Papers with visual representation learning
Simple Temperature Cool-down in Contrastive Framework for Unsupervised Sentence Representation Learning (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing studies have focused on the effectiveness of contrastive learning in deep learning. |
| Approach: | They propose a method to improve sentence representation of unsupervised contrastive learning by examining the role of temperature in VRL and SRL. |
| Outcome: | The proposed method improves representation of unsupervised contrastive learning by cooling the temperature of the representation space. |
Bootstrap Your Own PLM: Boosting Semantic Features of PLMs for Unsuperivsed Contrastive Learning (2024.findings-eacl)
Copied to clipboard
| Challenge: | Existing studies have shown that SimCSE significantly improves the performance of pretrained language models on the sentence representation benchmark. |
| Approach: | They propose a method called IFM which reduces the tendency of contrastive models for VRL to rely on feature-suppressing shortcut solutions. |
| Outcome: | The proposed method reduces the tendency of contrastive models for VRL to rely on feature-suppressing shortcut solutions. |
A Simple Angle-based Approach for Contrastive Learning of Unsupervised Sentence Representation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | a promising baseline SimCSE has made notable breakthroughs in unsupervised SRL . however, there is still room for designing a novel contrastive framework specifically targeted for SRL. |
| Approach: | They propose an angle-based similarity function for a contrastive objective and propose a new approach for SRL. |
| Outcome: | The proposed approach shows better training dynamics on SRL than the standard cosine similarity function. |
Imagination and Contemplation: A Balanced Framework for Semantic-Augmented Multimodal Machine Translation (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Multimodal Machine Translation (MMT) is effective in resolving linguistic ambiguities, but visual information often introduces redundancy or noise, potentially impairing translation quality. |
| Approach: | They propose a semantic-augmented framework that integrates "Imagination" and "Contemplation" they first generate synthetic images from source text and align them with authentic images via an optimal transport loss . |
| Outcome: | The proposed framework outperforms baselines on translation datasets with visually ambiguous or weakly correlated content. |