International Conference on Computer and Knowledge Engineering

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 Nezhad¹ Hojat Asgarian Dehkordi² Seyed Sajad Ashrafi³ Shahriar Baradaran Shokouhi⁴

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

An Ensemble CNN for Brain Age Estimation based on Hippocampal Region Applicable to Alzheimer's Diagnosis

Zahra Qodrati - Seyedeh Masoumeh Taji - Habibollah Danyali - Kamran Kazemi

HiCAP: Hierarchical Clustering-based Attention Pooling for Graph Representation Learning

Parsa Haddadian - Rooholah Abedian - Ali Moeini

Density Estimation Helps Adversarial Robustness

Afsaneh Hasanebrahimi - Bahareh Kaviani Baghbaderani - Reshad Hosseini - Ahmad Kalhor

An Exploratory Study of the Relationship between SATD and Other Software Development Activities

Shima Esfandiari - Ashkan Sami

An Improved and Accurate Measure for Mining Correlated High-utility Itemsets

Amir Masoud Heidari Orojloo - Morteza Keshtkaran

Traffic Sign Recognition Using Local Vision Transformer

Ali Farzipour - Omid Nejati Manzari - Shahriar B. Shokouhi

Performance Evaluation Study of Color Space Selection In Video Based Facial Expression Recognition Using Deep Neural Networks For Sentiment Analysis

Phee Wei Qin - Ervin Gubin Moung - Ali Farzamnia - Farashazillah Yahya - John Julius Danker Khoo - Maisarah Mohd Sufian

Deep Deterministic Policy Gradient in Acoustic To Articulatory inversion

Farzane Abdoli - Hamid Sheikhzade - Vahid Pourahmadi

Community-Based QoE Enhancement for User-Generated Content Live Streaming

Reza Saeedinia - S.Omid Fatemi - Daniele Lorenzi - Farzad Tashtarian - Christian Timmerer

Novel Insights in Deep Learning for Predicting Climate Phenomena

Mohammad Naisipour - Saghar Ganji - Iraj Saeedpanah - Behnam Mehrakizadeh - Ahmad Reza Labibzadeh