AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

POGA: Paraphrased and Oppositional Graph Alignment for Fine-Grained Cross-Modal Retrieval

Junfeng Zhang, Zhe Xue, Yuankai Qi, Junping Du, Xiangyang Kong, Yishuo Yan, Amin Beheshti, Jian Yang, Anton van den Hengel, Ming-Hsuan Yang

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval

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 hierarchical node contrastive loss to global loss (ablation)POGA (CLIP ViT-B/16) · DCII2T R@1: 66.58 -> 74.21Improved
add structural relation alignment loss (ablation)POGA (CLIP ViT-B/16) · DCII2T R@1: 74.21 -> 77.37Improved
add focal disambiguation loss (ablation)POGA (CLIP ViT-B/16) · DCII2T R@1: 77.37 -> 79.44Improved
add both paraphrased positives and oppositional negatives (ablation)POGA (CLIP ViT-B/16) · DCII2T R@1: 76.52 -> 79.44Improved
add paraphrased positives only (ablation)POGA (CLIP ViT-B/16) · DCII2T R@1: 76.52 -> 78.11Improved
add oppositional negatives only (ablation)POGA (CLIP ViT-B/16) · DCII2T R@1: 76.52 -> 78.34Improved
set relation loss weight to 0 (ablation)POGA · DCII2T R@1: drop of more than 3 pointsHurt
set focal loss weight to 0 (ablation)POGA · DCIT2I and I2T R@1: about 1-2 point dropHurt
raise relation loss weight beyond 0.8 (ablation)POGA · DCIRecallHurt
vary global loss weight in range 0.8 to 1.2 (ablation)POGA · DCIRecallNo clear effect
graph alignment with multi-granularity losses instead of GOALCLIP ViT-L/14 · DOCCI to DCI cross-datasetT2I R@1: 68.93 -> 81.31Improved
fine-tune with POGA instead of GOALCLIP ViT-B/16 · CIFAR100 zero-shotaccuracy: 59.70 -> 67.16Improved

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