Papers by Devi Parikh
SOrT-ing VQA Models : Contrastive Gradient Learning for Improved Consistency (2021.naacl-main)
Copied to clipboard
| Challenge: | Current visual question answering models are inconsistent in their understanding of the world . they answer difficult reasoning questions correctly but get associated sub-questions wrong . |
| Approach: | They propose a gradient-based interpretability approach to determine the questions most strongly correlated with the reasoning question on an image and a contrastive gradient learning based approach called Sub-question Oriented Tuning (SOrT). |
| Outcome: | The proposed approach improves model consistency by up to 6.5% points over existing approaches while improving visual grounding and robustness to rephrasings of questions. |
CoDraw: Collaborative Drawing as a Testbed for Grounded Goal-driven Communication (P19-1)
Copied to clipboard
Jin-Hwa Kim, Nikita Kitaev, Xinlei Chen, Marcus Rohrbach, Byoung-Tak Zhang, Yuandong Tian, Dhruv Batra, Devi Parikh
| Challenge: | a goal-driven collaborative drawing task combines language, perception, and actions in a partially observable environment . et al., 1990: 138K messages exchanged between human players. |
| Approach: | They propose a goal-driven collaborative task that combines language, perception, and action . they collect a clip art dataset and use it to build an image-drawing game between two agents . |
| Outcome: | The proposed task integrates language, perception, and action in a virtual world . it is based on a dataset of 10K dialogs and 138K messages exchanged between humans . |
CLEVR-Dialog: A Diagnostic Dataset for Multi-Round Reasoning in Visual Dialog (N19-1)
Copied to clipboard
| Challenge: | Visual Dialog is a multimodal task of answering a sequence of questions grounded in an image. |
| Approach: | They construct a dialog grammar that is grounded in the scene graphs of the images from the CLEVR dataset and use it to benchmark performance of standard visual dialog models. |
| Outcome: | The proposed model is based on a large diagnostic dataset for studying multi-round reasoning in visual dialog. |
Punny Captions: Witty Wordplay in Image Descriptions (N18-2)
Copied to clipboard
| Challenge: | Developing computational models that can produce contextually witty image descriptions is challenging because of the large corpus of sentences that are not available for large scale corpora. |
| Approach: | They propose to use linguistic wordplay, specifically puns, to generate witty image descriptions from large corpus of sentences or encode them via an encoder-decoder neural network architecture. |
| Outcome: | The proposed models perform better than baseline models using human data and show that they are slightly wittier than human-written witty descriptions. |
Do explanations make VQA models more predictable to a human? (D18-1)
Copied to clipboard
| Challenge: | Existing explanations of a model's behavior are not used in interactive tasks like Visual Question Answering (VQA). |
| Approach: | They analyze existing explanations and their role in making a VQA model more predictable to a human by using human-in-the-loop approaches that treat the model as a black-box. |
| Outcome: | The proposed explanations make a model more predictable to humans, whereas human-in-the-loop approaches treat it as a black-box do. |
Where Are You? Localization from Embodied Dialog (2020.emnlp-main)
Copied to clipboard
| Challenge: | Observer and Locator perform a cooperative localization task in a 3D environment. |
| Approach: | They propose a dataset of 6k dialogs in which two humans complete a cooperative localization task. |
| Outcome: | The proposed model achieves 32.7% success at identifying the Observer’s location within 3m in unseen buildings, vs. 70.4% for human Locators. |
Improving Generative Visual Dialog by Answering Diverse Questions (D19-1)
Copied to clipboard
| Challenge: | Prior work on training generative Visual Dialog models with reinforcement learning has shown that this improvement saturates and starts degrading after a few rounds of interaction, and does not lead to a better Visual Dialog model. |
| Approach: | They propose a Q-Bot-A-Bot image-guessing game that allows Q-BOT to ask diverse questions, thus reducing repetitions and enabling A-BOTT to explore a larger state space during RL. |
| Outcome: | The proposed approach improves Q-Bot-A-Bot image-guessing performance but degrades after a few rounds of interaction and does not lead to a better Visual Dialog model. |
VISITRON: Visual Semantics-Aligned Interactively Trained Object-Navigator (2022.findings-acl)
Copied to clipboard
Ayush Shrivastava, Karthik Gopalakrishnan, Yang Liu, Robinson Piramuthu, Gokhan Tur, Devi Parikh, Dilek Hakkani-Tur
| Challenge: | Interactive robots navigating photo-realistic environments need to be trained to handle dynamic nature of dialogue and vision-and-language navigation (VLN). |
| Approach: | They propose a Transformer-based multi-modal navigator that is better suited to the interactive regime inherent to Cooperative Vision-and-Dialog Navigation (CVDN). |
| Outcome: | The proposed model is trained to identify and associate object-level concepts and semantics between the environment and dialogue history and identify when to interact vs. navigate via imitation learning of a binary classification head. |