# ConceptAttention: Diffusion Transformers Learn Highly Interpretable Features

arXiv: https://arxiv.org/abs/2502.04320 · HTML: https://mlsanity.com/paper/2502.04320/

## Key facts

- Cited by 52 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 45 of its 52 references that are in the map.
- First posted on arXiv 6 Feb 2025.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 45)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [iBOT: Image BERT Pre-Training with Online Tokenizer](https://mlsanity.com/paper/2111.07832/) (2021)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [Quantifying Attention Flow in Transformers](https://mlsanity.com/paper/2005.00928/) (2020)
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [Training-Free Layout Control with Cross-Attention Guidance](https://mlsanity.com/paper/2304.03373/) (2023)
- [Your Diffusion Model is Secretly a Zero-Shot Classifier](https://mlsanity.com/paper/2303.16203/) (2023)
- [Diffusion Self-Guidance for Controllable Image Generation](https://mlsanity.com/paper/2306.00986/) (2023)
- [SegDiff: Image Segmentation with Diffusion Probabilistic Models](https://mlsanity.com/paper/2112.00390/) (2021)
- [Unsupervised Semantic Segmentation by Distilling Feature Correspondences](https://mlsanity.com/paper/2203.08414/) (2022)

## Built on by (most cited first, 30 of 52)

- [WordCon: Word-level Typography Control in Scene Text Rendering](https://mlsanity.com/paper/2506.21276/) (2025)
- [LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers](https://mlsanity.com/paper/2505.23758/) (2025)
- [Attention (as Discrete-Time Markov) Chains](https://mlsanity.com/paper/2507.17657/) (2025)
- [From Generation to Generalization: Emergent Few-Shot Learning in Video Diffusion Models](https://mlsanity.com/paper/2506.07280/) (2025)
- [Localizing Knowledge in Diffusion Transformers](https://mlsanity.com/paper/2505.18832/) (2025)
- [Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned Interventions](https://mlsanity.com/paper/2512.08486/) (2025)
- [DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse Autoencoders](https://mlsanity.com/paper/2602.05859/) (2026)
- [S3OD: Towards Generalizable Salient Object Detection with Synthetic Data](https://mlsanity.com/paper/2510.21605/) (2025)
- [Scale Where It Matters: Training-Free Localized Scaling for Diffusion Models](https://mlsanity.com/paper/2511.19917/) (2025)
- [Object-WIPER : Training-Free Object and Associated Effect Removal in Videos](https://mlsanity.com/paper/2601.06391/) (2026)
- [Formal Abductive Latent Explanations for Prototype-Based Networks](https://mlsanity.com/paper/2511.16588/) (2025)
- [Layer-wise Instance Binding for Regional and Occlusion Control in Text-to-Image Diffusion Transformers](https://mlsanity.com/paper/2603.05769/) (2026)
- [TRACE: Your Diffusion Model is Secretly an Instance Edge Detector](https://mlsanity.com/paper/2503.07982/) (2025)
- [Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals](https://mlsanity.com/paper/2505.21062/) (2025)
- [Rare Text Semantics Were Always There in Your Diffusion Transformer](https://mlsanity.com/paper/2510.03886/) (2025)
- [TS-Attn: Temporal-wise Separable Attention for Multi-Event Video Generation](https://mlsanity.com/paper/2604.19473/) (2026)
- [Text Template Tokens Are Implicit Semantic Registers in Diffusion Transformers](https://mlsanity.com/paper/2607.19139/) (2026)
- [Making Training-Free Diffusion Segmentors Scale with the Generative Power](https://mlsanity.com/paper/2603.06178/) (2026)
- [TaxaAdapter: Vision Taxonomy Models are Key to Fine-grained Image Generation over the Tree of Life](https://mlsanity.com/paper/2603.26128/) (2026)
- [On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers](https://mlsanity.com/paper/2603.28762/) (2026)
- [LOCATEdit: Graph Laplacian Optimized Cross Attention for Localized Text-Guided Image Editing](https://mlsanity.com/paper/2503.21541/) (2025)
- [The Cow of Rembrandt - Analyzing Artistic Prompt Interpretation in Text-to-Image Models](https://mlsanity.com/paper/2507.23313/) (2025)
- [ChartGaze: Enhancing Chart Understanding in LVLMs with Eye-Tracking Guided Attention Refinement](https://mlsanity.com/paper/2509.13282/) (2025)
- [RefAM: Attention Magnets for Zero-Shot Referral Segmentation](https://mlsanity.com/paper/2509.22650/) (2025)
- [Few Channels Draw The Whole Picture: Revealing Massive Activations in Diffusion Transformers](https://mlsanity.com/paper/2605.13974/) (2026)
- [Hidden in Plain Sight -- Class Competition Focuses Attribution Maps](https://mlsanity.com/paper/2503.07346/) (2025)
- [Focal Guidance: Unlocking Controllability from Semantic-Weak Layers in Video Diffusion Models](https://mlsanity.com/paper/2601.07287/) (2026)
- [Interpretable Motion-Attentive Maps: Spatio-Temporally Localizing Concepts in Video Diffusion Transformers](https://mlsanity.com/paper/2603.02919/) (2026)
- [The Latent Color Subspace: Emergent Order in High-Dimensional Chaos](https://mlsanity.com/paper/2603.12261/) (2026)
- [What Concepts Lie Within? Detecting and Suppressing Risky Content in Diffusion Transformers](https://mlsanity.com/paper/2605.10180/) (2026)

## Abstract (arXiv)

Do the rich representations of multi-modal diffusion transformers (DiTs) exhibit unique properties that enhance their interpretability? We introduce ConceptAttention, a novel method that leverages the expressive power of DiT attention layers to generate high-quality saliency maps that precisely locate textual concepts within images. Without requiring additional training, ConceptAttention repurposes the parameters of DiT attention layers to produce highly contextualized concept embeddings, contributing the major discovery that performing linear projections in the output space of DiT attention layers yields significantly sharper saliency maps compared to commonly used cross-attention maps. ConceptAttention even achieves state-of-the-art performance on zero-shot image segmentation benchmarks, outperforming 15 other zero-shot interpretability methods on the ImageNet-Segmentation dataset. ConceptAttention works for popular image models and even seamlessly generalizes to video generation. Our work contributes the first evidence that the representations of multi-modal DiTs are highly transferable to vision tasks like segmentation.