mlsanityData to 14 Oct 2026

MARS-CLIP: Multi-Resolution and Attention Refined Zero-Shot Image Segmentation

arXiv 2609.08283 ↗First posted 8 Sep 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in zero-shot transfer but often struggles with dense prediction tasks due to low spatial resolution and the loss of structural information. To address these limitations, we propose MARS-CLIP (Multi-resolution and Attention Refined Segmentation for CLIP), a novel framework for zero-shot semantic segmentation. Our approach introduces two key strategies: (i) a multi-resolution feature extraction module that fuses local fine-grained features with global context to overcome input resolution constraints, and (ii) an attention refinement mechanism that injects spatial and color biases from intermediate layers into the final self-attention block to accurately restore object boundaries. A set of experiments on six public datasets demonstrates that MARS-CLIP significantly outperforms state-of-the-art methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 22 of its 29 references that are in the map. First posted on arXiv 8 Sep 2026.

Builds on

22 of 29 references.

References · 22

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  5. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  6. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  7. 2016Semantic Understanding of Scenes through the ADE20K Datasetcited by 1,069
  8. 2016COCO-Stuff: Thing and Stuff Classes in Contextcited by 864
  9. 2020Image Segmentation Using Deep Learning: A Surveycited by 660
  10. 2021Extract Free Dense Labels from CLIPcited by 583
  11. 2019Zero-Shot Semantic Segmentationcited by 245
  12. 2023SCLIP: Rethinking Self-Attention for Dense Vision-Language Inferencecited by 170
10 more
  1. 2020Single-Stage Semantic Segmentation from Image Labelscited by 167
  2. 2024ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inferencecited by 113
  3. 2024ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentationcited by 111
  4. 2023A Closer Look at the Explainability of Contrastive Language-Image Pre-trainingcited by 96
  5. 2023Grounding Everything: Emerging Localization Properties in Vision-Language Transformerscited by 91
  6. 2024Pay Attention to Your Neighbours: Training-Free Open-Vocabulary Semantic Segmentationcited by 77
  7. 2021Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentationcited by 53
  8. 2024Training-Free Open-Vocabulary Segmentation with Offline Diffusion-Augmented Prototype Generationcited by 44
  9. 2024ResCLIP: Residual Attention for Training-free Dense Vision-language Inferencecited by 29
  10. 2023Emergent Open-Vocabulary Semantic Segmentation from Off-the-shelf Vision-Language Modelscited by 15

Built on by

Not cited yet.