A survey on deep learning in medical image analysis

One of the main challenges in feature learning using Deep Convolutional Neural Networks (DCNNs) for large-scale face recognition is the design of appropriate loss functions that can enhance the discriminative power. Centre loss penalises the distance between deep features and their corresponding class centres in the Euclidean space to achieve intra-class compactness. SphereFace assumes that the linear transformation matrix in the last fully connected layer can be used as a representation of the class centres in the angular space and therefore penalises the angles between deep features and their corresponding weights in a multiplicative way. Recently, a popular line of research is to incorporate margins in well-established loss functions in order to maximise face class separability. In this paper, we propose an Additive Angular Margin Loss (ArcFace) to obtain highly discriminative features for face recognition. The proposed ArcFace has a clear geometric interpretation due to its exact correspondence to geodesic distance on a hypersphere. We present arguably the most extensive experimental evaluation against all recent state-of-the-art face recognition methods on ten face recognition benchmarks which includes a new large-scale image database with trillions of pairs and a large-scale video dataset. We show that ArcFace consistently outperforms the state of the art and can be easily implemented with negligible computational overhead. To facilitate future research, the code has been made available.

/pdf/arcface-additive-angular-margin-loss-for-deep-face-7vvlem659h.pdf

ArcFace: Additive Angular Margin Loss for Deep Face Recognition

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

The objective of this paper is speaker recognition under noisy and unconstrained conditions. 
We make two key contributions. First, we introduce a very large-scale audio-visual speaker recognition dataset collected from open-source media. Using a fully automated pipeline, we curate VoxCeleb2 which contains over a million utterances from over 6,000 speakers. This is several times larger than any publicly available speaker recognition dataset. 
Second, we develop and compare Convolutional Neural Network (CNN) models and training strategies that can effectively recognise identities from voice under various conditions. The models trained on the VoxCeleb2 dataset surpass the performance of previous works on a benchmark dataset by a significant margin.

VoxCeleb2: Deep Speaker Recognition.

One of the main challenges in feature learning using Deep Convolutional Neural Networks (DCNNs) for large-scale face recognition is the design of appropriate loss functions that enhance discriminative power. Centre loss penalises the distance between the deep features and their corresponding class centres in the Euclidean space to achieve intra-class compactness. SphereFace assumes that the linear transformation matrix in the last fully connected layer can be used as a representation of the class centres in an angular space and penalises the angles between the deep features and their corresponding weights in a multiplicative way. Recently, a popular line of research is to incorporate margins in well-established loss functions in order to maximise face class separability. In this paper, we propose an Additive Angular Margin Loss (ArcFace) to obtain highly discriminative features for face recognition. The proposed ArcFace has a clear geometric interpretation due to the exact correspondence to the geodesic distance on the hypersphere. We present arguably the most extensive experimental evaluation of all the recent state-of-the-art face recognition methods on over 10 face recognition benchmarks including a new large-scale image database with trillion level of pairs and a large-scale video dataset. We show that ArcFace consistently outperforms the state-of-the-art and can be easily implemented with negligible computational overhead. We release all refined training data, training codes, pre-trained models and training logs, which will help reproduce the results in this paper.

The quantification of subcortical volume development from 3D fetal ultrasound can provide important diagnostic information during pregnancy monitoring. However, manual segmentation of subcortical structures in ultrasound volumes is time-consuming and challenging due to low soft tissue contrast, speckle and shadowing artifacts. For this reason, we developed a convolutional neural network (CNN) for the automated segmentation of the choroid plexus (CP), lateral posterior ventricle horns (LPVH), cavum septum pellucidum et vergae (CSPV), and cerebellum (CB) from 3D ultrasound. As ground-truth labels are scarce and expensive to obtain, we applied few-shot learning, in which only a small number of manual annotations (n = 9) are used to train a CNN. We compared training a CNN with only a few individually annotated volumes versus many weakly labelled volumes obtained from atlas-based segmentations. This showed that segmentation performance close to intra-observer variability can be obtained with only a handful of manual annotations. Finally, the trained models were applied to a large number (n = 278) of ultrasound image volumes of a diverse, healthy population, obtaining novel US-specific growth curves of the respective structures during the second trimester of gestation.

https://www.biorxiv.org/content/biorxiv/early/2021/10/01/2021.09.29.462430.full.pdf

Subcortical Segmentation of the Fetal Brain in 3D Ultrasound using Deep Learning

The objective of Audio-Visual Segmentation (AVS) is to localise the sounding objects within visual scenes by accurately predicting pixel-wise segmentation masks. To tackle the task, it involves a comprehensive consideration of both the data and model aspects. In this paper, first, we initiate a novel pipeline for generating artificial data for the AVS task without human annotating. We leverage existing image segmentation and audio datasets to match the image-mask pairs with its corresponding audio samples with the linkage of category labels, that allows us to effortlessly compose (image, audio, mask) triplets for training AVS models. The pipeline is annotation-free and scalable to cover a large number of categories. Additionally, we introduce a lightweight approach SAMA-AVS to adapt the pre-trained segment anything model~(SAM) to the AVS task. By introducing only a small number of trainable parameters with adapters, the proposed model can effectively achieve adequate audio-visual fusion and interaction in the encoding stage with vast majority of parameters fixed. We conduct extensive experiments, and the results show our proposed model remarkably surpasses other competing methods. Moreover, by using the proposed model pretrained with our synthetic data, the performance on real AVSBench data is further improved, achieving 83.17 mIoU on S4 subset and 66.95 mIoU on MS3 set.

Annotation-free Audio-Visual Segmentation

The objective of this work is to localize sound sources that are visible in a video without using manual annotations Our key technical contribution is to show that, by training the network to explicitly discriminate challenging image fragments, even for images that do contain the object emitting the sound, we can significantly boost the localization performance We do so elegantly by introducing a mechanism to mine hard samples and add them to a contrastive learning formulation automatically We show that our algorithm achieves state-of-the-art performance on the popular Flickr SoundNet dataset Furthermore, we introduce the VGG-Sound Source (VGG-SS) benchmark, a new set of annotations for the recently-introduced VGG-Sound dataset, where the sound sources visible in each video clip are explicitly marked with bounding box annotations This dataset is 20 times larger than analogous existing ones, contains 5K videos spanning over 200 categories, and, differently from Flickr SoundNet, is video-based On VGG-SS, we also show that our algorithm achieves state-of-the-art performance against several baselines

Localizing Visual Sounds the Hard Way

The objective of this work is to achieve sensorless reconstruction of a 3D volume from a set of 2D freehand ultrasound images with deep implicit representation. In contrast to the conventional way that represents a 3D volume as a discrete voxel grid, we do so by parameterizing it as the zero level-set of a continuous function, i.e. implicitly representing the 3D volume as a mapping from the spatial coordinates to the corresponding intensity values. Our proposed model, termed as ImplicitVol, takes a set of 2D scans and their estimated locations in 3D as input, jointly re?fing the estimated 3D locations and learning a full reconstruction of the 3D volume. When testing on real 2D ultrasound images, novel cross-sectional views that are sampled from ImplicitVol show significantly better visual quality than those sampled from existing reconstruction approaches, outperforming them by over 30% (NCC and SSIM), between the output and ground-truth on the 3D volume testing data. The code will be made publicly available.

ImplicitVol: Sensorless 3D Ultrasound Reconstruction with Deep Implicit Representation.

In this paper, we propose a self-supervised approach for tumor segmentation. Specifically, we advocate a zero-shot setting, where models from self-supervised learning should be directly applicable for the downstream task, without using any manual annotations whatsoever. We make the following contributions. First, with careful examination on existing self-supervised learning approaches, we reveal the surprising result that, given suitable data augmentation, models trained from scratch in fact achieve comparable performance to those pre-trained with self-supervised learning. Second, inspired by the fact that tumors tend to be characterized independently to the contexts, we propose a scalable pipeline for generating synthetic tumor data, and train a self-supervised model that minimises the generalisation gap with the downstream task. Third, we conduct extensive ablation studies on different downstream datasets, BraTS2018 for brain tumor segmentation and LiTS2017 for liver tumor segmentation. While evaluating the model transferability for tumor segmentation under a low-annotation regime, including an extreme case of zero-shot segmentation, the proposed approach demonstrates state-of-the-art performance, substantially outperforming all existing self-supervised approaches, and opening up the usage of self-supervised learning in practical scenarios.

Weidi Xie

Papers

Subcortical Segmentation of the Fetal Brain in 3D Ultrasound using Deep Learning

Annotation-free Audio-Visual Segmentation

Localizing Visual Sounds the Hard Way

ImplicitVol: Sensorless 3D Ultrasound Reconstruction with Deep Implicit Representation.

Self-supervised Tumor Segmentation through Layer Decomposition