Saving rainforests is a key to halting adverse climate changes. In this paper, we introduce an innovative solution built on acoustic surveillance and machine learning technologies to help rainforest conservation. In particular, We propose new convolutional neural network (CNN) models for environmental sound classification and achieved promising preliminary results on two datasets, including a public audio dataset and our real rainforest sound dataset. The proposed audio classification models can be easily extended in an automated machine learning paradigm and integrated in cloud-based services for real world deployment.
We propose a simple, fast, and accurate one-stage approach to visual grounding, inspired by the following insight. The performances of existing propose-and-rank two-stage methods are capped by the quality of the region candidates they propose in the first stage --- if none of the candidates could cover the ground truth region, there is no hope in the second stage to rank the right region to the top. To avoid this caveat, we propose a one-stage model that enables end-to-end joint optimization. The main idea is as straightforward as fusing a text query's embedding into the YOLOv3 object detector, augmented by spatial features so as to account for spatial mentions in the query. Despite being simple, this one-stage approach shows great potential in terms of both accuracy and speed for both phrase localization and referring expression comprehension, according to our experiments. Given these results along with careful investigations into some popular region proposals, we advocate for visual grounding a paradigm shift from the conventional two-stage methods to the one-stage framework.
We address the problem of video moment localization with natural language, i.e. localizing a video segment described by a natural language sentence. While most prior work focuses on grounding the query as a whole, temporal dependencies and reasoning between events within the text are not fully considered. In this paper, we propose a novel Temporal Compositional Modular Network (TCMN) where a tree attention network first automatically decomposes a sentence into three descriptions with respect to the main event, context event and temporal signal. Two modules are then utilized to measure the visual similarity and location similarity between each segment and the decomposed descriptions. Moreover, since the main event and context event may rely on different modalities (RGB or optical flow), we use late fusion to form an ensemble of four models, where each model is independently trained by one combination of the visual input. Experiments show that our model outperforms the state-of-the-art methods on the TEMPO dataset.
Current deep neural network based approaches to computed tomography (CT) metal artifact reduction (MAR) are supervised methods that rely on synthesized metal artifacts for training. However, as synthesized data may not accurately simulate the underlying physical mechanisms of CT imaging, the supervised methods often generalize poorly to clinical applications. To address this problem, we propose, to the best of our knowledge, the first unsupervised learning approach to MAR. Specifically, we introduce a novel artifact disentanglement network that disentangles the metal artifacts from CT images in the latent space. It supports different forms of generations (artifact reduction, artifact transfer, and self-reconstruction, etc.) with specialized loss functions to obviate the need for supervision with synthesized data. Extensive experiments show that when applied to a synthesized dataset, our method addresses metal artifacts significantly better than the existing unsupervised models designed for natural image-to-image translation problems, and achieves comparable performance to existing supervised models for MAR. When applied to clinical datasets, our method demonstrates better generalization ability over the supervised models. The source code of this paper is publicly available at https://github.com/liaohaofu/adn.
In this paper, we address the problem of monocular depth estimation when only a limited number of training image-depth pairs are available. To achieve a high regression accuracy, the state-of-the-art estimation methods rely on CNNs trained with a large number of image-depth pairs, which are prohibitively costly or even infeasible to acquire. Aiming to break the curse of such expensive data collections, we propose a semi-supervised adversarial learning framework that only utilizes a small number of image-depth pairs in conjunction with a large number of easily-available monocular images to achieve high performance. In particular, we use one generator to regress the depth and two discriminators to evaluate the predicted depth , i.e., one inspects the image-depth pair while the other inspects the depth channel alone. These two discriminators provide their feedbacks to the generator as the loss to generate more realistic and accurate depth predictions. Experiments show that the proposed approach can (1) improve most state-of-the-art models on the NYUD v2 dataset by effectively leveraging additional unlabeled data sources; (2) reach state-of-the-art accuracy when the training set is small, e.g., on the Make3D dataset; (3) adapt well to an unseen new dataset (Make3D in our case) after training on an annotated dataset (KITTI in our case).
Human body part parsing refers to the task of predicting the semantic segmentation mask for each body part. Fully supervised body part parsing methods achieve good performances, but require an enormous amount of effort to annotate part masks for training. In contrast to high annotation costs required for a limited number of part mask annotations, a large number of weak labels such as poses and full body masks already exist and contain relevant information. Motivated by the possibility of using existing weak labels, we propose the first weakly supervised body part parsing framework. The basic idea is to train a parsing network with pose generated part priors that has blank uncertain regions on estimated boundaries, and use an iterative refinement module to generate new supervision and predictions on these regions. When sufficient extra weak supervisions are available, our weakly-supervised results (62.0% mIoU) on Pascal-Person-Part are comparable to the fully supervised state-of-the-art results (63.6% mIoU). Furthermore, in the extended semi-supervised setting, the proposed framework outperforms the state-of-art methods. In addition, we show that the proposed framework can be extended to other keypoint-supervised part parsing tasks such as face parsing.
Generating radiology reports is time-consuming and requires extensive expertise in practice. Therefore, reliable automatic radiology report generation is highly desired to alleviate the workload. Although deep learning techniques have been successfully applied to image classification and image captioning tasks, radiology report generation remains challenging in regards to understanding and linking complicated medical visual contents with accurate natural language descriptions. In addition, the data scales of open-access datasets that contain paired medical images and reports remain very limited. To cope with these practical challenges, we propose a generative encoder-decoder model and focus on chest x-ray images and reports with the following improvements. First, we pretrain the encoder with a large number of chest x-ray images to accurately recognize 14 common radiographic observations, while taking advantage of the multi-view images by enforcing the cross-view consistency. Second, we synthesize multi-view visual features based on a sentence-level attention mechanism in a late fusion fashion. In addition, in order to enrich the decoder with descriptive semantics and enforce the correctness of the deterministic medical-related contents such as mentions of organs or diagnoses, we extract medical concepts based on the radiology reports in the training data and fine-tune the encoder to extract the most frequent medical concepts from the x-ray images. Such concepts are fused with each decoding step by a word-level attention model. The experimental results conducted on the Indiana University Chest X-Ray dataset demonstrate that the proposed model achieves the state-of-the-art performance compared with other baseline approaches.
Universal style transfer is an image editing task that renders an input content image using the visual style of arbitrary reference images, including both artistic and photorealistic stylization. Given a pair of images as the source of content and the reference of style, existing solutions usually first train an auto-encoder (AE) to reconstruct the image using deep features and then embeds pre-defined style transfer modules into the AE reconstruction procedure to transfer the style of the reconstructed image through modifying the deep features. While existing methods typically need multiple rounds of time-consuming AE reconstruction for better stylization, our work intends to design novel neural network architectures on top of AE for fast style transfer with fewer artifacts and distortions all in one pass of end-to-end inference. To this end, we propose two network architectures named ArtNet and PhotoNet to improve artistic and photo-realistic stylization, respectively. Extensive experiments demonstrate that ArtNet generates images with fewer artifacts and distortions against the state-of-the-art artistic transfer algorithms, while PhotoNet improves the photorealistic stylization results by creating sharp images faithfully preserving rich details of the input content. Moreover, ArtNet and PhotoNet can achieve 3X to 100X speed-up over the state-of-the-art algorithms, which is a major advantage for large content images.
A conventional approach to computed tomography (CT) or cone beam CT (CBCT) metal artifact reduction is to replace the X-ray projection data within the metal trace with synthesized data. However, existing projection or sinogram completion methods cannot always produce anatomically consistent information to fill the metal trace, and thus, when the metallic implant is large, significant secondary artifacts are often introduced. In this work, we propose to replace metal artifact affected regions with anatomically consistent content through joint projection-sinogram correction as well as adversarial learning. To handle the metallic implants of diverse shapes and large sizes, we also propose a novel mask pyramid network that enforces the mask information across the network's encoding layers and a mask fusion loss that reduces early saturation of adversarial training. Our experimental results show that the proposed projection-sinogram correction designs are effective and our method recovers information from the metal traces better than the state-of-the-art methods.
Download fraud is a prevalent threat in mobile App markets, where fraudsters manipulate the number of downloads of Apps via various cheating approaches. Purchased fake downloads can mislead recommendation and search algorithms and further lead to bad user experience in App markets. In this paper, we investigate download fraud problem based on a company's App Market, which is one of the most popular Android App markets. We release a honeypot App on the App Market and purchase fake downloads from fraudster agents to track fraud activities in the wild. Based on our interaction with the fraudsters, we categorize download fraud activities into three types according to their intentions: boosting front end downloads, optimizing App search ranking, and enhancing user acquisition&retention rate. For the download fraud aimed at optimizing App search ranking, we select, evaluate, and validate several features in identifying fake downloads based on billions of download data. To get a comprehensive understanding of download fraud, we further gather stances of App marketers, fraudster agencies, and market operators on download fraud. The followed analysis and suggestions shed light on the ways to mitigate download fraud in App markets and other social platforms. To the best of our knowledge, this is the first work that investigates the download fraud problem in mobile App markets.