The knowledge extracted by the delegator is then utilized to maintain the performance of the model on old tasks in incremental learning.
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 particular, we develop a novel cross-channel feature augmentation module, which is a combo of map-attend-group-map operations.
Surprisingly, by varying the granularity of division on feature maps, we are able to modulate the reconstruction capability of the model for both normal and abnormal samples.
Object detection involves two sub-tasks, i. e. localizing objects in an image and classifying them into various categories.
The key lies in the design of the graph structure, which encodes skeleton topology information.
no code implementations • 26 Apr 2020 • Qi She, Fan Feng, Qi Liu, Rosa H. M. Chan, Xinyue Hao, Chuanlin Lan, Qihan Yang, Vincenzo Lomonaco, German I. Parisi, Heechul Bae, Eoin Brophy, Baoquan Chen, Gabriele Graffieti, Vidit Goel, Hyonyoung Han, Sathursan Kanagarajah, Somesh Kumar, Siew-Kei Lam, Tin Lun Lam, Liang Ma, Davide Maltoni, Lorenzo Pellegrini, Duvindu Piyasena, ShiLiang Pu, Debdoot Sheet, Soonyong Song, Youngsung Son, Zhengwei Wang, Tomas E. Ward, Jianwen Wu, Meiqing Wu, Di Xie, Yangsheng Xu, Lin Yang, Qiaoyong Zhong, Liguang Zhou
This report summarizes IROS 2019-Lifelong Robotic Vision Competition (Lifelong Object Recognition Challenge) with methods and results from the top $8$ finalists (out of over~$150$ teams).
The key lies in generalization of prior knowledge learned from large-scale base classes and fast adaptation of the classifier to novel classes.
By sharing the convolution kernels of different views, spatial and temporal features are collaboratively learned and thus benefit from each other.
In particular, we propose a novel multi-stage training strategy which learns incremental triplet margin and improves triplet loss effectively.
Skeleton-based human action recognition has recently drawn increasing attentions with the availability of large-scale skeleton datasets.
Ranked #2 on Skeleton Based Action Recognition on PKU-MMD
Deep region-based object detector consists of a region proposal step and a deep object recognition step.
Current state-of-the-art approaches to skeleton-based action recognition are mostly based on recurrent neural networks (RNN).
Ranked #3 on Skeleton Based Action Recognition on PKU-MMD