The human visual perception system has strong robustness in image fusion. This robustness is based on human visual perception system's characteristics of feature selection and non-linear fusion of different features. In order to simulate the human visual perception mechanism in image fusion tasks, we propose a multi-source image fusion framework that combines illuminance factors and attention mechanisms. The framework effectively combines traditional image features and modern deep learning features. First, we perform multi-scale decomposition of multi-source images. Then, the visual saliency map and the deep feature map are combined with the illuminance fusion factor to perform high-low frequency nonlinear fusion. Secondly, the characteristics of high and low frequency fusion are selected through the channel attention network to obtain the final fusion map. By simulating the nonlinear characteristics and selection characteristics of the human visual perception system in image fusion, the fused image is more in line with the human visual perception mechanism. Finally, we validate our fusion framework on public datasets of infrared and visible images, medical images and multi-focus images. The experimental results demonstrate the superiority of our fusion framework over state-of-arts in visual quality, objective fusion metrics and robustness.
The Earth's surface is continually changing, and identifying changes plays an important role in urban planning and sustainability. Although change detection techniques have been successfully developed for many years, these techniques are still limited to experts and facilitators in related fields. In order to provide every user with flexible access to change information and help them better understand land-cover changes, we introduce a novel task: change detection-based visual question answering (CDVQA) on multi-temporal aerial images. In particular, multi-temporal images can be queried to obtain high level change-based information according to content changes between two input images. We first build a CDVQA dataset including multi-temporal image-question-answer triplets using an automatic question-answer generation method. Then, a baseline CDVQA framework is devised in this work, and it contains four parts: multi-temporal feature encoding, multi-temporal fusion, multi-modal fusion, and answer prediction. In addition, we also introduce a change enhancing module to multi-temporal feature encoding, aiming at incorporating more change-related information. Finally, effects of different backbones and multi-temporal fusion strategies are studied on the performance of CDVQA task. The experimental results provide useful insights for developing better CDVQA models, which are important for future research on this task. We will make our dataset and code publicly available.
Single image deraining is a crucial problem because rain severely degenerates the visibility of images and affects the performance of computer vision tasks like outdoor surveillance systems and intelligent vehicles. In this paper, we propose the new convolutional neural network (CNN) called the wavelet channel attention module with a fusion network. Wavelet transform and the inverse wavelet transform are substituted for down-sampling and up-sampling so feature maps from the wavelet transform and convolutions contain different frequencies and scales. Furthermore, feature maps are integrated by channel attention. Our proposed network learns confidence maps of four sub-band images derived from the wavelet transform of the original images. Finally, the clear image can be well restored via the wavelet reconstruction and fusion of the low-frequency part and high-frequency parts. Several experimental results on synthetic and real images present that the proposed algorithm outperforms state-of-the-art methods.
We present Mirable's submission to the 2021 Emotions and Themes in Music challenge. In this work, we intend to address the question: can we leverage semi-supervised learning techniques on music emotion recognition? With that, we experiment with noisy student training, which has improved model performance in the image classification domain. As the noisy student method requires a strong teacher model, we further delve into the factors including (i) input training length and (ii) complementary music representations to further boost the performance of the teacher model. For (i), we find that models trained with short input length perform better in PR-AUC, whereas those trained with long input length perform better in ROC-AUC. For (ii), we find that using harmonic pitch class profiles (HPCP) consistently improve tagging performance, which suggests that harmonic representation is useful for music emotion tagging. Finally, we find that noisy student method only improves tagging results for the case of long training length. Additionally, we find that ensembling representations trained with different training lengths can improve tagging results significantly, which suggest a possible direction to explore incorporating multiple temporal resolutions in the network architecture for future work.
Limited availability of large image datasets is a major issue in the development of accurate and generalizable machine learning methods in medicine. The limitations in the amount of data are mainly due to the use of different acquisition protocols, different hardware, and data privacy. At the same time, training a classification model on a small dataset leads to a poor generalization quality of the model. To overcome this issue, a combination of various image datasets of different provenance is often used, e.g., multi-site studies. However, if an additional dataset does not include all classes of the task, the learning of the classification model can be biased to the device or place of acquisition. This is especially the case for Magnetic Resonance (MR) images, where different MR scanners introduce a bias that limits the performance of the model. In this paper, we present a novel method that learns to ignore the scanner-related features present in the images, while learning features relevant for the classification task. We focus on a real-world scenario, where only a small dataset provides images of all classes. We exploit this circumstance by introducing specific additional constraints on the latent space, which lead the focus on disease-related rather than scanner-specific features. Our method Learn to Ignore outperforms state-of-the-art domain adaptation methods on a multi-site MRI dataset on a classification task between Multiple Sclerosis patients and healthy subjects.
We propose \textbf{SUB-Depth}, a universal multi-task training framework for self-supervised monocular depth estimation (SDE). Depth models trained with SUB-Depth outperform the same models trained in a standard single-task SDE framework. By introducing an additional self-distillation task into a standard SDE training framework, SUB-Depth trains a depth network, not only to predict the depth map for an image reconstruction task, but also to distill knowledge from a trained teacher network with unlabelled data. To take advantage of this multi-task setting, we propose homoscedastic uncertainty formulations for each task to penalize areas likely to be affected by teacher network noise, or violate SDE assumptions. We present extensive evaluations on KITTI to demonstrate the improvements achieved by training a range of existing networks using the proposed framework, and we achieve state-of-the-art performance on this task. Additionally, SUB-Depth enables models to estimate uncertainty on depth output.
When data is unlabelled and the target task is not known a priori, divergent search offers a strategy for learning a wide range of skills. Having such a repertoire allows a system to adapt to new, unforeseen tasks. Unlabelled image data is plentiful, but it is not always known which features will be required for downstream tasks. We propose a method for divergent search in the few-shot image classification setting and evaluate with Omniglot and Mini-ImageNet. This high-dimensional behavior space includes all possible ways of partitioning the data. To manage divergent search in this space, we rely on a meta-learning framework to integrate useful features from diverse tasks into a single model. The final layer of this model is used as an index into the `archive' of all past behaviors. We search for regions in the behavior space that the current archive cannot reach. As expected, divergent search is outperformed by models with a strong bias toward the evaluation tasks. But it is able to match and sometimes exceed the performance of models that have a weak bias toward the target task or none at all. This demonstrates that divergent search is a viable approach, even in high-dimensional behavior spaces.
In this work, we introduce a novel method to learn everyday-like multi-stage tasks from a single human demonstration, without requiring any prior object knowledge. Inspired by the recent Coarse-to-Fine Imitation Learning method, we model imitation learning as a learned object reaching phase followed by an open-loop replay of the demonstrator's actions. We build upon this for multi-stage tasks where, following the human demonstration, the robot can autonomously collect image data for the entire multi-stage task, by reaching the next object in the sequence and then replaying the demonstration, and then repeating in a loop for all stages of the task. We evaluate with real-world experiments on a set of everyday-like multi-stage tasks, which we show that our method can solve from a single demonstration. Videos and supplementary material can be found at https://www.robot-learning.uk/self-replay.
Lighting plays a central role in conveying the essence and depth of the subject in a portrait photograph. Professional photographers will carefully control the lighting in their studio to manipulate the appearance of their subject, while consumer photographers are usually constrained to the illumination of their environment. Though prior works have explored techniques for relighting an image, their utility is usually limited due to requirements of specialized hardware, multiple images of the subject under controlled or known illuminations, or accurate models of geometry and reflectance. To this end, we present a system for portrait relighting: a neural network that takes as input a single RGB image of a portrait taken with a standard cellphone camera in an unconstrained environment, and from that image produces a relit image of that subject as though it were illuminated according to any provided environment map. Our method is trained on a small database of 18 individuals captured under different directional light sources in a controlled light stage setup consisting of a densely sampled sphere of lights. Our proposed technique produces quantitatively superior results on our dataset's validation set compared to prior works, and produces convincing qualitative relighting results on a dataset of hundreds of real-world cellphone portraits. Because our technique can produce a 640 $\times$ 640 image in only 160 milliseconds, it may enable interactive user-facing photographic applications in the future.
Standard plane recognition plays an important role in prenatal ultrasound (US) screening. Automatically recognizing the standard plane along with the corresponding anatomical structures in US image can not only facilitate US image interpretation but also improve diagnostic efficiency. In this study, we build a novel multi-label learning (MLL) scheme to identify multiple standard planes and corresponding anatomical structures of fetus simultaneously. Our contribution is three-fold. First, we represent the class correlation by word embeddings to capture the fine-grained semantic and latent statistical concurrency. Second, we equip the MLL with a graph convolutional network to explore the inner and outer relationship among categories. Third, we propose a novel cluster relabel-based contrastive learning algorithm to encourage the divergence among ambiguous classes. Extensive validation was performed on our large in-house dataset. Our approach reports the highest accuracy as 90.25% for standard planes labeling, 85.59% for planes and structures labeling and mAP as 94.63%. The proposed MLL scheme provides a novel perspective for standard plane recognition and can be easily extended to other medical image classification tasks.