Unidirectional Thin Adapter for Efficient Adaptation of Deep Neural Networks

03/20/2022
by   Han Gyel Sun, et al.
0

In this paper, we propose a new adapter network for adapting a pre-trained deep neural network to a target domain with minimal computation. The proposed model, unidirectional thin adapter (UDTA), helps the classifier adapt to new data by providing auxiliary features that complement the backbone network. UDTA takes outputs from multiple layers of the backbone as input features but does not transmit any feature to the backbone. As a result, UDTA can learn without computing the gradient of the backbone, which saves computation for training significantly. In addition, since UDTA learns the target task without modifying the backbone, a single backbone can adapt to multiple tasks by learning only UDTAs separately. In experiments on five fine-grained classification datasets consisting of a small number of samples, UDTA significantly reduced computation and training time required for backpropagation while showing comparable or even improved accuracy compared with conventional adapter models.

READ FULL TEXT

page 2

page 7

page 15

research
06/13/2022

LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning

Fine-tuning large pre-trained models on downstream tasks has been adopte...
research
07/20/2020

XMixup: Efficient Transfer Learning with Auxiliary Samples by Cross-domain Mixup

Transferring knowledge from large source datasets is an effective way to...
research
04/27/2021

Efficient Pre-trained Features and Recurrent Pseudo-Labeling inUnsupervised Domain Adaptation

Domain adaptation (DA) mitigates the domain shift problem when transferr...
research
05/12/2022

Cross-domain Few-shot Meta-learning Using Stacking

Cross-domain few-shot meta-learning (CDFSML) addresses learning problems...
research
02/27/2023

Supervised Virtual-to-Real Domain Adaptation for Object Detection Task using YOLO

Deep neural network shows excellent use in a lot of real-world tasks. On...
research
07/01/2022

DRESS: Dynamic REal-time Sparse Subnets

The limited and dynamically varied resources on edge devices motivate us...
research
03/26/2023

Mind the Backbone: Minimizing Backbone Distortion for Robust Object Detection

Building object detectors that are robust to domain shifts is critical f...

Please sign up or login with your details

Forgot password? Click here to reset