paper-with-me

Papers

Cross-Task Knowledge Transfer for Visually-Grounded Navigation

2019-05-01 · ICLR 2019 5 · Devendra Singh Chaplot, Lisa Lee, Ruslan Salakhutdinov, Devi Parikh, Dhruv Batra

Recent efforts on training visual navigation agents conditioned on language using deep reinforcement learning have been successful in learning policies for two different tasks: learning to follow navigational instructions and embodied question answering. In this paper, we aim to learn a multitask model capable of jointly learning both tasks, and transferring knowledge of words and their grounding in visual objects across tasks. The proposed model uses a novel Dual-Attention unit to disentangle the knowledge of words in the textual representations and visual objects in the visual representations, and align them with each other. This disentangled task-invariant alignment of representations facilitates grounding and knowledge transfer across both tasks. We show that the proposed model outperforms a range of baselines on both tasks in simulated 3D environments. We also show that this disentanglement of representations makes our model modular, interpretable, and allows for zero-shot transfer to instructions containing new words by leveraging object detectors.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningDisentanglementEmbodied Question AnsweringQuestion AnsweringReinforcement LearningTransfer LearningVisual Navigation

Similar Papers 제목 키워드 기반

On the Transferability of Visually Grounded PCFGs

2023-10-21 · Yanpeng Zhao, Ivan Titov

There has been a significant surge of interest in visually grounded grammar induction in recent times. While a variety of models have been developed for the task and have demonstrated impressive performance, they have no…

Transfer Learning

VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning

2022-03-20 · CVPR 2022 1 · Wenjia Xu, Yongqin Xian, Jiuniu Wang, Bernt Schiele 외

Human-annotated attributes serve as powerful semantic embeddings in zero-shot learning. However, their annotation process is labor-intensive and needs expert supervision. Current unsupervised semantic embeddings, i.e., w…

Transfer LearningWord EmbeddingsZero-Shot Learning

Hindi as a Second Language: Improving Visually Grounded Speech with Semantically Similar Samples

2023-03-30 · Hyeonggon Ryu, Arda Senocak, In So Kweon, Joon Son Chung

The objective of this work is to explore the learning of visually grounded speech models (VGS) from multilingual perspective. Bilingual VGS models are generally trained with an equal number of spoken captions from both l…

Cross-Modal RetrievalRetrieval

Improving the Efficiency of Visually Augmented Language Models

2024-09-17 · Paula Ontalvilla, Aitor Ormazabal, Gorka Azkune

Despite the impressive performance of autoregressive Language Models (LM) it has been shown that due to reporting bias, LMs lack visual knowledge, i.e. they do not know much about the visual world and its properties. To …

Image GenerationImage RetrievalLanguage ModelingLanguage Modelling+2

K-MaT: Knowledge-Anchored Manifold Transport for Cross-Modal Prompt Learning in Medical Imaging

2026-03-06 · Jiajun Zeng, Shadi Albarqouni arxiv

Large-scale biomedical vision-language models (VLMs) adapted on high-end imaging (e.g., CT) often fail to transfer to frontline low-end modalities (e.g., radiography), collapsing into modality-specific shortcuts. We prop…