Text-Only Training for Image Captioning using Noise-Injected CLIP (2022.findings-emnlp)
Copied to clipboard
| Challenge: | a new approach to image captioning requires large datasets of captioned images and is difficult to collect. |
| Approach: | They propose to use a decoder to translate CLIP textual embeddings back into text . they show that this intuition is “almost correct” because of a gap between the embeddable spaces . |
| Outcome: | The proposed approach shows that the intuition is “almost correct” because of a gap between the embedding spaces, and rectifies this via noise injection during training. |
Similar Papers
IFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing text-only training methods overlook the modality gap between using text data during training and employing images during inference. |
| Approach: | They propose a novel approach that aligns text features with visually relevant features to mitigate the modality gap between using text data during training and employing images during inference. |
| Outcome: | The proposed method outperforms the state-of-the-art methods in image captioning and video captioning by a significant margin compared to training with text data. |
TROPE: TRaining-Free Object-Part Enhancement for Seamlessly Improving Fine-Grained Zero-Shot Image Captioning (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to enhance zero-shot abilities in image captioning fail with fine-grained datasets. |
| Approach: | They propose a method to enhance captions with additional object-part details using object detector proposals and natural language processing techniques. |
| Outcome: | The proposed method improves performance on fine-grained datasets and improves on existing methods. |
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. |
CLIPText: A New Paradigm for Zero-shot Text Classification (2023.findings-acl)
Copied to clipboard
| Challenge: | Experimental results show that CLIP can be applied to zero-shot text classification tasks. |
| Approach: | They propose a CLIP model for zero-shot text classification that integrates prompt into CLIPText to better derive knowledge from CLIP. |
| Outcome: | The proposed model can be applied to a text-image matching problem and show that it can be used for language tasks. |
Zero-Shot Text Classification with Self-Training (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in large pretrained language models have increased attention to zero-shot text classification. |
| Approach: | They propose a plug-and-play method to bridge this gap by requiring only class names along with an unlabeled dataset. |
| Outcome: | The proposed model can be trained on a natural language inference dataset and performs on dozens of unseen tasks without the need for domain expertise or trial and error. |
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. |
ZEST: Zero-shot Learning from Text Descriptions using Textual Similarity and Visual Summarization (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Specifically, given birds’ images with free-text descriptions of their species, we learn to classify images of previously-unseen species based on specie descriptions. |
| Approach: | They propose to leverage the similarity between species and extract visual summaries from the texts to match visual features to the parts of the text that discuss them. |
| Outcome: | The proposed model outperforms the state-of-the-art on the largest benchmarks for text-based zero-shot learning. |
The Role of Data Curation in Image Captioning (2024.eacl-long)
Copied to clipboard
| Challenge: | Existing image captioning models treat all samples equally, neglecting mismatched data . Several other techniques have relied on curriculum learning strategies to adapt learning to the difficulty of the task. |
| Approach: | They propose to actively curate difficult samples in datasets using curriculum learning strategies to improve captioning models. |
| Outcome: | The proposed methods outperform existing models on the Flickr30K and COCO datasets. |
MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning (2023.acl-long)
Copied to clipboard
| Challenge: | Existing methods for supervised visual captioning require large scale of images or videos paired with descriptions in a specific language. |
| Approach: | They propose a zero-shot approach that generates captions for different scenarios without labeling . they use concept prompts to retrieve concepts and auto-encode them to learn writing styles . |
| Outcome: | The proposed approach generates captions for different scenarios and languages without labeled vision-caption pairs. |
Precision or Recall? An Analysis of Image Captions for Training Text-to-Image Generation Model (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in text-to-image models have demonstrated remarkable capabilities in image synthesis. |
| Approach: | They analyze the critical role of caption precision and recall in text-to-image model training. |
| Outcome: | The proposed model trains with synthetic captions that show similar behavior to those trained on human-annotated captions. |