Recent years have witnessed the rapid growth of machine learning in a wide range of fields such as image recognition, text classification, credit scoring prediction, recommendation system, etc. In spite of their great performance in different sectors, researchers still concern about the mechanism under any machine learning (ML) techniques that are inherently black-box and becoming more complex to achieve higher accuracy. Therefore, interpreting machine learning model is currently a mainstream topic in the research community. However, the traditional interpretable machine learning focuses on the association instead of the causality. This paper provides an overview of causal analysis with the fundamental background and key concepts, and then summarizes most recent causal approaches for interpretable machine learning. The evaluation techniques for assessing method quality, and open problems in causal interpretability are also discussed in this paper.
As the popularity of mobile photography is growing constantly, lots of efforts are being invested now into building complex hand-crafted camera ISP solutions. In this work, we demonstrate that even the most sophisticated ISP pipelines can be replaced with a single end-to-end deep learning model trained without any prior knowledge about the sensor and optics used in a particular device. For this, we present PyNET, a novel pyramidal CNN architecture designed for fine-grained image restoration that implicitly learns to perform all ISP steps such as image demosaicing, denoising, white balancing, color and contrast correction, demoireing, etc. The model is trained to convert RAW Bayer data obtained directly from mobile camera sensor into photos captured with a professional high-end DSLR camera, making the solution independent of any particular mobile ISP implementation. To validate the proposed approach on the real data, we collected a large-scale dataset consisting of 10 thousand full-resolution RAW-RGB image pairs captured in the wild with the Huawei P20 cameraphone (12.3 MP Sony Exmor IMX380 sensor) and Canon 5D Mark IV DSLR. The experiments demonstrate that the proposed solution can easily get to the level of the embedded P20's ISP pipeline that, unlike our approach, is combining the data from two (RGB + B/W) camera sensors. The dataset, pre-trained models and codes used in this paper are available on the project website.
Mitotic count is a commonly used method to assess the level of progression of breast cancer, which is now the fourth most prevalent cancer. Unfortunately, counting mitosis is a tedious and subjective task with poor reproducibility, especially for non-experts. Luckily, since the machine can read and compare more data with greater efficiency this could be the next modern technique to count mitosis. Furthermore, technological advancements in medicine have led to the increase in image data available for use in training. In this work, we propose a network constructed using a similar approach to one that has been used for image fraud detection with the segmented image map as the second stream input to Faster RCNN. This region-based detection model combines a fully convolutional Region Proposal Network to generate proposals and a classification network to classify each of these proposals as containing mitosis or not. Features from both streams are fused in the bilinear pooling layer to maintain the spatial concurrence of each. After training this model on the ICPR 2014 MITOSIS contest dataset, we received an F-measure score of 0.507, higher than both the winners score and scores from recent tests on the same data. Our method is clinically applicable, taking only around five min per ten full High Power Field slides when tested on a Quadro P6000 cloud GPU.
We present deep neural network methodology to reconstruct the 3d pose and shape of people, given an input RGB image. We rely on a recently introduced, expressivefull body statistical 3d human model, GHUM, trained end-to-end, and learn to reconstruct its pose and shape state in a self-supervised regime. Central to our methodology, is a learning to learn and optimize approach, referred to as HUmanNeural Descent (HUND), which avoids both second-order differentiation when training the model parameters,and expensive state gradient descent in order to accurately minimize a semantic differentiable rendering loss at test time. Instead, we rely on novel recurrent stages to update the pose and shape parameters such that not only losses are minimized effectively, but the process is meta-regularized in order to ensure end-progress. HUND's symmetry between training and testing makes it the first 3d human sensing architecture to natively support different operating regimes including self-supervised ones. In diverse tests, we show that HUND achieves very competitive results in datasets like H3.6M and 3DPW, aswell as good quality 3d reconstructions for complex imagery collected in-the-wild.
Conventional data augmentation realized by performing simple pre-processing operations (\eg, rotation, crop, \etc) has been validated for its advantage in enhancing the performance for medical image segmentation. However, the data generated by these conventional augmentation methods are random and sometimes harmful to the subsequent segmentation. In this paper, we developed a novel automatic learning-based data augmentation method for medical image segmentation which models the augmentation task as a trial-and-error procedure using deep reinforcement learning (DRL). In our method, we innovatively combine the data augmentation module and the subsequent segmentation module in an end-to-end training manner with a consistent loss. Specifically, the best sequential combination of different basic operations is automatically learned by directly maximizing the performance improvement (\ie, Dice ratio) on the available validation set. We extensively evaluated our method on CT kidney tumor segmentation which validated the promising results of our method.
Improving the robustness of neural nets in regression tasks is key to their application in multiple domains. Deep learning-based approaches aim to achieve this goal either by improving the manner in which they produce their prediction of specific values (i.e., point prediction), or by producing prediction intervals (PIs) that quantify uncertainty. We present PIVEN, a deep neural network for producing both a PI and a prediction of specific values. Benchmark experiments show that our approach produces tighter uncertainty bounds than the current state-of-the-art approach for producing PIs, while managing to maintain comparable performance to the state-of-the-art approach for specific value-prediction. Additional evaluation on large image datasets further support our conclusions.
We propose the first stochastic framework to employ uncertainty for RGB-D saliency detection by learning from the data labeling process. Existing RGB-D saliency detection models treat this task as a point estimation problem by predicting a single saliency map following a deterministic learning pipeline. We argue that, however, the deterministic solution is relatively ill-posed. Inspired by the saliency data labeling process, we propose a generative architecture to achieve probabilistic RGB-D saliency detection which utilizes a latent variable to model the labeling variations. Our framework includes two main models: 1) a generator model, which maps the input image and latent variable to stochastic saliency prediction, and 2) an inference model, which gradually updates the latent variable by sampling it from the true or approximate posterior distribution. The generator model is an encoder-decoder saliency network. To infer the latent variable, we introduce two different solutions: i) a Conditional Variational Auto-encoder with an extra encoder to approximate the posterior distribution of the latent variable; and ii) an Alternating Back-Propagation technique, which directly samples the latent variable from the true posterior distribution. Qualitative and quantitative results on six challenging RGB-D benchmark datasets show our approach's superior performance in learning the distribution of saliency maps. The source code is publicly available via our project page: https://github.com/JingZhang617/UCNet.
Detecting Graphical User Interface (GUI) elements in GUI images is a domain-specific object detection task. It supports many software engineering tasks, such as GUI animation and testing, GUI search and code generation. Existing studies for GUI element detection directly borrow the mature methods from computer vision (CV) domain, including old fashioned ones that rely on traditional image processing features (e.g., canny edge, contours), and deep learning models that learn to detect from large-scale GUI data. Unfortunately, these CV methods are not originally designed with the awareness of the unique characteristics of GUIs and GUI elements and the high localization accuracy of the GUI element detection task. We conduct the first large-scale empirical study of seven representative GUI element detection methods on over 50k GUI images to understand the capabilities, limitations and effective designs of these methods. This study not only sheds the light on the technical challenges to be addressed but also informs the design of new GUI element detection methods. We accordingly design a new GUI-specific old-fashioned method for non-text GUI element detection which adopts a novel top-down coarse-to-fine strategy, and incorporate it with the mature deep learning model for GUI text detection.Our evaluation on 25,000 GUI images shows that our method significantly advances the start-of-the-art performance in GUI element detection.
A steady momentum of innovations and breakthroughs has convincingly pushed the limits of unsupervised image representation learning. Compared to static 2D images, video has one more dimension (time). The inherent supervision existing in such sequential structure offers a fertile ground for building unsupervised learning models. In this paper, we compose a trilogy of exploring the basic and generic supervision in the sequence from spatial, spatiotemporal and sequential perspectives. We materialize the supervisory signals through determining whether a pair of samples is from one frame or from one video, and whether a triplet of samples is in the correct temporal order. We uniquely regard the signals as the foundation in contrastive learning and derive a particular form named Sequence Contrastive Learning (SeCo). SeCo shows superior results under the linear protocol on action recognition (Kinetics), untrimmed activity recognition (ActivityNet) and object tracking (OTB-100). More remarkably, SeCo demonstrates considerable improvements over recent unsupervised pre-training techniques, and leads the accuracy by 2.96% and 6.47% against fully-supervised ImageNet pre-training in action recognition task on UCF101 and HMDB51, respectively.
In this work, we aim for temporally consistent semantic segmentation throughout frames in a video. Many semantic segmentation algorithms process images individually which leads to an inconsistent scene interpretation due to illumination changes, occlusions and other variations over time. To achieve a temporally consistent prediction, we train a convolutional neural network (CNN) which propagates features through consecutive frames in a video using a convolutional long short term memory (ConvLSTM) cell. Besides the temporal feature propagation, we penalize inconsistencies in our loss function. We show in our experiments that the performance improves when utilizing video information compared to single frame prediction. The mean intersection over union (mIoU) metric on the Cityscapes validation set increases from 45.2 % for the single frames to 57.9 % for video data after implementing the ConvLSTM to propagate features trough time on the ESPNet. Most importantly, inconsistency decreases from 4.5 % to 1.3 % which is a reduction by 71.1 %. Our results indicate that the added temporal information produces a frame-to-frame consistent and more accurate image understanding compared to single frame processing.