Please wait ...
0% Complete
Home
/
11th International Conference on Computer and Knowledge Engineering
To Transfer or Not To Transfer (TNT): Action Recognition in Still Image Using Transfer Learning
Authors :
Ali Soltani Nezhad
1
Hojat Asgarian Dehkordi
2
Seyed Sajad Ashrafi
3
Shahriar Baradaran Shokouhi
4
1- School of Electrical Engineering, Iran University of Science and Technology, Tehran 16846-13144, Iran
2- School of Electrical Engineering, Iran University of Science and Technology, Tehran 16846-13144, Iran
3- School of Electrical Engineering, Iran University of Science and Technology, Tehran 16846-13144, Iran
4- School of Electrical Engineering, Iran University of Science and Technology, Tehran 16846-13144, Iran
Keywords :
Action Recognition, Still Image, Transfer Learning, Knowledge Distillation
Abstract :
Lack of training data and small datasets is one of the main challenges in human action recognition in still images. For this reason, training a network from scratch does not lead to good results just by using this little training data. Hence, many existing methods use the transfer learning techniques such as fine-tuning a pre-trained network with initial weights from ImageNet. It is important to note that some of the weights obtained from ImageNet are not suitable for human action recognition tasks. On the other hand, in fine-tuning the network, suitable initial weights for human action recognition may be changed. This paper proposes a method called To Transfer or Not To Transfer (TNT) based on knowledge distillation. In this method, a none trainable teacher with ImageNet weights is employed to train a light student network for action recognition tasks. In order to transfer relevant knowledge and not to transfer insufficient knowledge from teacher to student, a To Transfer or Not To Transfer Loss (TNTL) function is introduced in this paper. The proposed method is evaluated on Stanford 40 and Pascal VOC datasets, and the results show the superiority of this method over existing methods that exploit more parameters.
Papers List
List of archived papers
Enhancing Cloud Security with Federated CNN-LSTM: A Novel Approach to Intrusion Detection
Reyhaneh Ilaghi - Raheleh Ilaghi - Fereshteh Rahmani - Seyyed hamid Ghafoori
Deep Deterministic Policy Gradient in Acoustic To Articulatory inversion
Farzane Abdoli - Hamid Sheikhzade - Vahid Pourahmadi
Dual-Mode Density-Aware Attention-based Hierarchical Graph Pooling
Roya Booryaee - Parsa Haddadian - Ali Kamandi
Graph Attention Networks for Modeling Multi-Sensor Relationships in Early Prediction of Critical Events in ICU Patients
Amir Akhavan Saffar - Danial Eskandari Faruji - Javad Hamidzadeh
Improving LoRaWAN Scalability for IoT Applications using Context Information
Hamed Mahmoudi - Behrouz ShahgholiGhahfarokhi
Class-Aware Balanced Point Cloud Donwsampling for Efficient Large-Scale 3D Scene Understanding
Mohammad Yousefipour - Marjan Naderan - Morteza Jaderyan
An Adaptive Budget and Deadline-aware Algorithm for Scheduling Workflows Ensemble in IaaS Clouds
Negin Shafinezhad - Hamid Abrishami - Saeid Abrishami
A Survey of the AVOA Metaheuristic Algorithm and its Suitability for Power System Optimization and Damping Controller Design
Aliyu Sabo - Theophilus Ebuka Odoh - Samuel Habu - Hossien Shahinzadeh - Farshad Ebrahimi
FinTNet: From Tweets to Trades
Dorsa Tavakoli - Saman Haratizadeh
A novel hybrid DMHS-GMDH algorithm to predict COVID-19 pandemic time series
Ahmad Taheri - Shahriar Ghashghaei - Amin Beheshti - Keyvan RahimiZadeh
more
Samin Hamayesh - Version 46.0.2