A Nonlinear, Noise-aware, Quasi-clustering Approach to Learning Deep CNNs from Noisy Labels

Ishan Jindal, Matthew Nokleby, Daniel Pressel; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 64-72

The success of deep convolutional networks on image classification and recognition tasks depends on the avail- ability of large, labeled datasets, but it can be difficult to obtain a large number of accurate labels. To deal with this problem, we present Nonlinear, Noise-aware, Quasi- clustering (NNAQC), a method for learning deep convolutional networks from datasets corrupted by unknown label noise. We append a nonlinear noise model to a standard convolutional network, which is learned in tandem with the parameters of the network. Further, we train the network using a loss function that encourages the clustering of training images. We argue that the non-linear noise model, while not rigorous as a probabilistic model, results in a more effective denoising operator during backpropagation. We evaluate the performance of NNAQC on artificially injected label noise to MNIST, CIFAR-10, CIFAR-100 and ImageNet datasets and on a large-scale Clothing1M dataset with inherent label noise. On all these datasets, NNAQC provides significantly improved classification performance over the state of the art and is robust to the amount of label noise and the training samples.