홈 › Papers

Class-Incremental Domain Adaptation

2020-08-04 · ECCV 2020 8 · Jogendra Nath Kundu, Rahul Mysore Venkatesh, Naveen Venkat, Ambareesh Revanur, R. Venkatesh Babu

We introduce a practical Domain Adaptation (DA) paradigm called Class-Incremental Domain Adaptation (CIDA). Existing DA methods tackle domain-shift but are unsuitable for learning novel target-domain classes. Meanwhile, class-incremental (CI) methods enable learning of new classes in absence of source training data but fail under a domain-shift without labeled supervision. In this work, we effectively identify the limitations of these approaches in the CIDA paradigm. Motivated by theoretical and empirical observations, we propose an effective method, inspired by prototypical networks, that enables classification of target samples into both shared and novel (one-shot) target classes, even under a domain-shift. Our approach yields superior performance as compared to both DA and CI methods in the CIDA paradigm.

📄 PDF Abstract BibTeX arXiv:2008.01389

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Adaptation

Methods 이 논문이 사용한 방법론

CIDA Continuously Indexed Domain Adaptation combines traditional adversarial adaptation with a novel discriminator that models the encoding-conditioned domain index…

Incremental Open-set Domain Adaptation

2024-08-31 · Sayan Rakshit, Hmrishav Bandyopadhyay, Nibaran Das, Biplab Banerjee

Catastrophic forgetting makes neural network models unstable when learning visual domains consecutively. The neural network model drifts to catastrophic forgetting-induced low performance of previously learnt domains whe…

Domain Adaptation image-classification Image Classification Incremental Learning

Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation

2022-07-22 · Hongbin Lin, Yifan Zhang, Zhen Qiu, Shuaicheng Niu 외

This paper studies a new, practical but challenging problem, called Class-Incremental Unsupervised Domain Adaptation (CI-UDA), where the labeled source domain contains all classes, but the classes in the unlabeled target…

Domain Adaptation Unsupervised Domain Adaptation

FRIDA -- Generative Feature Replay for Incremental Domain Adaptation

2021-12-28 · Sayan Rakshit, Anwesh Mohanty, Ruchika Chavhan, Biplab Banerjee 외

We tackle the novel problem of incremental unsupervised domain adaptation (IDA) in this paper. We assume that a labeled source domain and different unlabeled target domains are incrementally observed with the constraint …

Domain Adaptation Generative Adversarial Network Unsupervised Domain Adaptation

DiffClass: Diffusion-Based Class Incremental Learning

2024-03-08 · Zichong Meng, Jie Zhang, Changdi Yang, Zheng Zhan 외

Class Incremental Learning (CIL) is challenging due to catastrophic forgetting. On top of that, Exemplar-free Class Incremental Learning is even more challenging due to forbidden access to previous task data. Recent exem…

class-incremental learning Class Incremental Learning Domain Adaptation Exemplar-Free+2

Versatile Incremental Learning: Towards Class and Domain-Agnostic Incremental Learning

2024-09-17 · Min-Yeong Park, Jae-Ho Lee, Gyeong-Moon Park

Incremental Learning (IL) aims to accumulate knowledge from sequential input tasks while overcoming catastrophic forgetting. Existing IL methods typically assume that an incoming task has only increments of classes or do…

Incremental Learning