While human vision inherently achieves robust cross-domain depth estimation through binocular coordination, robotic systems employing stereo matching still confront significant challenges in maintaining robustness across domains when performing real-time environmental depth perception. Furthermore, most stereo matching methods struggle with challenging regions such as object boundaries and non-overlapping areas on the left side of the left image, resulting in disparity maps that are relatively indistinct and lacking fine details. In this paper, we propose Learning More in Challenging Areas (LMC) to alleviate this problem, which enhances the domain generalization of the model through targeted training on challenging regions. LMC is a simple yet effective data-driven training framework primarily based on self-distillation. Specifically, 1) We pre-train models on a high-frequency dataset to improve perception ability on object boundaries; 2) We develop a self-distillation training strategy to benefit learning in non-overlapping areas on the left side of the left image; 3) We design an adaptive difficult area mask to balance the loss weight on other undefined challenging regions. Under our proposed training framework, GwcNet achieves 33% and 23% performance improvements in autonomous driving benchmarks KITTI 2012 and KITTI 2015 respectively, while preserving real-time inference efficiency without computational overhead.

Click-through rate (CTR) prediction is one of the core tasks in industrial applications such as online advertising and recommender systems. However, the performance of existing CTR models is hampered by the cold-start users who have very few historical behavior data, given that these models often rely on enough sequential behavior data to learn the embedding vectors. In this paper, we propose a novel framework dubbed GF2 to alleviate the cold-start problem in deep learning based CTR prediction. GF2 augments the embeddings of cold-start users after the embedding layer in the deep CTR model based on the Generative Adversarial Network (GAN), and the obtained generator by GAN can be further fine-tuned locally to enhance the CTR prediction in cold-start settings. GF2 is general for deep CTR models that use embeddings to model the features of users, and it has already been deployed in real-world online display advertising system. Experimental results on two large-scale real-world datasets show that GF2 can significantly improve the prediction performance over three polular deep CTR models.

3-D inversion for gravity data is of great significance in geophysical quantitative interpretation. However, due to the complexity of the density distribution on the subsurface and nonuniqueness of inverse problems, the classical inversion still has many shortages. The smooth constrained inversion results in redundant structures, whereas the results of the compact inversion are too focused, and excessively rely on the choice of target density parameters. In view of the above issues, we develop a 3-D combined compact and smooth inversion for gravity and gravity gradient data. The objective function is built by the combination of the minimization of field source volume and the misfit between observed and predicted data. The prior information is treated as the “target density” in the inversion process. Furthermore, in order to solve the problem of overreliance on “target density,” we improve a 3-D gravity inversion algorithm where the model constraints include the combination of compact and smooth factors. Model tests show the method can better recover the source distribution when the parameter of target density is not given. Also, we make a comparative analysis of the inversion results of different gradient components and conclude that the inversion results of the gradient data$g_{xy}$are better than those of other gradient components. Finally, we apply the method to the real gravity data. The inferred results of the anomalous rock mass are consistent with the previous geologic knowledge.

Machine learning techniques have been widely applied to various applications. However, they are potentially vulnerable to data poisoning attacks, where sophisticated attackers can disrupt the learning procedure by injecting a fraction of malicious samples into the training dataset. Existing defense techniques against poisoning attacks are largely attack-specific: they are designed for one specific type of attacks but do not work for other types, mainly due to the distinct principles they follow. Yet few general defense strategies have been developed. In this paper, we propose De-Pois, an attack-agnostic defense against poisoning attacks. The key idea of De-Pois is to train a mimic model the purpose of which is to imitate the behavior of the target model trained by clean samples. We take advantage of Generative Adversarial Networks (GANs) to facilitate informative training data augmentation as well as the mimic model construction. By comparing the prediction differences between the mimic model and the target model, De-Pois is thus able to distinguish the poisoned samples from clean ones, without explicit knowledge of any ML algorithms or types of poisoning attacks. We implement four types of poisoning attacks and evaluate De-Pois with five typical defense methods on different realistic datasets. The results demonstrate that De-Pois is effective and efficient for detecting poisoned data against all the four types of poisoning attacks, with both the accuracy and F1-score over 0.9 on average.

Recommender systems (RS) have become an essential component of web services due to their excellent performance. Despite their great success, RS have proved to be vulnerable to data poisoning attacks, which inject well-crafted fake profiles into RS, so that the target items can be maliciously recommended. In this paper, we first reveal that existing poisoning attacks in RS can be detected effortlessly, as the features of the generated fake profiles cannot be inconsistent with those of normal profiles all the time. We further propose RecUP, a poisoning attack in RS that can generate plausible profiles whose features stay almost the same as the normal ones, based on Generative Adversarial Networks (GAN). To tailor GAN for poisoning in RS, we develop HRGAN and devise a loss function to guide the training of the generator, along with a masking operation with selected potentially powerful profiles, so that the final generated profiles can perform malicious recommendations as expected. Evaluations against various defense methods using three real-world datasets show that, RecUP can generate the most plausible profiles while maintaining comparable attacking performance compared with state-of-the-art attacks.