| Challenge: | Contrastive language-image pre-training models have demonstrated considerable success across various vision-language tasks, such as text-to-image retrieval. |
| Approach: | They propose a fine-tuning approach to enhance the representations of CLIP models for paraphrases by leveraging large language models. |
| Outcome: | The proposed model improves on baseline models across paraphrased retrieval, visual genome relation and attribution, and seven semantic textual similarity tasks. |
Similar Papers
AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to build a strong multilingual multimodal representation model are lacking in good-quality text-image pairs. |
| Approach: | They propose a method to build a strong multilingual multimodal representation model using English text-image pairs instead of a model from scratch. |
| Outcome: | The proposed model outperforms the original CLIP model on multilingual multimodal benchmarks. |
Fine-grained Image Captioning with CLIP Reward (2022.findings-naacl)
Copied to clipboard
| Challenge: | Modern image captioning models are usually trained with text similarity objectives . reference captions often describe only the most salient objects in images . |
| Approach: | They propose to use CLIP to calculate multi-modal similarity and use it as a reward function . they propose a simple finetuning strategy to improve grammar that does not require extra text annotation. |
| Outcome: | The proposed model generates more distinctive captions than the CIDEroptimized model on text-to-image retrieval and fineCapEval. |
ComCLIP: Training-Free Compositional Image and Text Matching (2024.naacl-long)
Copied to clipboard
| Challenge: | erroneous semantics of individual entities are essentially confounders that cause the matching failure. |
| Approach: | They propose a training-free compositional CLIP model which disentangles input images into subjects, objects, and action subimages and composes CLIP’s vision encoder and text encoder to perform evolving matching over compositional text embedding and subimage embeddments. |
| Outcome: | The proposed model mitigates spurious correlations introduced by the pretrained CLIP models and dynamically evaluates the importance of each component. |
CLIP4IDC: CLIP for Image Difference Captioning (2022.aacl-short)
Copied to clipboard
| Challenge: | Conventional approaches learn an IDC model with a pre-trained and usually frozen visual feature extractor. |
| Approach: | They propose to transfer a CLIP model to the downstream IDC task to address two major issues: (1) a large domain gap exists between the pre-training datasets used for training such a visual feature extractor; (2) the visual feature extraction often does not effectively encode the visual changes between two images. |
| Outcome: | Experiments on three IDC benchmark datasets show the proposed model performs well. |
LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning (2023.acl-short)
Copied to clipboard
| Challenge: | Recent advances in pre-trained language models have been limited when fine-tuned on small datasets. |
| Approach: | They propose to add contrastive learning to prompt-based fine-tuning to improve model performance. |
| Outcome: | The proposed approach outperforms other methods on multiple text classification benchmarks. |
Paraphrase-based Contrastive Learning for Sentence Pair Modeling (2025.naacl-srw)
Copied to clipboard
| Challenge: | Existing methods to improve performance of sentence pair modeling are not available on a large-scale for non-English languages. |
| Approach: | They propose a method to apply contrastive learning to pre-trained masked language models . they use sentence embeddings of paraphrase pairs to make similar sentences . |
| Outcome: | The proposed method can be used on four sentence pair modeling tasks in English and Japanese. |
Cross-lingual and Multilingual CLIP (2022.lrec-1)
Copied to clipboard
| Challenge: | OpenAI released CLIP, a model that relates the textual and visual domains with unprecedented accuracy. |
| Approach: | They propose to use cross-lingual teacher learning to re-train an English textual encoder using a large dataset of images and captions. |
| Outcome: | The proposed method outperforms baselines on multilingual image-text retrieval while retaining low cost. |
Controllable Paraphrase Generation for Semantic and Lexical Similarities (2024.lrec-main)
Copied to clipboard
| Challenge: | Lexically diverse paraphrases are crucial in data augmentation because they enhance the linguistic diversity of the corpus. |
| Approach: | They propose a controllable model for semantic and lexical similarities by attaching tags to the head of the input sentence. |
| Outcome: | The proposed model can paraphrase an input sentence according to the tags specified. |
Paraphrastic Representations at Scale (2022.emnlp-demos)
Copied to clipboard
| Challenge: | a new system allows users to train their own state-of-the-art paraphrastic sentence representations in a variety of languages. |
| Approach: | They propose a system that allows users to train their own paraphrastic sentence representations in a variety of languages. |
| Outcome: | The proposed models outperform previous models on monolingual and cross-lingual tasks and can be used on CPUs with little difference in inference speed. |
Leaner and Faster: Two-Stage Model Compression for Lightweight Text-Image Retrieval (2022.naacl-main)
Copied to clipboard
| Challenge: | Existing text-image approaches use pre-trained vision-language representations for text retrieval . however, these models pose non-trivial memory requirements and substantial indexing time . |
| Approach: | They propose a framework to compress large pre-trained dual-encoders for lightweight text-image retrieval. |
| Outcome: | The proposed model performs better on Flickr30K and MSCOCO benchmarks than the original full model on mobile devices. |