AI Paper Atlas

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

PixCLIP: Towards Fine-grained Vision-Language Understanding via Any-granularity Pixel-Text Alignment

YiCheng Xiao, Yu Chen, Hao-Xuan Ma, Jiale Hong, Caorui Li, Lingxiang Wu, Haiyun Guo, Jinqiao Wang

ICML 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Fine-grained improvements to CLIP

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
add local-global representation enhancement loss L_LG (ablation)PixCLIP (L_CL baseline) · RefCOCO Valaccuracy: 51.144% -> 59.041%Improved
add fine-grained cropping alignment loss L_FC (ablation)PixCLIP (L_CL + L_LG) · Urban1k I2TRecall@1: 88.9% -> 91.0%Improved
add L_FC to L_CL + L_LG on Ref-SAV M2T (ablation)PixCLIP · Ref-SAV M2TRecall@1: 47.4% -> 47.3%No clear effect
add L_LG and L_FC to mask-text contrastive training (ablation)PixCLIP · Urban1k T2IRecall@1: 92.4% -> 93.7%Improved
fuse mask embedding by adding to image patch embedding instead of concatenation (ablation)PixCLIP · DOCCI I2TRecall@1: 86.6 -> 96.7Improved
use full-image ratio 0.1 rather than 0.2 or 0.3 (ablation)PixCLIP · Instance-COCOtop-1 accuracy: 72.0 (0.3) -> 72.7 (0.1)Improved
train PixCLIP with mask prompts instead of Alpha-CLIPPixCLIP · Ref-SAV M2TRecall@1: 28.3% -> 47.3%Improved
use PixCLIP versus LLM2CLIP on short-text retrievalPixCLIP · Flickr30k I2TRecall@1: 88.5 -> 84.2Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 3 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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