Decoupled Box Proposal and Featurization with Ultrafine-Grained Semantic Labels Improve Image Captioning and Visual Question Answering (D19-1)
Copied to clipboard
| Challenge: | Object detection is used in vision and language tasks but is expensive to learn . popular models rely on annotating ground-truths for bounding boxes and semantic labels . empirically, object detection leads to effective transfer learning and improved captioning and visual question answering models . |
| Approach: | They examine the effect of decoupling box proposal and featurization on down-stream tasks . they propose a family of "two-stage" object detectors that propose category-agnostic bounding boxes . |
| Outcome: | The proposed method improves image captioning and visual question answering models by leveraging large amounts of labeled annotations. |
Similar Papers
Defoiling Foiled Image Captions (N18-2)
Copied to clipboard
| Challenge: | Existing models for vision-to-language tasks do not understand images sufficiently, despite their impressive performance. |
| Approach: | They propose to use explicit object information to solve foiled caption detection problem . they propose to replace a word in caption with a semantically similar word . |
| Outcome: | The proposed model achieves state-of-the-art on a recently published dataset with scores exceeding those achieved by humans on the task. |
Fusion of Detected Objects in Text for Visual Question Answering (D19-1)
Copied to clipboard
| Challenge: | Recent neural architectures such as Transformer and BERT allow for multimodal context, which may help model the meaning of words in general and also sharpen its understanding of instances of words. |
| Approach: | They propose a neural architecture that combines vision and natural language to advance models of multimodal context. |
| Outcome: | The proposed architecture achieves the highest performance on the Visual Commonsense Reasoning benchmark and the best performance to date on the public leaderboard. |
On Advances in Text Generation from Images Beyond Captioning: A Case Study in Self-Rationalization (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Combining visual modality with pretrained language models has been effective for descriptive tasks such as image captioning. |
| Approach: | They ask: do multimodal models combine visual and visual adapted language models? they find that CLIP image representations and scaling of language models do not consistently improve self-rationalization in multimodal tasks. |
| Outcome: | The proposed model types do not consistently improve self-rationalization in multimodal tasks. |
Infusing Finetuning with Semantic Dependencies (2021.tacl-1)
Copied to clipboard
| Challenge: | Several diagnostics help to localize the benefits of our approach. |
| Approach: | They apply convolutional graph encoders to integrate semantic parses into task-specific finetuning. |
| Outcome: | The proposed approach yields benefits to natural language understanding (NLU) tasks in the GLUE benchmark. |
ReCAP: Semantic Role Enhanced Caption Generation (2024.lrec-main)
Copied to clipboard
| Challenge: | Current vision language models lack specificity and overlook various aspects of the image. |
| Approach: | They propose to use semantic roles as control signals to guide captions to specific argument structures by focusing on specific objects and their associated semantic roles instead of general descriptions. |
| Outcome: | The proposed framework produces captions that exhibit enhanced quality, diversity, and controllability. |
Cross-lingual Transfer or Machine Translation? On Data Augmentation for Monolingual Semantic Textual Similarity (2024.lrec-main)
Copied to clipboard
| Challenge: | Using labeled NLI datasets for learning sentence embeddings leads to improved performance for natural language understanding tasks. |
| Approach: | They compare two data augmentation techniques for learning better sentence embeddings . they use a cross-lingual transfer technique that exploits English resources as training data to yield non-English sentence embeds as zero-shot inference . |
| Outcome: | The proposed techniques yield better performance on Japanese and Korean sentences. |
On the Importance of Delexicalization for Fact Verification (D19-1)
Copied to clipboard
| Challenge: | Neural networks (NNs) perform state-of-the-art (SOA) performance in many complex tasks. |
| Approach: | They investigate the importance that a model assigns to various aspects of data . they experiment with two strategies of masking to mitigate this dependence on lexicalized information . |
| Outcome: | The proposed model improves on the in-domain dataset by 10% compared to the fully lexicalized model. |
Exploring Data Augmentation for Code Generation Tasks (2023.findings-eacl)
Copied to clipboard
| Challenge: | Recent advances in natural language processing have impacted how models are trained for programming language tasks. |
| Approach: | They propose to use augmentation methods that yield consistent improvements in code translation and summarization by up to 6.9% and 7.5% respectively. |
| Outcome: | The proposed methods improve translation and summarization by 6.9% and 7.5% respectively. |
Grounding Semantic Roles in Images (D18-1)
Copied to clipboard
| Challenge: | Experimental results show that visual semantic role labeling is useful for text understanding . image-based role annotations are prohibitive, but the model induces frame-semantic visual representations . |
| Approach: | They propose to train a visual semantic role labeling model without prohibitive image annotations . they render candidate participants as image regions of objects and train vSRL model which learns to ground roles in the regions which depict the corresponding participant . |
| Outcome: | The proposed model trains without prohibitive image-based role annotations without prohibiting image-related annotations. |
On Efficient Language and Vision Assistants for Visually-Situated Natural Language Understanding: What Matters in Reading and Reasoning (2024.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in language and vision assistants have showcased impressive capabilities but suffer from a lack of transparency, limiting broader research and reproducibility. |
| Approach: | They propose to redefine the design of vision-language models by identifying key components and creating efficient models with constrained inference costs. |
| Outcome: | The proposed models achieve significant improvements in inference throughput while maintaining high performance. |