RGB and infrared images has shown remarkable robustness for object detection based on unmanned aerial vehicles (UAV). However, the primitive RGB and infrared (IR) images are inevitably misaligned due to the device gap between RGB and infrared cameras. Most existing methods rely on manually filtered and aligned images, and thus are limited in real-world application. Some recent methods tend to directly learn from misaligned images, which only weakly benefit from the multi-modality and may be misled by dramatically misaligned IR images. Considering that the manually aligned images are available during training while unavailable in inference, we explore a new learning paradigm using the IR modality as privileged information. In the training stage, our model learns to hallucinate the complementary knowledge in IR modality based on RGB modality. In inference, our model could hallucinate the complementary IR modality to facilitate UAV detection. Specifically, we propose to quantize the IR features and hallucinate the codebook-indices based on RGB features, which is more effective and robust than directly hallucinating features. In addition, we propose to hierarchically hallucinate multi-scale codebook-indices, which could further improve the hallucinating quality. Experiments on DroneVehicle and VisDrone datasets demonstrate the effectiveness of our method.

The Internet of Nano Things (IoNT) refers to an interconnected network of nanoscale components engineered to perform tasks such as data processing, storage, and actuation. IoNT has broad applications, including environmental monitoring and pollution source localization. In order to achieve monitoring and localization for multiple releasing sources (RSs), the deployment of nanosensor networks is indispensable. However, constrained by spatial limitations and high costs, sensors can only be sparsely deployed, resulting in severe degradation in localization performance. In this paper, we consider a turbulent diffusion molecular communication scenario and the objective is to enable multi-source localization and obstacle perception with sparse nanosensors. For sparse signal recovery, we first propose a real-symmetric based on Truncated Nuclear Norm Regularization with Alternating Direction Method of Multipliers (RS-TNNR) matrix completion algorithm, which utilizes the spatial symmetry of molecular diffusion to achieve precise data recovery under high missing ratios. Furthermore, for multi-source localization and obstacle perception, we also propose an Adaptive Iterative Grid based on Sparse Bayesian Learning (AIG-SBL) algorithm, which enhances the localization accuracy with SBL, mitigates off-grid errors via the proposed adaptive iterative grid, and simultaneously estimates obstacle position and radii. Simulation results demonstrate the effectiveness of the proposed algorithms for RS-TNNR and AIG-SBL.

Speech Emotion Recognition (SER) can play an important role in human-computer interaction. In this paper, we propose a logit knowledge distillation method for SER, called Cubic KD, that distill the knowledge of fine-tuned self-supervised models to allow better performance of small models. By creating cubic structures from teacher and student network output features and using a loss function to distill the cube structure through self-correlation between elements, Cubic KD efficiently captures knowledge within instances and among instances. We apply this distillation method to four student models and conduct experiments using the Emo-DB and IEMOCAP datasets. The results show that Cubic KD outperforms existing predictive logit knowledge distillation methods and is comparable to intermediate feature knowledge distillation methods. Our implementation code is available at https://github.com/Fly1toMoon/Cubic-Knowledge-Distillation