Modality-Balanced Models for Visual Dialogue

Abstract

The Visual Dialog task requires a model to exploit both image and conversational context information to generate the next response to the dialogue. However, via manual analysis, we find that a large number of conversational questions can be answered by only looking at the image without any access to the context history, while others still need the conversation context to predict the correct answers. We demonstrate that due to this reason, previous joint-modality (history and image) models over-rely on and are more prone to memorizing the dialogue history (e.g., by extracting certain keywords or patterns in the context information), whereas image-only models are more generalizable (because they cannot memorize or extract keywords from history) and perform substantially better at the primary normalized discounted cumulative gain (NDCG) task metric which allows multiple correct answers. Hence, this observation encourages us to explicitly maintain two models, i.e., an image-only model and an image-history joint model, and combine their complementary abilities for a more balanced multimodal model. We present multiple methods for this integration of the two models, via ensemble and consensus dropout fusion with shared parameters. Empirically, our models achieve strong results on the Visual Dialog challenge 2019 (rank 3 on NDCG and high balance across metrics), and substantially outperform the winner of the Visual Dialog challenge 2018 on most metrics.

Echo-Reconstruction: Audio-Augmented 3D Scene Reconstruction

“…Audio-visual learning: similar to its applications in natural language processing (NLP) and visual questing & answering systems [Hannan et al 2020;Kim et al 2020Kim et al , 2016, multi-modal learning using both audio-visual sensory inputs has also been used for classification tasks [Sterling et al 2018;Wilson et al 2019], audio-visual zooming [Nair et al 2019, and sound source separation [Ephrat et al 2018;Lee and Seung 2000] which have also isolated waves for specific generation tasks. Although similar in spirit, our audio-visual method, "Echoreconstruction, " differs from the existing methods by learning absorption and reflectance properties to detect a reflective surface, its depth, and material.…”