Arushi Goel
Research Subjects
Arushi Goel has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Andre Araujo
Google DeepMind
1 shared publication Basura Fernando
AI3, Institute of High Performance Computing, A*STAR
1 shared publication- Fei Sha
Ocean Univ. of China
1 shared publication - Felipe Cadar
Universidade Federal de Minas Gerais
1 shared publication Hakan Bilen
University of Edinburgh
1 shared publication- Hakan Bilen
The University of Edinburgh
1 shared publication
Latest Publications
- Open Access
Visually Interpretable Subtask Reasoning for Visual Question Answering
Answering complex visual questions like `Which red furniture can be used for sitting?' requires multi-step reasoning, including object recognition, attribute filtering, and relational understanding. Recent work improves interpretability in multimodal large language models (MLLMs) by decomposing tasks into sub-task programs, but these methods are computationally expensive and less accurate due to poor adaptation to target data. To address this, we introduce VISTAR (Visually Interpretable Subtask-Aware Reasoning Model), a subtask-driven training framework that enhances both interpretability and reasoning by generating textual and visual explanations within MLLMs. Instead of relying on external models, VISTAR fine-tunes MLLMs to produce structured Subtask-of-Thought rationales (step-by-step reasoning sequences). Experiments on two benchmarks show that VISTAR consistently improves reasoning accuracy while maintaining interpretability. Our code and dataset will be available at https://github.com/ChengJade/VISTAR.
Open AccessVisually Interpretable Subtask Reasoning for Visual Question Answering
Answering complex visual questions like `Which red furniture can be used for sitting?' requires multi-step reasoning, including object recognition, attribute filtering, and relational understanding. Recent work improves interpretability in multimodal large language models (MLLMs) by decomposing tasks into sub-task programs, but these methods are computationally expensive and less accurate due to poor adaptation to target data. To address this, we introduce VISTAR (Visually Interpretable Subtask-Aware Reasoning Model), a subtask-driven training framework that enhances both interpretability and reasoning by generating textual and visual explanations within MLLMs. Instead of relying on external models, VISTAR fine-tunes MLLMs to produce structured Subtask-of-Thought rationales (step-by-step reasoning sequences). Experiments on two benchmarks show that VISTAR consistently improves reasoning accuracy while maintaining interpretability. Our code and dataset will be available at https://github.com/ChengJade/VISTAR.
- Open Access
Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories
We propose Encyclopedic-VQA, a large scale visual question answering (VQA) dataset featuring visual questions about detailed properties of fine-grained categories and instances. It contains 221k unique question+answer pairs each matched with (up to) 5 images, resulting in a total of 1M VQA samples. Moreover, our dataset comes with a controlled knowledge base derived from Wikipedia, marking the evidence to support each answer. Empirically, we show that our dataset poses a hard challenge for large vision+language models as they perform poorly on our dataset: PaLI [14] is state-of-the-art on OK-VQA [37], yet it only achieves 13.0% accuracy on our dataset. Moreover, we experimentally show that progress on answering our encyclopedic questions can be achieved by augmenting large models with a mechanism that retrieves relevant information from the knowledge base. An oracle experiment with perfect retrieval achieves 87.0% accuracy on the single-hop portion of our dataset, and an automatic retrieval-augmented prototype yields 48.8%. We believe that our dataset enables future research on retrieval-augmented vision+language models. It is available at https://github.com/google-research/google-research/tree/master/encyclopedic_vqa .
Open AccessEncyclopedic VQA: Visual questions about detailed properties of fine-grained categories
We propose Encyclopedic-VQA, a large scale visual question answering (VQA) dataset featuring visual questions about detailed properties of fine-grained categories and instances. It contains 221k unique question+answer pairs each matched with (up to) 5 images, resulting in a total of 1M VQA samples. Moreover, our dataset comes with a controlled knowledge base derived from Wikipedia, marking the evidence to support each answer. Empirically, we show that our dataset poses a hard challenge for large vision+language models as they perform poorly on our dataset: PaLI [14] is state-of-the-art on OK-VQA [37], yet it only achieves 13.0% accuracy on our dataset. Moreover, we experimentally show that progress on answering our encyclopedic questions can be achieved by augmenting large models with a mechanism that retrieves relevant information from the knowledge base. An oracle experiment with perfect retrieval achieves 87.0% accuracy on the single-hop portion of our dataset, and an automatic retrieval-augmented prototype yields 48.8%. We believe that our dataset enables future research on retrieval-augmented vision+language models. It is available at https://github.com/google-research/google-research/tree/master/encyclopedic_vqa .
- 1 January 2020
- Published by Springer Nature
- p. 369-385
Injecting Prior Knowledge into Image Caption Generation
- 1 January 2020
- Published by Springer Nature
- p. 369-385
Injecting Prior Knowledge into Image Caption Generation
- Open Access
Cross-Domain Image Classification through Neural-Style Transfer Data Augmentation
In particular, the lack of sufficient amounts of domain-specific data can reduce the accuracy of a classifier. In this paper, we explore the effects of style transfer-based data transformation on the accuracy of a convolutional neural network classifiers in the context of automobile detection under adverse winter weather conditions. The detection of automobiles under highly adverse weather conditions is a difficult task as such conditions present large amounts of noise in each image. The InceptionV2 architecture is trained on a composite dataset, consisting of either normal car image dataset , a mixture of normal and style transferred car images, or a mixture of normal car images and those taken at blizzard conditions, at a ratio of 80:20. All three classifiers are then tested on a dataset of car images taken at blizzard conditions and on vehicle-free snow landscape images. We evaluate and contrast the effectiveness of each classifier upon each dataset, and discuss the strengths and weaknesses of style-transfer based approaches to data augmentation.
Open AccessCross-Domain Image Classification through Neural-Style Transfer Data Augmentation
In particular, the lack of sufficient amounts of domain-specific data can reduce the accuracy of a classifier. In this paper, we explore the effects of style transfer-based data transformation on the accuracy of a convolutional neural network classifiers in the context of automobile detection under adverse winter weather conditions. The detection of automobiles under highly adverse weather conditions is a difficult task as such conditions present large amounts of noise in each image. The InceptionV2 architecture is trained on a composite dataset, consisting of either normal car image dataset , a mixture of normal and style transferred car images, or a mixture of normal car images and those taken at blizzard conditions, at a ratio of 80:20. All three classifiers are then tested on a dataset of car images taken at blizzard conditions and on vehicle-free snow landscape images. We evaluate and contrast the effectiveness of each classifier upon each dataset, and discuss the strengths and weaknesses of style-transfer based approaches to data augmentation.