Collaborative Learning With Disentangled Features for Zero-Shot Domain Adaptation

2021-01-01 · ICCV 2021 10 · Won Young Jhoo, Jae-Pil Heo

Typical domain adaptation techniques aim to transfer label information from a label-rich source domain to a label-scarce target domain in the same label space. However, it is often hard to get even the unlabeled target domain data of a task of interest. In such a case, we can capture the domain shift between the source domain and target domain from an unseen task and transfer it to the task of interest, which is known as zero-shot domain adaptation (ZSDA). Existing state-of-the-art methods for ZSDA attempted to generate target domain data. However, training such generative models causes significant computational overhead and is hardly optimized. In this paper, we propose a novel ZSDA method that learns a task-agnostic domain shift by collaborative training of domain-invariant semantic features and task-invariant domain features via adversarial learning. Meanwhile, the spatial attention map is learned from disentangled feature representations to selectively emphasize the domain-specific salient parts of the domain-invariant features. Experimental results show that our ZSDA method achieves state-of-the-art performance on several benchmarks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation

Zero-Shot Policy Transfer with Disentangled Attention

2019-09-25 · Josh Roy, George Konidaris

Domain adaptation is an open problem in deep reinforcement learning (RL). Often, agents are asked to perform in environments where data is difficult to obtain. In such settings, agents are trained in similar environments…

Deep Reinforcement Learning Domain Adaptation Reinforcement Learning (RL)Representation Learning

Domain Disentangled Generative Adversarial Network for Zero-Shot Sketch-Based 3D Shape Retrieval

2022-02-24 · Rui Xu, Zongyan Han, Le Hui, Jianjun Qian 외

Sketch-based 3D shape retrieval is a challenging task due to the large domain discrepancy between sketches and 3D shapes. Since existing methods are trained and evaluated on the same categories, they cannot effectively r…

3D Shape Retrieval Generative Adversarial Network Retrieval Word Embeddings

DARLA: Improving Zero-Shot Transfer in Reinforcement Learning

2017-07-26 · ICML 2017 8 · Irina Higgins, Arka Pal, Andrei A. Rusu, Loic Matthey 외

Domain adaptation is an important open problem in deep reinforcement learning (RL). In many scenarios of interest data is hard to obtain, so agents may learn a source policy in a setting where data is readily available, …

Deep Reinforcement Learning Domain Adaptation reinforcement-learning Reinforcement Learning+2

ZstGAN: An Adversarial Approach for Unsupervised Zero-Shot Image-to-Image Translation

2019-06-01 · Jianxin Lin, Yingce Xia, Sen Liu, Shuqin Zhao 외

Image-to-image translation models have shown remarkable ability on transferring images among different domains. Most of existing work follows the setting that the source domain and target domain keep the same at training…

Attribute Image Generation Image-to-Image Translation Translation+1

A Generalizable Physics-guided Causal Model for Trajectory Prediction in Autonomous Driving

2026-02-15 · Zhenyu Zong, Yuchen Wang, Haohong Lin, Lu Gan 외 arxiv

Trajectory prediction for traffic agents is critical for safe autonomous driving. However, achieving effective zero-shot generalization in previously unseen domains remains a significant challenge. Motivated by the consi…

Zero-shot Generalization Trajectory Prediction Autonomous Driving