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
GAP: Fault tolerance Improvement of Convolutional Neural Networks through GAN-aided Pruning
Pouya Hosseinzadeh - Yasser Sedaghat - Ahad Harati
Leveraging the Power of Object Detection Models in Identifying Litter for a Significant Reduction in Environmental Pollution
Lim Zhen Xian - Ervin Gubin Moung - Jason Teo Tze Wi - Nordin Saad - Farashazillah Yahya - Tiong Lin Rui - Ali Farzamnia
Sum Rate Analysis and Power Allocation in Massive MIMO Systems with Power Constraints
Abdolrasoul Sakhaei Gharagezlou - Mahdi Nangir
A novel hybrid DMHS-GMDH algorithm to predict COVID-19 pandemic time series
Ahmad Taheri - Shahriar Ghashghaei - Amin Beheshti - Keyvan RahimiZadeh
Improvement of Credit Scoring by LSTM Autoencoder Model
Milad Sattari Maleki - Seyedeh Niusha Motevallian - Faezehsadat Hosseini - Mohammad Sabokrou - Hamidreza Soltanalizadeh Maleki
EEMC: Energy Efficient Multi-Clustering Using Grey Wolf Optimizer in WSNs
Maryam Ghorbanvirdi - Sayyed Majid Mazinani
Graph Representation Learning Towards Patents Network Analysis
Mohammad Heydari - Babak Teimourpour
Forecasting El Niño Six Months in Advance Utilizing Augmented Convolutional Neural Network
Mohammad Naisipour - Iraj Saeedpanah - Arash Adib - Mohammad Hossein Neisi Pour
Deep Inside Tor: Exploring Website Fingerprinting Attacks on Tor Traffic in Realistic Settings
Amirhossein Khajehpour - Farid Zandi - Navid Malekghaini - Mahdi Hemmatyar - Naeimeh Omidvar - Mahdi Jafari Siavoshani
Solving the influence maximization problem by using entropy and weight of edges
Farzaneh Kazemzadeh - Amir Karian - Mitra Mirzarezaee - Ali Asghar Safaei
more
Samin Hamayesh - Version 41.7.6