Microscopy images are powerful tools and widely used in the majority of research areas, such as biology, chemistry, physics and materials fields by various microscopies (Scanning Electron Microscope (SEM), Atomic Force Microscope (AFM) and the optical microscope, et al.). However, most of the microscopy images are colourless due to the unique imaging mechanism. Though investigating on some popular solutions proposed recently about colourizing microscopy images, we notice the process of those methods are usually tedious, complicated, and time-consuming. In this paper, inspired by the achievement of machine learning algorithms on different science fields, we introduce two artificial neural networks for grey microscopy image colourization: An end-to-end convolutional neural network (CNN) with a pre-trained model for feature extraction and a pixel-to-pixel Neural Style Transfer convolutional neural network (NST-CNN) which can colourize grey microscopy images with semantic information learned from a user-provided colour image at inference time. Our results show that our algorithm not only could able to colour the microscopy images under complex circumstances precisely but also make the colour naturally according to a massive number of nature images training with proper hue and saturation.
Writer identification based on a small amount of text is a challenging problem. In this paper, we propose a new benchmark study for writer identification based on word or text block images which approximately contain one word. In order to extract powerful features on these word images, a deep neural network, named FragNet, is proposed. The FragNet has two pathways: feature pyramid which is used to extract feature maps and fragment pathway which is trained to predict the writer identity based on fragments extracted from the input image and the feature maps on the feature pyramid. We conduct experiments on four benchmark datasets, which show that our proposed method can generate efficient and robust deep representations for writer identification based on both word and page images.
The objective of Content-Based Image Retrieval (CBIR) methods is essentially to extract, from large (image) databases, a specified number of images similar in visual and semantic content to a so-called query image. To bridge the semantic gap that exists between the representation of an image by low-level features (namely, colour, shape, texture) and its high-level semantic content as perceived by humans, CBIR systems typically make use of the relevance feedback (RF) mechanism. RF iteratively incorporates user-given inputs regarding the relevance of retrieved images, to improve retrieval efficiency. One approach is to vary the weights of the features dynamically via feature reweighting. In this work, an attempt has been made to improve retrieval accuracy by enhancing a CBIR system based on color features alone, through implicit incorporation of shape information obtained through prior segmentation of the images. Novel schemes for feature reweighting as well as for initialization of the relevant set for improved relevance feedback, have also been proposed for boosting performance of RF- based CBIR. At the same time, new measures for evaluation of retrieval accuracy have been suggested, to overcome the limitations of existing measures in the RF context. Results of extensive experiments have been presented to illustrate the effectiveness of the proposed approaches.
The task of blood vessel segmentation in microscopy images is crucial for many diagnostic and research applications. However, vessels can look vastly different, depending on the transient imaging conditions, and collecting data for supervised training is laborious. We present a novel deep learning method for unsupervised segmentation of blood vessels. The method is inspired by the field of active contours and we introduce a new loss term, which is based on the morphological Active Contours Without Edges (ACWE) optimization method. The role of the morphological operators is played by novel pooling layers that are incorporated to the network's architecture.We demonstrate the challenges that are faced by previous supervised learning solutions, when the imaging conditions shift. Our unsupervised method is able to outperform such previous methods in both the labeled dataset, and when applied to similar but different datasets. Our code, as well as efficient PyTorch reimplementations of the baseline methods VesselNN and DeepVess is available on GitHub - https://github.com/shirgur/UMIS.
Camera traps enable the automatic collection of large quantities of image data. Biologists all over the world use camera traps to monitor animal populations. We have recently been making strides towards automatic species classification in camera trap images. However, as we try to expand the geographic scope of these models we are faced with an interesting question: how do we train models that perform well on new (unseen during training) camera trap locations? Can we leverage data from other modalities, such as citizen science data and remote sensing data? In order to tackle this problem, we have prepared a challenge where the training data and test data are from different cameras spread across the globe. For each camera, we provide a series of remote sensing imagery that is tied to the location of the camera. We also provide citizen science imagery from the set of species seen in our data. The challenge is to correctly classify species in the test camera traps.
While neural network hardware accelerators provide a substantial amount of raw compute throughput, the models deployed on them must be co-designed for the underlying hardware architecture to obtain the optimal system performance. We present a class of computer vision models designed using hardware-aware neural architecture search and customized to run on the Edge TPU, Google's neural network hardware accelerator for low-power, edge devices. For the Edge TPU in Coral devices, these models enable real-time image classification performance while achieving accuracy typically seen only with larger, compute-heavy models running in data centers. On Pixel 4's Edge TPU, these models improve the accuracy-latency tradeoff over existing SoTA mobile models.
We describe an approach to learning rich representations for images, that enables simple and effective predictors in a range of vision tasks involving spatially structured maps. Our key idea is to map small image elements to feature representations extracted from a sequence of nested regions of increasing spatial extent. These regions are obtained by "zooming out" from the pixel/superpixel all the way to scene-level resolution, and hence we call these zoom-out features. Applied to semantic segmentation and other structured prediction tasks, our approach exploits statistical structure in the image and in the label space without setting up explicit structured prediction mechanisms, and thus avoids complex and expensive inference. Instead image elements are classified by a feedforward multilayer network with skip-layer connections spanning the zoom-out levels. When used in conjunction with modern neural architectures such as ResNet, DenseNet and NASNet (to which it is complementary) our approach achieves competitive accuracy on segmentation benchmarks. In addition, we propose an approach for learning category-level semantic segmentation purely from image-level classification tag. It exploits localization cues that emerge from training a modified zoom-out architecture tailored for classification tasks, to drive a weakly supervised process that automatically labels a sparse, diverse training set of points likely to belong to classes of interest. Finally, we introduce data-driven regularization functions for the supervised training of CNNs. Our innovation takes the form of a regularizer derived by learning an autoencoder over the set of annotations. This approach leverages an improved representation of label space to inform extraction of features from images
Image-based tracking of medical instruments is an integral part of many surgical data science applications. Previous research has addressed the tasks of detecting, segmenting and tracking medical instruments based on laparoscopic video data. However, the methods proposed still tend to fail when applied to challenging images and do not generalize well to data they have not been trained on. This paper introduces the Heidelberg Colorectal (HeiCo) data set - the first publicly available data set enabling comprehensive benchmarking of medical instrument detection and segmentation algorithms with a specific emphasis on robustness and generalization capabilities of the methods. Our data set comprises 30 laparoscopic videos and corresponding sensor data from medical devices in the operating room for three different types of laparoscopic surgery. Annotations include surgical phase labels for all frames in the videos as well as instance-wise segmentation masks for surgical instruments in more than 10,000 individual frames. The data has successfully been used to organize international competitions in the scope of the Endoscopic Vision Challenges (EndoVis) 2017 and 2019.
Defocus Blur Detection(DBD) aims to separate in-focus and out-of-focus regions from a single image pixel-wisely. This task has been paid much attention since bokeh effects are widely used in digital cameras and smartphone photography. However, identifying obscure homogeneous regions and borderline transitions in partially defocus images is still challenging. To solve these problems, we introduce depth information into DBD for the first time. When the camera parameters are fixed, we argue that the accuracy of DBD is highly related to scene depth. Hence, we consider the depth information as the approximate soft label of DBD and propose a joint learning framework inspired by knowledge distillation. In detail, we learn the defocus blur from ground truth and the depth distilled from a well-trained depth estimation network at the same time. Thus, the sharp region will provide a strong prior for depth estimation while the blur detection also gains benefits from the distilled depth. Besides, we propose a novel decoder in the fully convolutional network(FCN) as our network structure. In each level of the decoder, we design the Selective Reception Field Block(SRFB) for merging multi-scale features efficiently and reuse the side outputs as Supervision-guided Attention Block(SAB). Unlike previous methods, the proposed decoder builds reception field pyramids and emphasizes salient regions simply and efficiently. Experiments show that our approach outperforms 11 other state-of-the-art methods on two popular datasets. Our method also runs at over 30 fps on a single GPU, which is 2x faster than previous works. The code is available at: https://github.com/vinthony/depth-distillation
Generative adversarial networks (GANs) have been extensively studied in the past few years. Arguably the revolutionary techniques are in the area of computer vision such as plausible image generation, image to image translation, facial attribute manipulation and similar domains. Despite the significant success achieved in computer vision field, applying GANs over real-world problems still have three main challenges: (1) High quality image generation; (2) Diverse image generation; and (3) Stable training. Considering numerous GAN-related research in the literature, we provide a study on the architecture-variants and loss-variants, which are proposed to handle these three challenges from two perspectives. We propose loss and architecture-variants for classifying most popular GANs, and discuss the potential improvements with focusing on these two aspects. While several reviews for GANs have been presented, there is no work focusing on the review of GAN-variants based on handling challenges mentioned above. In this paper, we review and critically discuss 7 architecture-variant GANs and 9 loss-variant GANs for remedying those three challenges. The objective of this review is to provide an insight on the footprint that current GANs research focuses on the performance improvement. Code related to GAN-variants studied in this work is summarized on https://github.com/sheqi/GAN_Review.