Recently, differentiable search methods have made major progress in reducing the computational costs of neural architecture search. However, these approaches often report lower accuracy in evaluating the searched architecture or transferring it to another dataset. This is arguably due to the large gap between the architecture depths in search and evaluation scenarios. In this paper, we present an efficient algorithm which allows the depth of searched architectures to grow gradually during the training procedure. This brings two issues, namely, heavier computational overheads and weaker search stability, which we solve using search space approximation and regularization, respectively. With a significantly reduced search time (∼7 hours on a single GPU), our approach achieves state-of-the-art performance on both the proxy dataset (CIFAR10 or CIFAR100) and the target dataset (Im-ageNet). Code is available at https://github.com/ chenxin061/pdarts.
We often use the positive fuzzy rules only for image classification in traditional image classification systems, ignoring the useful negative classification information. Thanh Minh Nguyen and QMJonathan Wu introduced the negative fuzzy rules into the image classification, and proposed combination of positive and negative fuzzy rules to form the positive and negative fuzzy rule system, and then applied it to remote sensing image/natural image classification. Their experiments demonstrated that their proposed method has achieved promising results. However, since their method was realized using the feedforward neural network model which requires adjusting the weights in the gradient descent way, the training speed is very slow. Extreme learning machine (ELM) is a single hidden layer feedforward neural network (SLFNs) learning algorithm, which has distinctive advantages such as quick learning, good generalization performance. In this paper, the equivalence between ELM and the positive and negative fuzzy rule system is revealed, so ELM can be naturally used for training the positive and negative fuzzy rule system quickly for image classification. Our experimental results indicate this claim.
With the rapid development of neural architecture search (NAS), researchers found powerful network architectures for a wide range of vision tasks. However, it remains unclear if the searched architecture can transfer across different types of tasks as manually designed ones did. This paper puts forward this problem, referred to as NAS in the wild, which explores the possibility of finding the optimal architecture in a proxy dataset and then deploying it to mostly unseen scenarios.We instantiate this setting using a currently popular algorithm named differentiable architecture search (DARTS), which often suffers unsatisfying performance while being transferred across different tasks. We argue that the accuracy drop originates from the formulation that uses a supernetwork for search but a sub-network for re-training. The different properties of these stages have resulted in a significant optimization gap, and consequently, the architectural parameters "over-fit" the super-network. To alleviate the gap, we present a progressive method that gradually increases the network depth during the search stage, which leads to the Progressive DARTS (P-DARTS) algorithm. With a reduced search cost (7 hours on a single GPU), P-DARTS achieves improved performance on both the proxy dataset (CIFAR10) and a few target problems (ImageNet classification, COCO detection and three ReID benchmarks). Our code is available at https://github.com/chenxin061/pdarts.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.