Related papers: Feature Decomposition for Reducing Negative Transf…

We introduce a model-based image reconstruction framework with a convolution neural network (CNN) based regularization prior. The proposed formulation provides a systematic approach for deriving deep architectures for inverse problems with…

Effective modeling of heterogeneous subpopulations presents a significant challenge due to variations in individual characteristics and behaviors. This paper proposes a novel approach to address this issue through multi-task learning (MTL)…

Most uses of machine learning today involve training a model from scratch for a particular task, or sometimes starting with a model pretrained on a related task and then fine-tuning on a downstream task. Both approaches offer limited…

Human densepose estimation, aiming at establishing dense correspondences between 2D pixels of human body and 3D human body template, is a key technique in enabling machines to have an understanding of people in images. It still poses…

Thanks to digitization of industrial assets in fleets, the ambitious goal of transferring fault diagnosis models fromone machine to the other has raised great interest. Solving these domain adaptive transfer learning tasks has the potential…

We introduce a novel method that enables parameter-efficient transfer and multi-task learning with deep neural networks. The basic approach is to learn a model patch - a small set of parameters - that will specialize to each task, instead…

Facial attributes (\eg, age and attractiveness) estimation performance has been greatly improved by using convolutional neural networks. However, existing methods have an inconsistency between the training objectives and the evaluation…

Transfer in Reinforcement Learning aims to improve learning performance on target tasks using knowledge from experienced source tasks. Successor Representations (SR) and their extension Successor Features (SF) are prominent transfer…

Residual connections are one of the most important components in neural network architectures for mitigating the vanishing gradient problem and facilitating the training of much deeper networks. One possible explanation for how residual…

Federated learning (FL) is a popular framework for training an AI model using distributed mobile data in a wireless network. It features data parallelism by distributing the learning task to multiple edge devices while attempting to…

Transfer learning is a popular paradigm for utilizing existing knowledge from previous learning tasks to improve the performance of new ones. It has enjoyed numerous empirical successes and inspired a growing number of theoretical studies.…

Humans are incredibly good at transferring knowledge from one domain to another, enabling rapid learning of new tasks. Likewise, transfer learning has enabled enormous success in many computer vision problems using pretraining. However, the…

In current scenario several commercial and social organizations are using computer networks for their business and management purposes. In order to meet the business requirements networks are also grow. The growth of network also promotes…

In this paper, we propose a novel multi-task learning method based on the deep convolutional network. The proposed deep network has four convolutional layers, three max-pooling layers, and two parallel fully connected layers. To adjust the…

Neural networks are often trained on multiple tasks, either simultaneously (multi-task learning, MTL) or sequentially (pretraining and subsequent finetuning, PT+FT). In particular, it is common practice to pretrain neural networks on a…

An increasingly popular machine learning paradigm is to pretrain a neural network (NN) on many tasks offline, then adapt it to downstream tasks, often by re-training only the last linear layer of the network. This approach yields strong…

The purpose of feature extraction on convolutional neural networks is to reuse deep representations learnt for a pre-trained model to solve a new, potentially unrelated problem. However, raw feature extraction from all layers is unfeasible…

Multi-task learning (MTL) is an effective method for learning related tasks, but designing MTL models necessitates deciding which and how many parameters should be task-specific, as opposed to shared between tasks. We investigate this issue…

Most existing multi-source domain adaptation (MSDA) methods minimize the distance between multiple source-target domain pairs via feature distribution alignment, an approach borrowed from the single source setting. However, with diverse…

In many practical visual recognition scenarios, feature distribution in the source domain is generally different from that of the target domain, which results in the emergence of general cross-domain visual recognition problems. To address…