ML p(r)ior | Learning Discriminative Features via Label Consistent Neural Network

Learning Discriminative Features via Label Consistent Neural Network

2016-02-03
Deep Convolutional Neural Networks (CNN) enforces supervised information only at the output layer, and hidden layers are trained by back propagating the prediction error from the output layer without explicit supervision. We propose a supervised feature learning approach, Label Consistent Neural Network, which enforces direct supervision in late hidden layers. We associate each neuron in a hidden layer with a particular class label and encourage it to be activated for input signals from the same class. More specifically, we introduce a label consistency regularization called "discriminative representation error" loss for late hidden layers and combine it with classification error loss to build our overall objective function. This label consistency constraint alleviates the common problem of gradient vanishing and tends to faster convergence; it also makes the features derived from late hidden layers discriminative enough for classification even using a simple $k$-NN classifier, since input signals from the same class will have very similar representations. Experimental results demonstrate that our approach achieves state-of-the-art performances on several public benchmarks for action and object category recognition.
PDF

Highlights - Most important sentences from the article

Login to like/save this paper, take notes and configure your recommendations

Related Articles

2014-09-04
1409.1556 | cs.CV

In this work we investigate the effect of the convolutional network depth on its accuracy in the lar… show more
PDF

Highlights - Most important sentences from the article

2015-12-14

In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it… show more
PDF

Highlights - Most important sentences from the article

2017-05-22
1705.07750 | cs.CV

The paucity of videos in current action classification datasets (UCF-101 and HMDB-51) has made it di… show more
PDF

Highlights - Most important sentences from the article

2013-10-06

We evaluate whether features extracted from the activation of a deep convolutional network trained i… show more
PDF

Highlights - Most important sentences from the article

2015-04-24
1504.06375 | cs.CV

We develop a new edge detection algorithm that tackles two important issues in this long-standing vi… show more
PDF

Highlights - Most important sentences from the article

2018-05-05

Neural net classifiers trained on data with annotated class labels can also capture apparent visual … show more
PDF

Highlights - Most important sentences from the article

2012-07-03

When a large feedforward neural network is trained on a small training set, it typically performs po… show more
PDF

Highlights - Most important sentences from the article

2014-12-20
1412.6622 | cs.LG

Deep learning has proven itself as a successful set of models for learning useful semantic represent… show more
PDF

Highlights - Most important sentences from the article

2018-01-16
1801.05365 | cs.CV

We propose a deep learning-based solution for the problem of feature learning in one-class classific… show more
PDF

Highlights - Most important sentences from the article

2018-08-14

Current major approaches to visual recognition follow an end-to-end formulation that classifies an i… show more
PDF

Highlights - Most important sentences from the article

2018-05-23

Neural networks are a powerful class of nonlinear functions that can be trained end-to-end on variou… show more
PDF

Highlights - Most important sentences from the article

2016-10-27

We learn rich natural sound representations by capitalizing on large amounts of unlabeled sound data… show more
PDF

Highlights - Most important sentences from the article

2016-11-21
1611.06678 | cs.CV

The CNN-encoding of features from entire videos for the representation of human actions has rarely b… show more
PDF

Highlights - Most important sentences from the article

2019-03-07
1903.03161 | cs.CV

We propose a novel deep convolutional neural network (CNN) based multi-task learning approach for op… show more
PDF

Highlights - Most important sentences from the article

2016-04-22

Recent applications of Convolutional Neural Networks (ConvNets) for human action recognition in vide… show more
PDF

Highlights - Most important sentences from the article