Open AccessDissertation
Transfer learning algorithms for image classification
Michael Collins,Trevor Darrell,Ariadna Quattoni +2 more
- 01 Jan 2009
TL;DR: A joint sparsity transfer algorithm for image classification based on the observation that related categories might be learnable using only a small subset of shared relevant features and an optimization algorithm whose time and memory complexity is O( n log n) with n being the number of parameters of the joint model.
read more
Abstract: An ideal image classifier should be able to exploit complex high dimensional feature representations even when only a few labeled examples are available for training. To achieve this goal we develop transfer learning algorithms that: (1) Leverage unlabeled data annotated with meta-data; and (2) Exploit labeled data from related categories.
In the first part of this thesis we show how to use the structure learning framework (Ando and Zhang, 2005) to learn efficient image representations from unlabeled images annotated with meta-data.
In the second part we present a joint sparsity transfer algorithm for image classification. Our algorithm is based on the observation that related categories might be learnable using only a small subset of shared relevant features. To find these features we propose to train classifiers jointly with a shared regularization penalty that minimizes the total number of features involved in the approximation.
To solve the joint sparse approximation problem we develop an optimization algorithm whose time and memory complexity is O( n log n) with n being the number of parameters of the joint model.
We conduct experiments on news-topic and keyword prediction image classification tasks. We test our method in two settings: a transfer learning and multitask learning setting and show that in both cases leveraging knowledge from related categories can improve performance when training data per category is scarce. Furthermore, our results demonstrate that our model can successfully recover jointly sparse solutions. (Copies available exclusively from MIT Libraries, Rm. 14-0551, Cambridge, MA 02139-4307. Ph. 617-253-5668; Fax 617-253-1690.)
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Transfer Learning for Image Classification
Manali Shaha,Meenakshi Pawar +1 more
- 29 Mar 2018
TL;DR: Transfer learning is used to fine-tune the pre-trained network (VGG19) parameters for image classification task and performance analysis shows that fine-tuned VGG19 architecture outperforms the other CNN and hybrid learning approach for image Classification task.
336
An efficient projection for l1, ∞ regularization
Ariadna Quattoni,Xavier Carreras,Michael Collins,Trevor Darrell +3 more
- 14 Jun 2009
TL;DR: A simple and effective projected gradient method for optimization of l1, ∞ regularized problems and results show that it is effective in discovering jointly sparse solutions.
155
Efficient Structure Learning of Markov Networks using L1-Regularization
Bernhard Schölkopf,John Platt,Thomas Hofmann +2 more
- 01 Jan 2007
TL;DR: This paper provides a computationally efficient method for learning Markov network structure from data based on the use of L1 regularization on the weights of the log-linear model, which achieves considerably higher generalization performance than the more standard L2-based method (a Gaussian parameter prior) or pure maximum-likelihood learning.
113
Classification of High Resolution Remote Sensing Images using Deep Learning Techniques
Bini Alias,R. Karthika,Latha Parameswaran +2 more
- 01 Sep 2018
TL;DR: Transfer learning is used efficiently for the feature extraction from a pretrained Convolutional Neural Network model which is used for training in the classification task and the classification yielded a better accurate results.
18
Model Predictive Control and Transfer Learning of Hybrid Systems Using Lifting Linearization Applied to Cable Suspension Systems
01 Apr 2022
TL;DR: In this article , a model predictive control (MPC) of nonlinear hybrid systems using lifting linearization underpinned by Koopman Operator is presented. But the model is not transferable to a similar system with different parameters.
7
References
•Book
The Nature of Statistical Learning Theory
Vladimir Vapnik
- 01 Jan 1995
TL;DR: Setting of the learning problem consistency of learning processes bounds on the rate of convergence ofLearning processes controlling the generalization ability of learning process constructing learning algorithms what is important in learning theory?
46K
Support-Vector Networks
Corinna Cortes,Vladimir Vapnik +1 more
TL;DR: High generalization ability of support-vector networks utilizing polynomial input transformations is demonstrated and the performance of the support- vector network is compared to various classical learning algorithms that all took part in a benchmark study of Optical Character Recognition.
Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
Aude Oliva,Antonio Torralba +1 more
TL;DR: The performance of the spatial envelope model shows that specific information about object shape or identity is not a requirement for scene categorization and that modeling a holistic representation of the scene informs about its probable semantic category.
7.5K
Additive Logistic Regression : A Statistical View of Boosting
TL;DR: This work shows that this seemingly mysterious phenomenon of boosting can be understood in terms of well-known statistical principles, namely additive modeling and maximum likelihood, and develops more direct approximations and shows that they exhibit nearly identical results to boosting.
Greed is good: algorithmic results for sparse approximation
TL;DR: This article presents new results on using a greedy algorithm, orthogonal matching pursuit (OMP), to solve the sparse approximation problem over redundant dictionaries and develops a sufficient condition under which OMP can identify atoms from an optimal approximation of a nonsparse signal.