# SLiMe: Segment Like Me

arXiv: https://arxiv.org/abs/2309.03179 · HTML: https://mlsanity.com/paper/2309.03179/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 31 of its 41 references that are in the map.
- First posted on arXiv 6 Sep 2023.

## Placed in

- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)
- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (2022)
- [Language-driven Semantic Segmentation](https://mlsanity.com/paper/2201.03546/) (2022)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [MaskGAN: Towards Diverse and Interactive Facial Image Manipulation](https://mlsanity.com/paper/1907.11922/) (2019)
- [Label-Efficient Semantic Segmentation with Diffusion Models](https://mlsanity.com/paper/2112.03126/) (2021)
- [Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts](https://mlsanity.com/paper/1406.2031/) (2014)
- [SegGPT: Segmenting Everything In Context](https://mlsanity.com/paper/2304.03284/) (2023)
- [Localizing Object-level Shape Variations with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.11306/) (2023)
- [Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion](https://mlsanity.com/paper/2308.12469/) (2023)
- [Unsupervised Semantic Correspondence Using Stable Diffusion](https://mlsanity.com/paper/2305.15581/) (2023)
- [Repurposing GANs for One-shot Semantic Part Segmentation](https://mlsanity.com/paper/2103.04379/) (2021)
- [Feature-Proxy Transformer for Few-Shot Segmentation](https://mlsanity.com/paper/2210.06908/) (2022)
- [Peekaboo: Text to Image Diffusion Models are Zero-Shot Segmentors](https://mlsanity.com/paper/2211.13224/) (2022)
- [Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation](https://mlsanity.com/paper/2208.00306/) (2022)
- [Semantic Part Segmentation using Compositional Model combining Shape and Appearance](https://mlsanity.com/paper/1412.6124/) (2014)
- [PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentation](https://mlsanity.com/paper/2301.00954/) (2023)

## Built on by (most cited first, 30 of 34)

- [Training-Free Consistent Text-to-Image Generation](https://mlsanity.com/paper/2402.03286/) (2024)
- [ViVid-1-to-3: Novel View Synthesis with Video Diffusion Models](https://mlsanity.com/paper/2312.01305/) (2023)
- [StreamDiffusion: A Pipeline-level Solution for Real-time Interactive Generation](https://mlsanity.com/paper/2312.12491/) (2023)
- [TokenCompose: Text-to-Image Diffusion with Token-level Supervision](https://mlsanity.com/paper/2312.03626/) (2023)
- [Diff-Tracker: Text-to-Image Diffusion Models are Unsupervised Trackers](https://mlsanity.com/paper/2407.08394/) (2024)
- [Unleashing Diffusion Transformers for Visual Correspondence by Modulating Massive Activations](https://mlsanity.com/paper/2505.18584/) (2025)
- [Unsupervised Keypoints from Pretrained Diffusion Models](https://mlsanity.com/paper/2312.00065/) (2023)
- [Detecting Out-Of-Distribution Earth Observation Images with Diffusion Models](https://mlsanity.com/paper/2404.12667/) (2024)
- [GLASS: Guided Latent Slot Diffusion for Object-Centric Learning](https://mlsanity.com/paper/2407.17929/) (2024)
- [Explore In-Context Segmentation via Latent Diffusion Models](https://mlsanity.com/paper/2403.09616/) (2024)
- [Click to Grasp: Zero-Shot Precise Manipulation via Visual Diffusion Descriptors](https://mlsanity.com/paper/2403.14526/) (2024)
- [Concept Replacer: Replacing Sensitive Concepts in Diffusion Models via Precision Localization](https://mlsanity.com/paper/2412.01244/) (2024)
- [iSeg: An Iterative Refinement-based Framework for Training-free Segmentation](https://mlsanity.com/paper/2409.03209/) (2024)
- [Can Generative Geospatial Diffusion Models Excel as Discriminative Geospatial Foundation Models?](https://mlsanity.com/paper/2503.07890/) (2025)
- [Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Models](https://mlsanity.com/paper/2403.07733/) (2024)
- [SMITE: Segment Me In TimE](https://mlsanity.com/paper/2410.18538/) (2024)
- [There is no SAMantics! Exploring SAM as a Backbone for Visual Understanding Tasks](https://mlsanity.com/paper/2411.15288/) (2024)
- [Steady Progress Beats Stagnation: Mutual Aid of Foundation and Conventional Models in Mixed Domain Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2503.16997/) (2025)
- [Generative Edge Detection with Stable Diffusion](https://mlsanity.com/paper/2410.03080/) (2024)
- [An Image-like Diffusion Method for Human-Object Interaction Detection](https://mlsanity.com/paper/2503.18134/) (2025)
- [Representative Feature Extraction During Diffusion Process for Sketch Extraction with One Example](https://mlsanity.com/paper/2401.04362/) (2024)
- [Studying Image Diffusion Features for Zero-Shot Video Object Segmentation](https://mlsanity.com/paper/2504.05468/) (2025)
- [PerSense: Training-Free Personalized Instance Segmentation in Dense Images](https://mlsanity.com/paper/2405.13518/) (2024)
- [Exploring Structured Semantic Priors Underlying Diffusion Score for Test-time Adaptation](https://mlsanity.com/paper/2501.00873/) (2025)
- [Towards PerSense++: Advancing Training-Free Personalized Instance Segmentation in Dense Images](https://mlsanity.com/paper/2508.14660/) (2025)
- [NERVE: Neighbourhood & Entropy-guided Random-walk for training free open-Vocabulary sEgmentation](https://mlsanity.com/paper/2511.08248/) (2025)
- [Personalized OVSS: Understanding Personal Concept in Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2507.11030/) (2025)
- [Leveraging Text-to-Image Diffusion Models for Unsupervised Visual Object Tracking](https://mlsanity.com/paper/2605.26933/) (2026)
- [MotionDreamer: Exploring Semantic Video Diffusion features for Zero-Shot 3D Mesh Animation](https://mlsanity.com/paper/2405.20155/) (2024)
- [RefCut: Interactive Segmentation with Reference Guidance](https://mlsanity.com/paper/2503.17820/) (2025)

## Abstract (arXiv)

Significant strides have been made using large vision-language models, like Stable Diffusion (SD), for a variety of downstream tasks, including image editing, image correspondence, and 3D shape generation. Inspired by these advancements, we explore leveraging these extensive vision-language models for segmenting images at any desired granularity using as few as one annotated sample by proposing SLiMe. SLiMe frames this problem as an optimization task. Specifically, given a single training image and its segmentation mask, we first extract attention maps, including our novel "weighted accumulated self-attention map" from the SD prior. Then, using the extracted attention maps, the text embeddings of Stable Diffusion are optimized such that, each of them, learn about a single segmented region from the training image. These learned embeddings then highlight the segmented region in the attention maps, which in turn can then be used to derive the segmentation map. This enables SLiMe to segment any real-world image during inference with the granularity of the segmented region in the training image, using just one example. Moreover, leveraging additional training data when available, i.e. few-shot, improves the performance of SLiMe. We carried out a knowledge-rich set of experiments examining various design factors and showed that SLiMe outperforms other existing one-shot and few-shot segmentation methods.