Semantic segmentation is important in medical image analysis. Inspired by the strong ability of traditional image analysis techniques in capturing shape priors and inter-subject similarity, many deep learning (DL) models have been recently proposed to exploit such prior information and achieved robust performance. However, these two types of important prior information are usually studied separately in existing models. In this paper, we propose a novel DL model to model both type of priors within a single framework. Specifically, we introduce an extra encoder into the classic encoder-decoder structure to form a Siamese structure for the encoders, where one of them takes a target image as input (the image-encoder), and the other concatenates a template image and its foreground regions as input (the template-encoder). The template-encoder encodes the shape priors and appearance characteristics of each foreground class in the template image. A cosine similarity based attention module is proposed to fuse the information from both encoders, to utilize both types of prior information encoded by the template-encoder and model the inter-subject similarity for each foreground class. Extensive experiments on two public datasets demonstrate that our proposed method can produce superior performance to competing methods.
Speaker verification (SV) aims to determine whether the speaker's identity of a test utterance is the same as the reference speech. In the past few years, extracting speaker embeddings using deep neural networks for SV systems has gone mainstream. Recently, different attention mechanisms and Transformer networks have been explored widely in SV fields. However, utilizing the original Transformer in SV directly may have frame-level information waste on output features, which could lead to restrictions on capacity and discrimination of speaker embeddings. Therefore, we propose an approach to derive utterance-level speaker embeddings via a Transformer architecture that uses a novel loss function named diffluence loss to integrate the feature information of different Transformer layers. Therein, the diffluence loss aims to aggregate frame-level features into an utterance-level representation, and it could be integrated into the Transformer expediently. Besides, we also introduce a learnable mel-fbank energy feature extractor named time-domain feature extractor that computes the mel-fbank features more precisely and efficiently than the standard mel-fbank extractor. Combining Diffluence loss and Time-domain feature extractor, we propose a novel Transformer-based time-domain SV model (DT-SV) with faster training speed and higher accuracy. Experiments indicate that our proposed model can achieve better performance in comparison with other models.
We propose to use the Generalized Morse Wavelets (GMWs) instead of commonly-used Morlet (or Gabor) wavelets in the Scattering Transform Network (STN), which we call the GMW-STN, for signal classification problems. The GMWs form a parameterized family of truly analytic wavelets while the Morlet wavelets are only approximately analytic. The analyticity of underlying wavelet filters in the STN is particularly important for nonstationary oscillatory signals such as music signals because it improves interpretability of the STN representations by providing multiscale amplitude and phase (and consequently frequency) information of input signals. We demonstrate the superiority of the GMW-STN over the conventional STN in music genre classification using the so-called GTZAN database. Moreover, we show the performance improvement of the GMW-STN by increasing its number of layers to three over the typical two-layer STN.}
Measuring contributions is a classical problem in cooperative game theory where the Shapley value is the most well-known solution concept. In this paper, we establish the convergence property of the Shapley value in parametric Bayesian learning games where players perform a Bayesian inference using their combined data, and the posterior-prior KL divergence is used as the characteristic function. We show that for any two players, under some regularity conditions, their difference in Shapley value converges in probability to the difference in Shapley value of a limiting game whose characteristic function is proportional to the log-determinant of the joint Fisher information. As an application, we present an online collaborative learning framework that is asymptotically Shapley-fair. Our result enables this to be achieved without any costly computations of posterior-prior KL divergences. Only a consistent estimator of the Fisher information is needed. The framework's effectiveness is demonstrated with experiments using real-world data.
Image matting is a long-standing problem in computer graphics and vision, mostly identified as the accurate estimation of the foreground in input images. We argue that the foreground objects can be represented by different-level information, including the central bodies, large-grained boundaries, refined details, etc. Based on this observation, in this paper, we propose a multi-scale information assembly framework (MSIA-matte) to pull out high-quality alpha mattes from single RGB images. Technically speaking, given an input image, we extract advanced semantics as our subject content and retain initial CNN features to encode different-level foreground expression, then combine them by our well-designed information assembly strategy. Extensive experiments can prove the effectiveness of the proposed MSIA-matte, and we can achieve state-of-the-art performance compared to most existing matting networks.
We present a novel, conditional generative probabilistic model of set-valued data with a tractable log density. This model is a continuous normalizing flow governed by permutation equivariant dynamics. These dynamics are driven by a learnable per-set-element term and pairwise interactions, both parametrized by deep neural networks. We illustrate the utility of this model via applications including (1) complex traffic scene generation conditioned on visually specified map information, and (2) object bounding box generation conditioned directly on images. We train our model by maximizing the expected likelihood of labeled conditional data under our flow, with the aid of a penalty that ensures the dynamics are smooth and hence efficiently solvable. Our method significantly outperforms non-permutation invariant baselines in terms of log likelihood and domain-specific metrics (offroad, collision, and combined infractions), yielding realistic samples that are difficult to distinguish from real data.
Achievable information rates of bipolar 4- and 8-ary constellations are experimentally compared to those of intensity modulation (IM) when using an oversampled direct detection receiver. The bipolar constellations gain up to 1.8 dB over their IM counterparts.
Recently, deep learning-based generative models have been introduced to generate singing voices. One approach is to predict the parametric vocoder features consisting of explicit speech parameters. This approach has the advantage that the meaning of each feature is explicitly distinguished. Another approach is to predict mel-spectrograms for a neural vocoder. However, parametric vocoders have limitations of voice quality and the mel-spectrogram features are difficult to model because the timbre and pitch information are entangled. In this study, we propose a singing voice synthesis model with multi-task learning to use both approaches -- acoustic features for a parametric vocoder and mel-spectrograms for a neural vocoder. By using the parametric vocoder features as auxiliary features, the proposed model can efficiently disentangle and control the timbre and pitch components of the mel-spectrogram. Moreover, a generative adversarial network framework is applied to improve the quality of singing voices in a multi-singer model. Experimental results demonstrate that our proposed model can generate more natural singing voices than the single-task models, while performing better than the conventional parametric vocoder-based model.
We present PlanarRecon -- a novel framework for globally coherent detection and reconstruction of 3D planes from a posed monocular video. Unlike previous works that detect planes in 2D from a single image, PlanarRecon incrementally detects planes in 3D for each video fragment, which consists of a set of key frames, from a volumetric representation of the scene using neural networks. A learning-based tracking and fusion module is designed to merge planes from previous fragments to form a coherent global plane reconstruction. Such design allows PlanarRecon to integrate observations from multiple views within each fragment and temporal information across different ones, resulting in an accurate and coherent reconstruction of the scene abstraction with low-polygonal geometry. Experiments show that the proposed approach achieves state-of-the-art performances on the ScanNet dataset while being real-time.
Deep learning networks have shown promising results in fast magnetic resonance imaging (MRI) reconstruction. In our work, we develop deep networks to further improve the quantitative and the perceptual quality of reconstruction. To begin with, we propose reconsynergynet (RSN), a network that combines the complementary benefits of independently operating on both the image and the Fourier domain. For a single-coil acquisition, we introduce deep cascade RSN (DC-RSN), a cascade of RSN blocks interleaved with data fidelity (DF) units. Secondly, we improve the structure recovery of DC-RSN for T2 weighted Imaging (T2WI) through assistance of T1 weighted imaging (T1WI), a sequence with short acquisition time. T1 assistance is provided to DC-RSN through a gradient of log feature (GOLF) fusion. Furthermore, we propose perceptual refinement network (PRN) to refine the reconstructions for better visual information fidelity (VIF), a metric highly correlated to radiologists opinion on the image quality. Lastly, for multi-coil acquisition, we propose variable splitting RSN (VS-RSN), a deep cascade of blocks, each block containing RSN, multi-coil DF unit, and a weighted average module. We extensively validate our models DC-RSN and VS-RSN for single-coil and multi-coil acquisitions and report the state-of-the-art performance. We obtain a SSIM of 0.768, 0.923, 0.878 for knee single-coil-4x, multi-coil-4x, and multi-coil-8x in fastMRI. We also conduct experiments to demonstrate the efficacy of GOLF based T1 assistance and PRN.