Existing synthetic aperture radar automatic target recognition (SAR ATR) methods have been effective for the classification of seen target classes. However, it is more meaningful and challenging to distinguish the unseen target classes, i.e., open set recognition (OSR) problem, which is an urgent problem for the practical SAR ATR. The key solution of OSR is to effectively establish the exclusiveness of feature distribution of known classes. In this letter, we propose an entropy-awareness meta-learning method that improves the exclusiveness of feature distribution of known classes which means our method is effective for not only classifying the seen classes but also encountering the unseen other classes. Through meta-learning tasks, the proposed method learns to construct a feature space of the dynamic-assigned known classes. This feature space is required by the tasks to reject all other classes not belonging to the known classes. At the same time, the proposed entropy-awareness loss helps the model to enhance the feature space with effective and robust discrimination between the known and unknown classes. Therefore, our method can construct a dynamic feature space with discrimination between the known and unknown classes to simultaneously classify the dynamic-assigned known classes and reject the unknown classes. Experiments conducted on the moving and stationary target acquisition and recognition (MSTAR) dataset have shown the effectiveness of our method for SAR OSR.
Sufficient synthetic aperture radar (SAR) target images are very important for the development of researches. However, available SAR target images are often limited in practice, which hinders the progress of SAR application. In this paper, we propose an azimuth-controllable generative adversarial network to generate precise SAR target images with an intermediate azimuth between two given SAR images' azimuths. This network mainly contains three parts: generator, discriminator, and predictor. Through the proposed specific network structure, the generator can extract and fuse the optimal target features from two input SAR target images to generate SAR target image. Then a similarity discriminator and an azimuth predictor are designed. The similarity discriminator can differentiate the generated SAR target images from the real SAR images to ensure the accuracy of the generated, while the azimuth predictor measures the difference of azimuth between the generated and the desired to ensure the azimuth controllability of the generated. Therefore, the proposed network can generate precise SAR images, and their azimuths can be controlled well by the inputs of the deep network, which can generate the target images in different azimuths to solve the small sample problem to some degree and benefit the researches of SAR images. Extensive experimental results show the superiority of the proposed method in azimuth controllability and accuracy of SAR target image generation.
Convolutional neural networks (CNNs) have dominated the synthetic aperture radar (SAR) automatic target recognition (ATR) for years. However, under the limited SAR images, the width and depth of the CNN-based models are limited, and the widening of the received field for global features in images is hindered, which finally leads to the low performance of recognition. To address these challenges, we propose a Convolutional Transformer (ConvT) for SAR ATR few-shot learning (FSL). The proposed method focuses on constructing a hierarchical feature representation and capturing global dependencies of local features in each layer, named global in local. A novel hybrid loss is proposed to interpret the few SAR images in the forms of recognition labels and contrastive image pairs, construct abundant anchor-positive and anchor-negative image pairs in one batch and provide sufficient loss for the optimization of the ConvT to overcome the few sample effect. An auto augmentation is proposed to enhance and enrich the diversity and amount of the few training samples to explore the hidden feature in a few SAR images and avoid the over-fitting in SAR ATR FSL. Experiments conducted on the Moving and Stationary Target Acquisition and Recognition dataset (MSTAR) have shown the effectiveness of our proposed ConvT for SAR ATR FSL. Different from existing SAR ATR FSL methods employing additional training datasets, our method achieved pioneering performance without other SAR target images in training.
Query autocomplete (QAC) also known as typeahead, suggests list of complete queries as user types prefix in the search box. It is one of the key features of modern search engines specially in e-commerce. One of the goals of typeahead is to suggest relevant queries to users which are seasonally important. In this paper we propose a neural network based natural language processing (NLP) algorithm to incorporate seasonality as a signal and present end to end evaluation of the QAC ranking model. Incorporating seasonality into autocomplete ranking model can improve autocomplete relevance and business metric.
Recent work has studied text-to-audio synthesis using large amounts of paired text-audio data. However, audio recordings with high-quality text annotations can be difficult to acquire. In this work, we approach text-to-audio synthesis using unlabeled videos and pretrained language-vision models. We propose to learn the desired text-audio correspondence by leveraging the visual modality as a bridge. We train a conditional diffusion model to generate the audio track of a video, given a video frame encoded by a pretrained contrastive language-image pretraining (CLIP) model. At test time, we first explore performing a zero-shot modality transfer and condition the diffusion model with a CLIP-encoded text query. However, we observe a noticeable performance drop with respect to image queries. To close this gap, we further adopt a pretrained diffusion prior model to generate a CLIP image embedding given a CLIP text embedding. Our results show the effectiveness of the proposed method, and that the pretrained diffusion prior can reduce the modality transfer gap. While we focus on text-to-audio synthesis, the proposed model can also generate audio from image queries, and it shows competitive performance against a state-of-the-art image-to-audio synthesis model in a subjective listening test. This study offers a new direction of approaching text-to-audio synthesis that leverages the naturally-occurring audio-visual correspondence in videos and the power of pretrained language-vision models.
Self-driving vehicles (SDVs) are becoming reality but still suffer from "long-tail" challenges during natural driving: the SDVs will continually encounter rare, safety-critical cases that may not be included in the dataset they were trained. Some safety-assurance planners solve this problem by being conservative in all possible cases, which may significantly affect driving mobility. To this end, this work proposes a method to automatically adjust the conservative level according to each case's "long-tail" rate, named dynamically conservative planner (DCP). We first define the "long-tail" rate as an SDV's confidence to pass a driving case. The rate indicates the probability of safe-critical events and is estimated using the statistics bootstrapped method with historical data. Then, a reinforcement learning-based planner is designed to contain candidate policies with different conservative levels. The final policy is optimized based on the estimated "long-tail" rate. In this way, the DCP is designed to automatically adjust to be more conservative in low-confidence "long-tail" cases while keeping efficient otherwise. The DCP is evaluated in the CARLA simulator using driving cases with "long-tail" distributed training data. The results show that the DCP can accurately estimate the "long-tail" rate to identify potential risks. Based on the rate, the DCP automatically avoids potential collisions in "long-tail" cases using conservative decisions while not affecting the average velocity in other typical cases. Thus, the DCP is safer and more efficient than the baselines with fixed conservative levels, e.g., an always conservative planner. This work provides a technique to guarantee SDV's performance in unexpected driving cases without resorting to a global conservative setting, which contributes to solving the "long-tail" problem practically.
Significant progress has been made in self-supervised image denoising (SSID) in the recent few years. However, most methods focus on dealing with spatially independent noise, and they have little practicality on real-world sRGB images with spatially correlated noise. Although pixel-shuffle downsampling has been suggested for breaking the noise correlation, it breaks the original information of images, which limits the denoising performance. In this paper, we propose a novel perspective to solve this problem, i.e., seeking for spatially adaptive supervision for real-world sRGB image denoising. Specifically, we take into account the respective characteristics of flat and textured regions in noisy images, and construct supervisions for them separately. For flat areas, the supervision can be safely derived from non-adjacent pixels, which are much far from the current pixel for excluding the influence of the noise-correlated ones. And we extend the blind-spot network to a blind-neighborhood network (BNN) for providing supervision on flat areas. For textured regions, the supervision has to be closely related to the content of adjacent pixels. And we present a locally aware network (LAN) to meet the requirement, while LAN itself is selectively supervised with the output of BNN. Combining these two supervisions, a denoising network (e.g., U-Net) can be well-trained. Extensive experiments show that our method performs favorably against state-of-the-art SSID methods on real-world sRGB photographs. The code is available at https://github.com/nagejacob/SpatiallyAdaptiveSSID.
The attention-based Transformers have been increasingly applied to audio classification because of their global receptive field and ability to handle long-term dependency. However, the existing frameworks which are mainly extended from the Vision Transformers are not perfectly compatible with audio signals. In this paper, we introduce a Causal Audio Transformer (CAT) consisting of a Multi-Resolution Multi-Feature (MRMF) feature extraction with an acoustic attention block for more optimized audio modeling. In addition, we propose a causal module that alleviates over-fitting, helps with knowledge transfer, and improves interpretability. CAT obtains higher or comparable state-of-the-art classification performance on ESC50, AudioSet and UrbanSound8K datasets, and can be easily generalized to other Transformer-based models.
Accurate segmentation of multiple organs of the head, neck, chest, and abdomen from medical images is an essential step in computer-aided diagnosis, surgical navigation, and radiation therapy. In the past few years, with a data-driven feature extraction approach and end-to-end training, automatic deep learning-based multi-organ segmentation method has far outperformed traditional methods and become a new research topic. This review systematically summarizes the latest research in this field. For the first time, from the perspective of full and imperfect annotation, we comprehensively compile 161 studies on deep learning-based multi-organ segmentation in multiple regions such as the head and neck, chest, and abdomen, containing a total of 214 related references. The method based on full annotation summarizes the existing methods from four aspects: network architecture, network dimension, network dedicated modules, and network loss function. The method based on imperfect annotation summarizes the existing methods from two aspects: weak annotation-based methods and semi annotation-based methods. We also summarize frequently used datasets for multi-organ segmentation and discuss new challenges and new research trends in this field.