Toward Semantic-Agnostic and Shape-Aware Vision-Language Segmentation Models

• URL: http://arxiv.org/abs/2605.28348v1
• Date: Wed, 27 May 2026 11:51:33 GMT
• Title: Toward Semantic-Agnostic and Shape-Aware Vision-Language Segmentation Models
• Abstract summary: Vision-language segmentation models have recently achieved strong performance by leveraging high-level semantic categories object expressed in natural language.<n>We introduce Semantic-Agnostic aNd Shape-Aware (SANSA) segmentation, a new paradigm that requires segmentation models to operate solely from non-semantic textual descriptions.<n>Experiments show that finetuning on SANSA prompts yields up to a 20% mIoU improvement on this new segmentation task.
• Score: 0.9569208373364791
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-language segmentation models have recently achieved strong performance by leveraging high-level semantic object categories expressed in natural language. However, this semantic dependence limits their ability to reason about intrinsic visual properties such as shape, geometry, or texture, which are essential in many real-world applications. In this work, we introduce Semantic-Agnostic aNd Shape-Aware (SANSA) segmentation, a new paradigm that requires segmentation models to operate solely from non-semantic textual descriptions. To this end, we propose two strategies to generate SANSA segmentation prompts based on either dictionary constraints or example guidance, both generating semantic-agnostic textual descriptions. These prompts are then used to finetune segmentation models under semantic-agnostic supervision. Experiments show that finetuning on SANSA prompts yields up to a 20% mIoU improvement on this new segmentation task, compared to pretrained state-of-the-art models, while maintaining strong performance on standard semantic prompts. These results highlight the importance of low- and mid-level visual reasoning for improving the generalization and controllability of vision-language segmentation models.

Related papers

• Learning a Semantic Calibration Network for Open-Vocabulary Semantic Segmentation [5.122331812021513]
  Open-Vocabulary (OVS) extends the segmentation task from a fixed set to an open set.<n>We propose a novel Semantic Network (SCN) for open-vocabulary semantic segmentation.<n>The proposed method achieves significant performance improvements compared to state-of-the-art algorithms.
  arXiv  Detail & Related papers  (2026-06-06T06:42:03Z)
• Seg-Agent: Test-Time Multimodal Reasoning for Training-Free Language-Guided Segmentation [52.8308168727975]
  Seg-Agent is a completely training-free framework that pioneers Explicit Multimodal Chain-of-Reasoning.<n>Our approach constructs an interactive visual reasoning loop comprising three stages: generation, selection, and refinement.<n>Various-LangSeg is a novel benchmark covering explicit semantic, generic object, and reasoning-guided segmentation tasks.
  arXiv  Detail & Related papers  (2026-05-13T03:36:44Z)
• Cross-Domain Semantic Segmentation with Large Language Model-Assisted Descriptor Generation [0.0]
  LangSeg is a novel semantic segmentation method that leverages context-sensitive, fine-grained subclass descriptors.<n>We evaluate LangSeg on two challenging datasets, ADE20K and COCO-Stuff, where it outperforms state-of-the-art models.
  arXiv  Detail & Related papers  (2025-01-27T20:02:12Z)
• Envisioning Class Entity Reasoning by Large Language Models for Few-shot Learning [13.68867780184022]
  Few-shot learning aims to recognize new concepts using a limited number of visual samples. Our framework incorporates both the abstract class semantics and the concrete class entities extracted from Large Language Models (LLMs) For the challenging one-shot setting, our approach, utilizing the ResNet-12 backbone, achieves an average improvement of 1.95% over the second-best competitor.
  arXiv  Detail & Related papers  (2024-08-22T15:10:20Z)
• Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation [114.72734384299476]
  We propose a Language-Driven Visual Consensus (LDVC) approach, fostering improved alignment of semantic and visual information. We leverage class embeddings as anchors due to their discrete and abstract nature, steering vision features toward class embeddings. Our approach significantly boosts the capacity of segmentation models for unseen classes.
  arXiv  Detail & Related papers  (2024-03-13T11:23:55Z)
• IDRNet: Intervention-Driven Relation Network for Semantic Segmentation [34.09179171102469]
  Co-occurrent visual patterns suggest that pixel relation modeling facilitates dense prediction tasks. Despite the impressive results, existing paradigms often suffer from inadequate or ineffective contextual information aggregation. We propose a novel textbfIntervention-textbfDriven textbfRelation textbfNetwork.
  arXiv  Detail & Related papers  (2023-10-16T18:37:33Z)
• Exploring Open-Vocabulary Semantic Segmentation without Human Labels [76.15862573035565]
  We present ZeroSeg, a novel method that leverages the existing pretrained vision-language model (VL) to train semantic segmentation models. ZeroSeg overcomes this by distilling the visual concepts learned by VL models into a set of segment tokens, each summarizing a localized region of the target image. Our approach achieves state-of-the-art performance when compared to other zero-shot segmentation methods under the same training data.
  arXiv  Detail & Related papers  (2023-06-01T08:47:06Z)
• A Simple Baseline for Zero-shot Semantic Segmentation with Pre-trained Vision-language Model [61.58071099082296]
  It is unclear how to make zero-shot recognition working well on broader vision problems, such as object detection and semantic segmentation. In this paper, we target for zero-shot semantic segmentation, by building it on an off-the-shelf pre-trained vision-language model, i.e., CLIP. Our experimental results show that this simple framework surpasses previous state-of-the-arts by a large margin.
  arXiv  Detail & Related papers  (2021-12-29T18:56:18Z)
• Infusing Finetuning with Semantic Dependencies [62.37697048781823]
  We show that, unlike syntax, semantics is not brought to the surface by today's pretrained models. We then use convolutional graph encoders to explicitly incorporate semantic parses into task-specific finetuning.
  arXiv  Detail & Related papers  (2020-12-10T01:27:24Z)
• SLM: Learning a Discourse Language Representation with Sentence Unshuffling [53.42814722621715]
  We introduce Sentence-level Language Modeling, a new pre-training objective for learning a discourse language representation. We show that this feature of our model improves the performance of the original BERT by large margins.
  arXiv  Detail & Related papers  (2020-10-30T13:33:41Z)

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.