Training Hierarchical Feed-Forward Visual Recognition Models Using Transfer Learning from Pseudo-Tasks

By Amr Ahmed, Kai Yu, Wei Xu, Yihong Gong, Eric P. Xing. 2008

177 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Deep learning via semi-supervised embedding (2008, methodology): “We note that an alternative multi-task learning scheme is presented in (Ando & Zhang, 2005) and applied to neural networks in (Ahmed et al., 2008) which instead constructs auxiliary supervised tasks from unlabeled * data by constructing tasks with labels y .”
Ieee Transactions on Pattern Analysis and Machine Intelligence 1 Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks (2014, unknown): “Finally, the idea of creating an auxiliary task in order to learn a good data representation was previously used in natural language processing [22] and computer vision [23].”
Sharing features between objects and their attributes (2011, background): “Multi-task lea rning [7] is often accomplished through feature sharing, and some vision work explores text [19, 14] or pattern matching [2] data as auxiliary tasks.”
Learning Social Relation Traits from Face Images (2015, background): “It is worth noting that this bridging layer is different from the work of [1, 40], where the algorithms build some clusters from training data as an auxiliary task.”
Learning Deep Architectures for AI (2007, methodology): “Since 2006, deep networks have been applied with success not only in classification tasks [2, 17, 99, 111, 150, 153, 195], but also in regression [160], dimensionality reduction [74, 158], modeling textures [141], modeling motion [182, 183], object segmentation [114], information retrieval [154, 159”
Convolutional networks and applications in vision (2010, background): “Several works at NEC have also shown that using auxiliary tasks [35], [36] helps regularizing the system and produces excellent performance.”
On the Impact of Data Set Size in Transfer Learning Using Deep Neural Networks (2016, methodology): “In [1] the authors develop a relatively easy way to create new related tasks on which a CNN can train using the Caltech 101 data set.”
Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review (2017, background): “Further details are available in the original paper (Ahmed et al., 2008); an overview on the different forms of knowledge transfer and some of its early successes is provided by FeiFei (2006).”
Large-Scale FPGA-based Convolutional Networks (2011, background): “However, recent works have focused on training with an auxiliary task (Ahmed et al., 2008) or using unsupervised objectives (Ranzato et al.”
Transfer learning using computational intelligence: A survey (2015, background): “, gender and ethnicity recognition based on facial appearance [46], emotional facial appearance recognition derived from synthetic images of neutral faces to that of corresponding images of angry, happy and sad faces [60], age estimations from face images [65], and gaze gesture recognition by eye tr”
Learning and Transferring Mid-level Image Representations Using Convolutional Neural Networks (2014, unknown): “More similar to our work, [3] trains CNNs on unsupervised pseudo-tasks.”
Evaluation of Pooling Operations in Convolutional Architectures for Object Recognition (2010, unknown): “[1].”
A Review on Deep Learning Techniques Applied to Semantic Segmentation (2017, background): “Even if a dataset large enough is available and convergence does not take that long, it is often helpful to start with pre-trained weights instead of random initialized ones [20] [21].”
3D Convolutional Neural Networks for Human Action Recognition (2010, unknown): “More details on this scheme can be found in [35]–[37].”