Search Results for author:
Found 21 papers, 12 papers with code
Masked Image Residual Learning for Scaling Deeper Vision Transformers
With the same level of computational complexity as ViT-Base and ViT-Large, we instantiate 4. 5$\times$ and 2$\times$ deeper ViTs, dubbed ViT-S-54 and ViT-B-48.
Self-Evolved Dynamic Expansion Model for Task-Free Continual Learning
In this paper, we propose a novel and effective framework for TFCL, which dynamically expands the architecture of a DEM model through a self-assessment mechanism evaluating the diversity of knowledge among existing experts as expansion signals.
Wasserstein Expansible Variational Autoencoder for Discriminative and Generative Continual Learning
Despite promising achievements by the Variational Autoencoder (VAE) mixtures in continual learning, such methods ignore the redundancy among the probabilistic representations of their components when performing model expansion, leading to mixture components learning similar tasks.
Dynamic Appearance: A Video Representation for Action Recognition with Joint Training
Static appearance of video may impede the ability of a deep neural network to learn motion-relevant features in video action recognition.
Task-Free Continual Learning via Online Discrepancy Distance Learning
This paper develops a new theoretical analysis framework which provides generalization bounds based on the discrepancy distance between the visited samples and the entire information made available for training the model.
Continual Variational Autoencoder Learning via Online Cooperative Memorization
Due to their inference, data representation and reconstruction properties, Variational Autoencoders (VAE) have been successfully used in continual learning classification tasks.
BQN: Busy-Quiet Net Enabled by Motion Band-Pass Module for Action Recognition
Through experiments we show that the proposed MBPM can be used as a plug-in module in various CNN backbone architectures, significantly boosting their performance.
Learning an evolved mixture model for task-free continual learning
In this paper, we address a more challenging and realistic setting in CL, namely the Task-Free Continual Learning (TFCL) in which a model is trained on non-stationary data streams with no explicit task information.
Supplemental Material: Lifelong Generative Modelling Using Dynamic Expansion Graph Model
In this article, we provide the appendix for Lifelong Generative Modelling Using Dynamic Expansion Graph Model.
Lifelong Generative Modelling Using Dynamic Expansion Graph Model
In this paper we study the forgetting behaviour of VAEs using a joint GR and ENA methodology, by deriving an upper bound on the negative marginal log-likelihood.
Lifelong Infinite Mixture Model Based on Knowledge-Driven Dirichlet Process
Recent research efforts in lifelong learning propose to grow a mixture of models to adapt to an increasing number of tasks.
Lifelong Teacher-Student Network Learning
While the Student module is trained with a new given database, the Teacher module would remind the Student about the information learnt in the past.
Lifelong Twin Generative Adversarial Networks
In this paper, we propose a new continuously learning generative model, called the Lifelong Twin Generative Adversarial Networks (LT-GANs).
InfoVAEGAN : learning joint interpretable representations by information maximization and maximum likelihood
Learning disentangled and interpretable representations is an important step towards accomplishing comprehensive data representations on the manifold.
Lifelong Mixture of Variational Autoencoders
The mixing coefficients in the mixture, control the contributions of each expert in the goal representation.
Busy-Quiet Video Disentangling for Video Classification
We design a trainable Motion Band-Pass Module (MBPM) for separating busy information from quiet information in raw video data.
Ranked #15 on
Action Recognition
on UCF101
Learning latent representations across multiple data domains using Lifelong VAEGAN
The proposed model supports many downstream tasks that traditional generative replay methods can not, including interpolation and inference across different data domains.
Region-based Non-local Operation for Video Classification
Convolutional Neural Networks (CNNs) model long-range dependencies by deeply stacking convolution operations with small window sizes, which makes the optimizations difficult.
Ranked #32 on
Action Recognition
on Something-Something V1
Generating Memorable Images Based on Human Visual Memory Schemas
The VMS model is based upon the results of memory experiments conducted on human observers, and provides a 2D map of memorability.
Learning spatio-temporal representations with temporal squeeze pooling
In this paper, we propose a new video representation learning method, named Temporal Squeeze (TS) pooling, which can extract the essential movement information from a long sequence of video frames and map it into a set of few images, named Squeezed Images.
Ranked #43 on
Action Recognition
on UCF101
(using extra training data)
Defining Image Memorability using the Visual Memory Schema
Memorability of an image is a characteristic determined by the human observers' ability to remember images they have seen.
