Unsupervised Semantic Segmentation Facilitates Model Understanding

• URL: http://arxiv.org/abs/2605.29691v1
• Date: Thu, 28 May 2026 09:52:52 GMT
• Title: Unsupervised Semantic Segmentation Facilitates Model Understanding
• Abstract summary: Self-supervised learning (SSL) has produced a diverse landscape of vision transformers (ViTs)<n>We propose a simple and easily interpretable visualization protocol to make model understanding straightforward and intuitive for a broad audience.<n>We obtain novel insights into distinct positional biases and scaling behaviors, including strong boundary artifacts in DINOv3-Large model tokens.
• Score: 5.902216784679335
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-supervised learning (SSL) has produced a diverse landscape of vision transformers (ViTs) whose pretrained representations support a wide range of downstream tasks. Towards a better understanding of these models, a body of work has assessed the mechanics of their self-attention as well as the types of information captured across their representations, revealing, for example, stark differences between models trained with contrastive learning (CL) and masked image modeling (MIM). However, these advances in model understanding have not yet fully permeated the broader community, where insights specific to CL models are sometimes generalized to MIM models. To make model understanding straightforward and intuitive for a broad audience, we propose a simple and easily interpretable visualization protocol. Our protocol is based on visualizing unsupervised semantic segmentation results, yet our goal is not to maximize segmentation performance. Instead, it allows us to convey model behaviors that consistently emerge across images. Benchmarking a diverse set of SSL models across layers and representations, we obtain novel insights into distinct positional biases and scaling behaviors, including strong boundary artifacts in DINOv3-Large model tokens. These insights complement and help communicate a range of previous findings. Our protocol further enables a clear visual distinction between positional effects and the closely related but distinct locality bias, which has been studied much more extensively in the literature. The protocol is publicly available on GitHub and we believe it will catalyze further model understanding for a broad community.

Related papers

• Analyzing Finetuning Representation Shift for Multimodal LLMs Steering [56.710375516257876]
  We propose to map hidden states to interpretable visual and textual concepts.<n>This enables us to more efficiently compare certain semantic dynamics, such as the shift from an original and fine-tuned model.<n>We also demonstrate the use of shift vectors to capture these concepts changes.
  arXiv  Detail & Related papers  (2025-01-06T13:37:13Z)
• Corpus Considerations for Annotator Modeling and Scaling [9.263562546969695]
  We show that the commonly used user token model consistently outperforms more complex models. Our findings shed light on the relationship between corpus statistics and annotator modeling performance.
  arXiv  Detail & Related papers  (2024-04-02T22:27:24Z)
• A Probabilistic Model Behind Self-Supervised Learning [53.64989127914936]
  In self-supervised learning (SSL), representations are learned via an auxiliary task without annotated labels. We present a generative latent variable model for self-supervised learning. We show that several families of discriminative SSL, including contrastive methods, induce a comparable distribution over representations.
  arXiv  Detail & Related papers  (2024-02-02T13:31:17Z)
• RefSAM: Efficiently Adapting Segmenting Anything Model for Referring Video Object Segmentation [53.4319652364256]
  This paper presents the RefSAM model, which explores the potential of SAM for referring video object segmentation. Our proposed approach adapts the original SAM model to enhance cross-modality learning by employing a lightweight Cross-RValModal. We employ a parameter-efficient tuning strategy to align and fuse the language and vision features effectively.
  arXiv  Detail & Related papers  (2023-07-03T13:21:58Z)
• Scaling Vision-Language Models with Sparse Mixture of Experts [128.0882767889029]
  We show that mixture-of-experts (MoE) techniques can achieve state-of-the-art performance on a range of benchmarks over dense models of equivalent computational cost. Our research offers valuable insights into stabilizing the training of MoE models, understanding the impact of MoE on model interpretability, and balancing the trade-offs between compute performance when scaling vision-language models.
  arXiv  Detail & Related papers  (2023-03-13T16:00:31Z)
• Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization [113.03189252044773]
  We propose a unified framework, Style-HAllucinated Dual consistEncy learning (SHADE), to handle domain shift in various visual tasks. Our versatile SHADE can significantly enhance the generalization in various visual recognition tasks, including image classification, semantic segmentation and object detection.
  arXiv  Detail & Related papers  (2022-12-18T11:42:51Z)
• Localization vs. Semantics: Visual Representations in Unimodal and Multimodal Models [57.08925810659545]
  We conduct a comparative analysis of the visual representations in existing vision-and-language models and vision-only models. Our empirical observations suggest that vision-and-language models are better at label prediction tasks. We hope our study sheds light on the role of language in visual learning, and serves as an empirical guide for various pretrained models.
  arXiv  Detail & Related papers  (2022-12-01T05:00:18Z)
• High Fidelity Visualization of What Your Self-Supervised Representation Knows About [22.982471878833362]
  In this work, we showcase the use of a conditional diffusion based generative model (RCDM) to visualize representations learned with self-supervised models. We demonstrate how this model's generation quality is on par with state-of-the-art generative models while being faithful to the representation used as conditioning.
  arXiv  Detail & Related papers  (2021-12-16T19:23:33Z)
• Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations [78.12377360145078]
  Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection. In this paper, we first study how biases in the dataset affect existing methods. We show that current contrastive approaches work surprisingly well across: (i) object- versus scene-centric, (ii) uniform versus long-tailed and (iii) general versus domain-specific datasets.
  arXiv  Detail & Related papers  (2021-06-10T17:59:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.