Research map / Vision-language and multimodal / Cross-modal learning
Adversarial Representation Learning for Text-to-Image Matching
Nikolaos Sarafianos, Xiang Xu, Ioannis A. Kakadiaris
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add cross-modal projection matching loss to identification loss (ablation) | TIMAM · CUHK-PEDES text-to-image | Rank-1: 40.1 -> 49.8 | Improved |
| add identification loss to projection matching loss (ablation) | TIMAM · CUHK-PEDES text-to-image | Rank-1: 44.9 -> 49.8 | Improved |
| add BERT word embeddings (ablation) | TIMAM (no ARL) · CUHK-PEDES text-to-image | Rank-1: 49.8 -> 52.9 | Improved |
| add adversarial representation learning (ablation) | TIMAM (no BERT) · CUHK-PEDES text-to-image | Rank-1: 49.8 -> 51.3 | Improved |
| add adversarial representation learning (ablation) | TIMAM (with BERT) · CUHK-PEDES text-to-image | Rank-1: 52.9 -> 54.5 | Improved |
| add adversarial representation learning (ablation) | TIMAM · Flickr30K image-to-text | Rank-1: 51.2 -> 53.1 | Improved |
| add adversarial representation learning (ablation) | TIMAM · Flickr30K text-to-image | Rank-1: 41.0 -> 42.6 | Improved |
| replace FC word embedding with BERT (ablation) | TIMAM (ResNet-101) · Flickr30K text-to-image | Rank-1: 35.8 -> 40.6 | Improved |
| replace FC word embedding with BERT (ablation) | TIMAM (ResNet-152) · Flickr30K image-to-text | Rank-1: 50.1 -> 53.1 | Improved |
| deepen image backbone from ResNet-101 to ResNet-152 (ablation) | TIMAM (BERT) · Flickr30K text-to-image | Rank-1: 40.6 -> 42.6 | Improved |
| add conditional text augmentation (ablation) | TIMAM · CUHK-PEDES text-to-image | Rank-1 | Hurt |
| add text-to-image reconstruction objective (ablation) | TIMAM · CUHK-PEDES and Flickr30K | Rank-1 | No clear effect |
Closest papers by meaning
- Expressing Objects Just Like Words: Recurrent Visual Embedding for Image-Text Matching (AAAI 2020 · similarity 0.89)
- Image-Text Embedding Learning via Visual and Textual Semantic Reasoning (TPAMI 2022 · similarity 0.89)
- Composing Object Relations and Attributes for Image-Text Matching (CVPR 2024 · similarity 0.87)
- Improved Probabilistic Image-Text Representations (ICLR 2024 · similarity 0.87)
- VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks (ICLR 2025 · similarity 0.87)
- Text as Partial Constraint: Core–Residual Alignment for Robust Vision–Language Learning (NeurIPS 2026 · similarity 0.86)
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.
