Towards Better Uncertainty Sampling: Active Learning with Multiple Views for Deep Convolutional Neural Network

An Intelligent Multi-View Active Learning Method Based on a Double-Branch Network

“…The details of each branch structure in our double-branch network are: (a) Branch-1: convolution-relu-maxpooling-dropout- convolution- relu-maxpooling-dropout-convolution-dense-dropout-dense-softmax, (b) Branch-2: convolution- relu-convolution-relu-maxpooling-dropout-dense-relu-dropout-dense-softmax, with 32 convolution kernels, 4 × 4 kernel size, 2 × 2 pooling, dense layer with 128 units, and dropout probabilities are set to 0.25 and 0.5. For the Cifar-10, SVHN, Scene-15 and UIUC-Sports datasets, we replaced the LeNet architecture with the model in [ 21 ].…”

“…The above two baselines utilize the double-branch BCNN as their backbone networks, which is the same as our proposed MALDB. Besides, we also compare the performance of our approach with other existing methods including: max-entropy selection strategy based on Bayesian CNN (BCNN-EN for short) [ 25 ], active learning with multiple views (AL-MV for short) [ 21 ] and standard CNN with random sample selection (CNN for short) [ 3 ].…”

“…However, all of the above uncertainty based active learning methods for deep models only consider the classification output, which neglects a lot of valuable information of different level features learned by intermediate hidden layers. In addition, the selection of samples by only considering the classification output of final layer is very sensitive to the classification result of current classifier [ 21 ]. Therefore, in order to better estimate the uncertainty of samples, both the information of intermediate hidden layers and final output layer in the deep learning model should be taken into account.…”

“…The distinctiveness is obtained by combining the feature information from early to later layers, and the uncertainty of the sample is obtained by combining the maximum entropy. He et al [ 21 ] proposed a multi-view active learning that dynamically combines the uncertainty among hidden layers. The aforementioned two methods combine hidden layer and output layer information to select informative data and achieved good performance.…”

“…Since Wang and Shang [ 14 ] applied active learning to deep learning, the strategy of uncertainty sampling is widely used in various deep learning models to estimate the informativeness of samples. However, some studies have pointed out that the samples selected by the uncertainty evaluated only based on the final output in deep learning model are insufficient [ 20 , 21 ]. This is due to the fact the last layer of a deep learning model is task oriented, which ignores the information learned by the middle hidden layers during the data analysis and selection progress.…”