Unsupervised domain adaptive object detection aims to adapt detectors from a labelled source domain to an unlabelled target domain. Most existing works take a two-stage strategy that first generates region proposals and then detects objects of interest, where adversarial learning is widely adopted to mitigate the inter-domain discrepancy in both stages. However, adversarial learning may impair the alignment of well-aligned samples as it merely aligns the global distributions across domains. To address this issue, we design an uncertainty-aware domain adaptation network (UaDAN) that introduces conditional adversarial learning to align well-aligned and poorly-aligned samples separately in different manners. Specifically, we design an uncertainty metric that assesses the alignment of each sample and adjusts the strength of adversarial learning for well-aligned and poorly-aligned samples adaptively. In addition, we exploit the uncertainty metric to achieve curriculum learning that first performs easier image-level alignment and then more difficult instance-level alignment progressively. Extensive experiments over four challenging domain adaptive object detection datasets show that UaDAN achieves superior performance as compared with state-of-the-art methods.

Fixed-pattern noise (FPN), which is caused by the nonuniform opto-electronic responses of microbolometer focal-plane-array (FPA) optoelectronics, imposes a challenging problem in infrared imaging systems. In this paper, we successfully demonstrate that a better single-image-based non-uniformity correction (NUC) operator can be directly learned from a large number of simulated training images instead of being handcrafted as before. Our proposed training scheme, which is based on convolutional neural networks (CNNs) and a column FPN simulation module, gives rise to a powerful technique to reconstruct the noise-free infrared image from its corresponding noisy observation. Specifically, a comprehensive column FPN model is utilized to depict the nonlinear characteristics of column amplifiers in the readout circuit of FPA. A large number of high-fidelity training images are simulated based on this model and the end-to-end residual deep network is capable of learning the intrinsic difference between undesirable FPN and original image details. Therefore, column FPN can be accurately estimated and further subtracted from the raw infrared images to obtain NUC results. Comparative results with state-of-the-art single-image-based NUC methods, using real-captured noisy infrared images, demonstrate that our proposed deep-learning-based approach delivers better performances of FPN removal, detail preservation, and artifact suppression.

Infrared images have a wide range of military and civilian applications, including night vision, surveillance, and robotics. However, high-resolution infrared detectors are difficult to fabricate and their manufacturing cost is expensive. In this paper, we present a cascaded architecture of deep neural networks with multiple receptive fields to increase the spatial resolution of infrared images by a large scale factor (x8). Instead of reconstructing a high-resolution image from its low-resolution version using a single complex deep network, the key idea of our approach is to set up a mid-point (scale x2) between scale x1 and x8 such that lost information can be divided into two components. Lost information within each component contains similar patterns thus can be more accurately recovered even using a simpler deep network. In our proposed cascaded architecture, two consecutive deep networks with different receptive fields are jointly trained through a multi-scale loss function. The first network with a large receptive field is applied to recover largescale structure information, while the second one uses a relatively smaller receptive field to reconstruct small-scale image details. Our proposed method is systematically evaluated using realistic infrared images. Compared with state-of-the-art super-resolution methods, our proposed cascaded approach achieves improved reconstruction accuracy using significantly fewer parameters.

Vision and language understanding is one of the most fundamental and challenging problems in Multimedia Intelligence. Simultaneously understanding video actions with a related natural language question, and further produces accurate answer is even more challenging since it requires joint modeling information across modality. In the past few years, some studies begin to attack this problem by utilizing attention enhanced deep neural networks. However, simple attention mechanisms such as unidirectional attention fail to yield a better mapping between different modalities. Moreover, none of these Video QA models explore high-level semantics in augmented video-frame level. In this paper, we augmented each frame representation with its context information by a novel feature extractor that combines the advantages of Resnet and a variant of C3D. In addition, we proposed a novel alternating attention network which can alternately attend frame regions, video frames and words in the question in multi-turns. This yields better joint representations of video and question, further help the deep model to discover the deeper relationship between two modalities. Our method outperforms the state-of-the-art Video QA models on two existing video question answering datasets. Further ablation studies proved that our feature extractor and the alternating attention mechanism can improve the performance jointly.

Fusion of images acquired using different sensors generates a single output with enhanced information for high-level visual perception applications. The transformer architecture has demonstrated its powerful ability to obtain important global contextual dependencies for multi-modal image fusion tasks. However, transformer-based image fusion methods face many critical issues, such as incurring huge computational burdens, limited ability to learn local features, and the difficulty of handling images of arbitrary sizes. To address the above limits, we proposed a novel Laplacian Pyramid Hybrid (LapH) network to combine the advantages of CNN and transformer architectures for multi-modal image fusion tasks. With the divide-and-conquer philosophy, we first build a light-weight CNN-based branch, performing effective extraction and fusion of texture/edge features via central difference convolutions, to process the high-resolution components with abundant details encoded in the lower pyramid levels of the Laplacian pyramid. Then, we design a transformer-based branch to process the low-resolution base components, learning long-range dependencies of global-contextual features without incurring extensive computational loads. Here, we design a multi-scale recurrent modulation mechanism to integrate the edge/texture features from the CNN branch as guidance to progressively refine the feature extraction and fusion on low-frequency components. Finally, we propose a new multi-scale spatial consistency loss term based on the neighbor contrast in source images, generating fused images with more natural and realistic appearances. Extensive experiments on two different multi-modal image fusion tasks verify the superiority of our method. The source codes are made publicly available at https://github.com/rgttadv/LapH.