# Target Refocusing via Attention Redistribution for Open-Vocabulary Semantic Segmentation: An Explainability Perspective

arXiv: https://arxiv.org/abs/2511.16170 · HTML: https://mlsanity.com/paper/2511.16170/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 64 references that are in the map.
- First posted on arXiv 20 Nov 2025.

## Builds on (most cited first, 30 of 49)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [Vision Transformers Need Registers](https://mlsanity.com/paper/2309.16588/) (2023)
- [COCO-Stuff: Thing and Stuff Classes in Context](https://mlsanity.com/paper/1612.03716/) (2016)
- [Extract Free Dense Labels from CLIP](https://mlsanity.com/paper/2112.01071/) (2021)
- [Open-Vocabulary Semantic Segmentation with Mask-adapted CLIP](https://mlsanity.com/paper/2210.04150/) (2022)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [GroupViT: Semantic Segmentation Emerges from Text Supervision](https://mlsanity.com/paper/2202.11094/) (2022)
- [Image Segmentation Using Text and Image Prompts](https://mlsanity.com/paper/2112.10003/) (2021)
- [Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm](https://mlsanity.com/paper/2110.05208/) (2021)
- [Side Adapter Network for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2302.12242/) (2023)
- [Exploring Visual Prompts for Adapting Large-Scale Models](https://mlsanity.com/paper/2203.17274/) (2022)
- [Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/1906.00817/) (2019)
- [CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2303.11797/) (2023)
- [Unified Contrastive Learning in Image-Text-Label Space](https://mlsanity.com/paper/2204.03610/) (2022)
- [SCLIP: Rethinking Self-Attention for Dense Vision-Language Inference](https://mlsanity.com/paper/2312.01597/) (2023)
- [Unified Vision and Language Prompt Learning](https://mlsanity.com/paper/2210.07225/) (2022)
- [Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs](https://mlsanity.com/paper/2212.00785/) (2022)
- [CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction](https://mlsanity.com/paper/2310.01403/) (2023)
- [ReCo: Retrieve and Co-segment for Zero-shot Transfer](https://mlsanity.com/paper/2206.07045/) (2022)
- [ClearCLIP: Decomposing CLIP Representations for Dense Vision-Language Inference](https://mlsanity.com/paper/2407.12442/) (2024)
- [ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2408.04883/) (2024)
- [SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2311.15537/) (2023)
- [CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation](https://mlsanity.com/paper/2312.12359/) (2023)
- [Context-aware Feature Generation for Zero-shot Semantic Segmentation](https://mlsanity.com/paper/2008.06893/) (2020)
- [Grounding Everything: Emerging Localization Properties in Vision-Language Transformers](https://mlsanity.com/paper/2312.00878/) (2023)

## Built on by (most cited first, 5 of 5)

- [Taming SAM3 in the Wild: A Concept Bank for Open-Vocabulary Segmentation](https://mlsanity.com/paper/2602.06333/) (2026)
- [CoCo-SAM3: Harnessing Concept Conflict in Open-Vocabulary Semantic Segmentation](https://mlsanity.com/paper/2604.19648/) (2026)
- [FlowDIS: Language-Guided Dichotomous Image Segmentation with Flow Matching](https://mlsanity.com/paper/2605.05077/) (2026)
- [ActiveSAM: Fast and Accurate Open-Vocabulary Semantic Segmentation with Frozen SAM 3](https://mlsanity.com/paper/2606.16996/) (2026)
- [Rapid-Deployment Crack Measurement Based on SAM3 Semantic-Edge Response Decoding](https://mlsanity.com/paper/2607.12292/) (2026)

## Abstract (arXiv)

Open-vocabulary semantic segmentation (OVSS) employs pixel-level vision-language alignment to associate category-related prompts with corresponding pixels. A key challenge is enhancing the multimodal dense prediction capability, specifically this pixel-level multimodal alignment. Although existing methods achieve promising results by leveraging CLIP's vision-language alignment, they rarely investigate the performance boundaries of CLIP for dense prediction from an interpretability mechanisms perspective. In this work, we systematically investigate CLIP's internal mechanisms and identify a critical phenomenon: analogous to human distraction, CLIP diverts significant attention resources from target regions to irrelevant tokens. Our analysis reveals that these tokens arise from dimension-specific over-activation; filtering them enhances CLIP's dense prediction performance. Consequently, we propose ReFocusing CLIP (RF-CLIP), a training-free approach that emulates human distraction-refocusing behavior to redirect attention from distraction tokens back to target regions, thereby refining CLIP's multimodal alignment granularity. Our method achieves SOTA performance on eight benchmarks while maintaining high inference efficiency.