning in Medical Imaging

Identifiers and source

Literature Corpus work: 7156debd-18e0-58b2-b2b9-f3d0ae31fad2
DOI: 10.20944/preprints202606.2132.v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

HEADHUNTER: Training-Free Annotated Dataset Synthesis via Self-Guided Diffusion Transformer Attention Head SelectionDOI 10.20944/preprints202606.2132.v1Read

HEADHUNTER: Training-Free Annotated Dataset Synthesis via Self-Guided Diffusion Transformer Attention Head SelectionSemantic proximity Read

Enhancing Caption Fidelity via Explanation-Guided Captioning with Vision-Language Fine-TuningSemantic proximity Read

Adaptive Semantic Fusion for Contextual Image CaptioningSemantic proximity Read

An Efficient and Training-Free Approach for Subject-Driven Text-to-Image GenerationSemantic proximity Read

Language-Guided Segmentation of Medical Images: A Review of Foundation ModelsSemantic proximity Read

CAT: Content-Adaptive Image TokenizationSemantic proximity Read

FineRegion-LM: Enhancing Large Vision-Language Models for Fine-Grained Region-Level UnderstandingSemantic proximity Read

Contextual Synergy through Explicit and Implicit Relations: A Unified Perspective for Image Description GenerationSemantic proximity Read

Tarsier2: Advancing Large Vision-Language Models from Detailed Video Descriptions to Comprehensive Video UnderstandingSemantic proximity Read

Generative AI Enables Medical Image Segmentation in Ultra Low-Data RegimesSemantic proximity Read

Rethinking Convolutional Semantics for Image Caption Generation Beyond Recurrent ParadigmsSemantic proximity Read

DiscoverNet: Unsupervised Video Object Discovery through Discrete Visual Tokenization and Language Model-Inspired ReconstructionSemantic proximity Read