24 June 2024 in IEEE Open Journal of Intelligent Transportation Systems
From the perspective of artificial intelligence evaluation, the need to discover and explain the potential shortness of the evaluated intelligent algorithms/systems as well as the need to evaluate the intelligence level of such testees are of equal importance. In this paper, we propose a possible solution to these challenges: Explainable Evaluation for visual intelligence. Specifically, we focus on the problem setting where the internal mechanisms of AI algorithms are sophisticated, heterogeneous or unreachable. In this case, a latent attribute dictionary learning method with constrained by mapping consistency is proposed to explain the performance variation patterns of visual perception intelligence under different test samples. By jointly iteratively solving the learning of latent concept representation for test samples and the regression of latent concept-generalization performance, the mapping relationship between deep representation, semantic attribute annotation, and generalization performance of test samples is established to predict the degree of influence of semantic attributes on visual perception generalization performance. The optimal solution of proposed method could be reached via an alternating optimization process. Through quantitative experiments, we find that global mapping consistency constraints can make the learned latent concept representation strictly consistent with deep representation, thereby improving the accuracy of semantic attribute-perception performance correlation calculation.
31 December 2024 in Visual Intelligence
Fundamental machine learning theory shows that different samples contribute unequally to both the learning and testing processes. Recent studies on deep neural networks (DNNs) suggest that such sample differences are rooted in the distribution of intrinsic pattern information, namely sample regularity. Motivated by recent discoveries in network memorization and generalization, we propose a pair of sample regularity measures with a formulation-consistent representation for both processes. Specifically, the cumulative binary training/generalizing loss (CBTL/CBGL), the cumulative number of correct classifications of the training/test sample within the training phase, is proposed to quantify the stability in the memorization-generalization process, while forgetting/mal-generalizing events (ForEvents/MgEvents), i.e., the misclassification of previously learned or generalized samples, are utilized to represent the uncertainty of sample regularity with respect to optimization dynamics. The effectiveness and robustness of the proposed approaches for mini-batch stochastic gradient descent (SGD) optimization are validated through sample-wise analyses. Further training/test sample selection applications show that the proposed measures, which share the unified computing procedure, could benefit both tasks.