paper-with-me

홈 › Papers

KRNet: Towards Efficient Knowledge Replay

2022-05-23 · Yingying Zhang, Qiaoyong Zhong, Di Xie, ShiLiang Pu

The knowledge replay technique has been widely used in many tasks such as continual learning and continuous domain adaptation. The key lies in how to effectively encode the knowledge extracted from previous data and replay them during current training procedure. A simple yet effective model to achieve knowledge replay is autoencoder. However, the number of stored latent codes in autoencoder increases linearly with the scale of data and the trained encoder is redundant for the replaying stage. In this paper, we propose a novel and efficient knowledge recording network (KRNet) which directly maps an arbitrary sample identity number to the corresponding datum. Compared with autoencoder, our KRNet requires significantly ($400\times$) less storage cost for the latent codes and can be trained without the encoder sub-network. Extensive experiments validate the efficiency of KRNet, and as a showcase, it is successfully applied in the task of continual learning.

📄 PDF Abstract BibTeX arXiv:2205.11126

Code (0)

등록된 구현이 없습니다.

Tasks

Continual LearningDomain Adaptation

Similar Papers 제목 키워드 기반

Bounded KRnet and its applications to density estimation and approximation

2023-05-15 · Li Zeng, Xiaoliang Wan, Tao Zhou

In this paper, we develop an invertible mapping, called B-KRnet, on a bounded domain and apply it to density estimation/approximation for data or the solutions of PDEs such as the Fokker-Planck equation and the Keller-Se…

Density Estimation

VAE-KRnet and its applications to variational Bayes

2020-06-29 · Xiaoliang Wan, Shuangqing Wei

In this work, we have proposed a generative model, called VAE-KRnet, for density estimation or approximation, which combines the canonical variational autoencoder (VAE) with our recently developed flow-based generative m…

Density EstimationDimensionality Reduction

Knowledge Rectification for Camouflaged Object Detection: Unlocking Insights from Low-Quality Data

2025-03-28 · Juwei Guan, Xiaolin Fang, Donghyun Kim, Haotian Gong 외

Low-quality data often suffer from insufficient image details, introducing an extra implicit aspect of camouflage that complicates camouflaged object detection (COD). Existing COD methods focus primarily on high-quality …

Diversityobject-detectionObject DetectionSuper-Resolution

Augmented KRnet for density estimation and approximation

2021-05-26 · Xiaoliang Wan, Kejun Tang

In this work, we have proposed augmented KRnets including both discrete and continuous models. One difficulty in flow-based generative modeling is to maintain the invertibility of the transport map, which is often a trad…

Density Estimation

Learning Knowledge Representation with Meta Knowledge Distillation for Single Image Super-Resolution

2022-07-18 · Han Zhu, Zhenzhong Chen, Shan Liu

Knowledge distillation (KD), which can efficiently transfer knowledge from a cumbersome network (teacher) to a compact network (student), has demonstrated its advantages in some computer vision applications. The represen…

Image Super-ResolutionKnowledge DistillationMeta-LearningSuper-Resolution