In unsupervised person Re-ID, peer-teaching strategy leveraging two networks to facilitate training has been proven to be an effective method to deal with the pseudo label noise. However, training two networks with a set of noisy pseudo labels reduces the complementarity of the two networks and results in label noise accumulation. To handle this issue, this paper proposes a novel Dual Clustering Co-teaching (DCCT) approach. DCCT mainly exploits the features extracted by two networks to generate two sets of pseudo labels separately by clustering with different parameters. Each network is trained with the pseudo labels generated by its peer network, which can increase the complementarity of the two networks to reduce the impact of noises. Furthermore, we propose dual clustering with dynamic parameters (DCDP) to make the network adaptive and robust to dynamically changing clustering parameters. Moreover, Consistent Sample Mining (CSM) is proposed to find the samples with unchanged pseudo labels during training for potential noisy sample removal. Extensive experiments demonstrate the effectiveness of the proposed method, which outperforms the state-of-the-art unsupervised person Re-ID methods by a considerable margin and surpasses most methods utilizing camera information.

The key procedure of haze image synthesis with adversarial training lies in the disentanglement of the feature involved only in haze synthesis, i.e., the style feature , from the feature representing the invariant semantic content, i.e., the content feature . Previous methods introduced a binary classifier to constrain the domain membership from being distinguished through the learned content feature during the training stage, thereby the style information is separated from the content feature. However, we find that these methods cannot achieve complete content-style disentanglement. The entanglement of the flawed style feature with content information inevitably leads to the inferior rendering of haze images. To address this issue, we propose a self-supervised style regression model with stochastic linear interpolation that can suppress the content information in the style feature. Ablative experiments demonstrate the disentangling completeness and its superiority in density-aware haze image synthesis. Moreover, the synthesized haze data are applied to test the generalization ability of vehicle detectors. Further study on the relation between haze density and detection performance shows that haze has an obvious impact on the generalization ability of vehicle detectors and that the degree of performance degradation is linearly correlated to the haze density, which in turn validates the effectiveness of the proposed method.

Achieving excellent generalization on perceiving real traffic scenarios with diversity is the long-term goal for building robust autonomous driving systems. A recent theoretical study shows that the generalization on the worst-group of test samples is far more difficult than others. Therefore, we propose to discover potential shortness of certain perception module by analyzing its worst-scenario performance. However, with the benchmark datasets growing huge and tremendous, exhaustive searching for the worst perception scenario (WPS) seems to be time consuming and unnecessary. To address this, we present an automatic searching scheme empowered by reinforcement learning. In this case, worst scenario mining is formulated as the discrete search on the Visual Operation Design Domain (ODD), namely scenario representation, by optimizing LSTM-RNN controller with the worst-performance reward. Moreover, a time-efficient K-reciprocal re-ranking technique is utilized to match the predicted scenario parameters with existing test data. The proposed method has been validated by finding the most challenging scenarios for various vehicle detectors on KITTI, BDD100k and our own benchmark set EVB. Furthermore, searching performances w.r.t different Visual ODDs are investigated and it is found that visual representations through generative adversarial network contribute to a better performance.

In this paper, we study the testing tasks evaluation and testees ranking problem, in which tasks have different difficulty levels, and testees have different capabilities. We assume that a testee may have a probability to pass a certain task so as to allow certain uncertainty. The goal of this problem is to simultaneously determine the relative difficulty level of each testing task and the relative capability of every testee, purely based on the test outcome. We design two models to solve this problem. The first one assumes that the test outcome follows a certain Bernoulli distribution; while the second one assumes that the test outcome follows a certain Bernoulli distribution with the beta distribution-type a priori knowledge. Then, we form the original problem into likelihood estimation problems and solve them by using coordinate descent algorithms. We show that the beta distribution-type a priori knowledge is needed, when we only carry out a limited number of tests due to time and financial budgets. All these findings are useful to intelligence tests. Finally, we discuss how to extend this statistical learning model for more general cases as well as in a specific case in the field of Computational Social Systems like artificial social cognition evaluation.

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.