Pradyumna Narayana


2023

pdf
KAFA: Rethinking Image Ad Understanding with Knowledge-Augmented Feature Adaptation of Vision-Language Models
Zhiwei Jia | Pradyumna Narayana | Arjun Akula | Garima Pruthi | Hao Su | Sugato Basu | Varun Jampani
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)

Image ad understanding is a crucial task with wide real-world applications. Although highly challenging with the involvement of diverse atypical scenes, real-world entities, and reasoning over scene-texts, how to interpret image ads is relatively under-explored, especially in the era of foundational vision-language models (VLMs) featuring impressive generalizability and adaptability. In this paper, we perform the first empirical study of image ad understanding through the lens of pre-trained VLMs. We benchmark and reveal practical challenges in adapting these VLMs to image ad understanding. We propose a simple feature adaptation strategy to effectively fuse multimodal information for image ads and further empower it with knowledge of real-world entities. We hope our study draws more attention to image ad understanding which is broadly relevant to the advertising industry.

2022

pdf
CPL: Counterfactual Prompt Learning for Vision and Language Models
Xuehai He | Diji Yang | Weixi Feng | Tsu-Jui Fu | Arjun Akula | Varun Jampani | Pradyumna Narayana | Sugato Basu | William Yang Wang | Xin Wang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Prompt tuning is a new few-shot transfer learning technique that only tunes the learnable prompt for pre-trained vision and language models such as CLIP. However, existing prompt tuning methods tend to learn spurious or entangled representations, which leads to poor generalization to unseen concepts. Towards non-spurious and efficient prompt learning from limited examples, this paper presents a novel Counterfactual Prompt Learning (CPL) method for vision and language models, which simultaneously employs counterfactual generation and contrastive learning in a joint optimization framework. Particularly, CPL constructs counterfactual by identifying minimal non-spurious feature change between semantically-similar positive and negative samples that causes concept change, and learns more generalizable prompt representation from both factual and counterfactual examples via contrastive learning. Extensive experiments demonstrate that CPL can obtain superior few-shot performance on different vision and language tasks than previous prompt tuning methods on CLIP. On image classification, we achieve 3.55% average relative improvement on unseen classes across seven datasets; on image-text retrieval and visual question answering, we gain up to 4.09% and 25.08% relative improvements across three few-shot scenarios on unseen test sets respectively.

pdf
Diagnosing Vision-and-Language Navigation: What Really Matters
Wanrong Zhu | Yuankai Qi | Pradyumna Narayana | Kazoo Sone | Sugato Basu | Xin Wang | Qi Wu | Miguel Eckstein | William Yang Wang
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Vision-and-language navigation (VLN) is a multimodal task where an agent follows natural language instructions and navigates in visual environments. Multiple setups have been proposed, and researchers apply new model architectures or training techniques to boost navigation performance. However, there still exist non-negligible gaps between machines’ performance and human benchmarks. Moreover, the agents’ inner mechanisms for navigation decisions remain unclear. To the best of our knowledge, how the agents perceive the multimodal input is under-studied and needs investigation. In this work, we conduct a series of diagnostic experiments to unveil agents’ focus during navigation. Results show that indoor navigation agents refer to both object and direction tokens when making decisions. In contrast, outdoor navigation agents heavily rely on direction tokens and poorly understand the object tokens. Transformer-based agents acquire a better cross-modal understanding of objects and display strong numerical reasoning ability than non-Transformer-based agents. When it comes to vision-and-language alignments, many models claim that they can align object tokens with specific visual targets. We find unbalanced attention on the vision and text input and doubt the reliability of such cross-modal alignments.

2021

pdf
Multimodal Text Style Transfer for Outdoor Vision-and-Language Navigation
Wanrong Zhu | Xin Wang | Tsu-Jui Fu | An Yan | Pradyumna Narayana | Kazoo Sone | Sugato Basu | William Yang Wang
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

One of the most challenging topics in Natural Language Processing (NLP) is visually-grounded language understanding and reasoning. Outdoor vision-and-language navigation (VLN) is such a task where an agent follows natural language instructions and navigates in real-life urban environments. With the lack of human-annotated instructions that illustrate the intricate urban scenes, outdoor VLN remains a challenging task to solve. In this paper, we introduce a Multimodal Text Style Transfer (MTST) learning approach and leverage external multimodal resources to mitigate data scarcity in outdoor navigation tasks. We first enrich the navigation data by transferring the style of the instructions generated by Google Maps API, then pre-train the navigator with the augmented external outdoor navigation dataset. Experimental results show that our MTST learning approach is model-agnostic, and our MTST approach significantly outperforms the baseline models on the outdoor VLN task, improving task completion rate by 8.7% relatively on the test set.

2020

pdf
Towards Understanding Sample Variance in Visually Grounded Language Generation: Evaluations and Observations
Wanrong Zhu | Xin Wang | Pradyumna Narayana | Kazoo Sone | Sugato Basu | William Yang Wang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

A major challenge in visually grounded language generation is to build robust benchmark datasets and models that can generalize well in real-world settings. To do this, it is critical to ensure that our evaluation protocols are correct, and benchmarks are reliable. In this work, we set forth to design a set of experiments to understand an important but often ignored problem in visually grounded language generation: given that humans have different utilities and visual attention, how will the sample variance in multi-reference datasets affect the models’ performance? Empirically, we study several multi-reference datasets and corresponding vision-and-language tasks. We show that it is of paramount importance to report variance in experiments; that human-generated references could vary drastically in different datasets/tasks, revealing the nature of each task; that metric-wise, CIDEr has shown systematically larger variances than others. Our evaluations on reference-per-instance shed light on the design of reliable datasets in the future.

2017

pdf
Communicating and Acting: Understanding Gesture in Simulation Semantics
Nikhil Krishnaswamy | Pradyumna Narayana | Isaac Wang | Kyeongmin Rim | Rahul Bangar | Dhruva Patil | Gururaj Mulay | Ross Beveridge | Jaime Ruiz | Bruce Draper | James Pustejovsky
Proceedings of the 12th International Conference on Computational Semantics (IWCS) — Short papers

pdf
Creating Common Ground through Multimodal Simulations
James Pustejovsky | Nikhil Krishnaswamy | Bruce Draper | Pradyumna Narayana | Rahul Bangar
Proceedings of the IWCS workshop on Foundations of Situated and Multimodal Communication