AI Paper Atlas

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

Guiding Diffusion-based Reconstruction with Contrastive Signals for Balanced Visual Representation

Boyu Han, Qianqian Xu, Shilong Bao, Zhiyong Yang, Ruochen Cui, Xilin Zhao, Qingming Huang

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: CLIP training recipes and data curation · 0 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 naive Lcon+Lrec sum with unified DCR loss (ablation)CLIP ViT-L@224 · MMVP-VLMaccuracy: 22.96 -> 33.30Improved
replace naive sum with DCR loss (ablation)CLIP ViT-L@224 · Zero-shot clusteringNMI/ACC/ARI: 0.72/0.65/0.50 -> 0.76/0.67/0.54Improved
use two-stage (projector alignment then encoder) instead of end-to-end (ablation)DCR · MMVP-VLMaccuracy: 25.93 -> 33.30Improved
use two-stage instead of end-to-end (ablation)DCR · Zero-shot clusteringNMI/ACC/ARI: 0.73/0.65/0.51 -> 0.76/0.67/0.54Improved
use SD-2.1 backbone vs other SD versions (incl. SD-XL) (ablation)DCR · MMVP-VLM and clusteringaccuracy, NMIMixed
apply DCR to CLIPOpenAI CLIP ViT-L@224 · MMVP-VLMaccuracy: 19.2 -> 33.3Improved
apply DIVA (reconstruction only) to CLIPOpenAI CLIP ViT-L@224 · Zero-shot clusteringACC: 0.61 -> 0.60Hurt
apply GenHancer to CLIPOpenAI CLIP ViT-L@224 · Zero-shot clusteringNMI: 0.71 -> 0.65Hurt
swap in DCR-enhanced CLIP in LLaVA-1.5LLaVA-1.5 Vicuna-7B · MMVP-MLLMaccuracy: 24.7 -> 31.3Improved
swap in DCR-enhanced CLIP in LLaVA-1.5LLaVA-1.5 Vicuna-7B · POPE adv / SciQA-IMGaccuracy: 85.8 vs 84.2 (POPE adv); 67.5 vs 66.8 SciQA, below un2CLIP 68.4Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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