AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Segmenting Visuals With Querying Words: Language Anchors For Semi-Supervised Image Segmentation

Numair Nadeem, Saeed Anwar, Muhammad Asad, Abdul Bais

ECCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Open-vocabulary alignment from VLMs · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace TQDM baseline with full HVLFormerTQDM (SigLIP2) · Pascal VOC (92 labels)mIoU: 76.1 -> 89.4Improved
add hierarchical query generation (ablation)HVLFormer SigLIP2 · COCO (232 labels)mIoU: 41.9 -> 45.3Improved
add semantic relevance estimation (SRE) (ablation)HVLFormer SigLIP2 · Pascal VOC (92 labels)mIoU: 79.4 -> 80.5Improved
add pixel-text refinement module (PTRM) (ablation)HVLFormer SigLIP2 · Pascal VOC (92 labels)mIoU: 80.5 -> 84.1Improved
add full CMCR (mask+class+align) (ablation)HVLFormer SigLIP2 · COCO (232 labels)mIoU: 54.8 -> 59.4Improved
use soft weighting by s_k instead of no SRE (ablation)HVLFormer SigLIP2 · COCO (232 labels)mIoU: 57.8 -> 59.4Improved
use fixed threshold s_k>0.5 instead of soft weighting (ablation)HVLFormer SigLIP2 · Pascal VOC (92 labels)mIoU: 89.4 -> 88.7Hurt
add dataset attributes to learnable prompt (ablation)HVLFormer SigLIP2 · Cityscapes (100 labels)mIoU: 78.3 -> 79.6Improved
use learnable instead of fixed prompt (class name only) (ablation)HVLFormer SigLIP2 · COCO (232 labels)mIoU: 54.2 -> 58.5Improved
increase hierarchy levels E from 1 to 3 (ablation)HVLFormer SigLIP2 · Pascal VOC (92 labels)mIoU: 87.3 -> 88.9Improved
replace cross-attention with PTRM (ablation)HVLFormer SigLIP2 · COCO (232 labels)mIoU: 57.2 -> 59.4Improved
replace vision-only UniMatch consistency with CMCR (ablation)HVLFormer SigLIP2 · Pascal VOC (92 labels)mIoU: 85.2 -> 89.4Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy