The cryo-electron microscopy (Cryo-EM) becomes popular for macromolecular structure determination. However, the 2D images which Cryo-EM detects are of high noise and often mixed with multiple heterogeneous conformations or contamination, imposing a challenge for denoising. Traditional image denoising methods can not remove Cryo-EM image noise well when the signal-noise-ratio (SNR) of images is meager. Thus it is desired to develop new effective denoising techniques to facilitate further research such as 3D reconstruction, 2D conformation classification, and so on. In this paper, we approach the robust image denoising problem in Cryo-EM by a joint Autoencoder and Generative Adversarial Networks (GAN) method. Equipped with robust $\ell_1$ Autoencoder and some designs of robust $\beta$-GANs, one can stabilize the training of GANs and achieve the state-of-the-art performance of robust denoising with low SNR data and against possible information contamination. The method is evaluated by both a heterogeneous conformational dataset on the Thermus aquaticus RNA Polymerase (RNAP) and a homogenous dataset on the Plasmodium falciparum 80S ribosome dataset (EMPIRE-10028), in terms of Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), as well as heterogeneous conformation clustering. These results suggest that our proposed methodology provides an effective tool for Cryo-EM 2D image denoising.
Heterogeneous domain adaptation (HDA) tackles the learning of cross-domain samples with both different probability distributions and feature representations. Most of existing HDA studies focus on the single-source scenario. In reality, however, it is not uncommon to obtain samples from multiple heterogeneous domains. In this paper, we study the multi-source heterogeneous domain adaptation problem, and propose a Conditional Weighting Adversarial Network (CWAN) to address it. The proposed CWAN adversarially learns a feature transformer, a label classifier, and a domain discriminator. To quantify the importance of different source domains, CWAN introduces a sophisticated conditional weighting scheme to calculate the weights of the source domains according to the conditional distribution divergence between the source and target domains. Different from existing weighting schemes, the proposed conditional weighting scheme not only weights the source domains but also implicitly aligns the conditional distributions during the optimization process. Experimental results clearly demonstrate that the proposed CWAN performs much better than several state-of-the-art methods on three real-world datasets.
Deep learning based models have excelled in many computer vision task and appear to surpass humans performance. However, these models require an avalanche of expensive human labeled training data and many iterations to train their large number of parameters. This severely limits their scalability to the real-world long-tail distributed categories. Learning from such extremely limited labeled examples is known as Few-shot learning. Different to prior arts that leverage meta-learning or data augmentation strategies to alleviate this extremely data-scarce problem, this paper presents a statistical approach, dubbed Instance Credibility Inference to exploit the support of unlabeled instances for few-shot visual recognition. Typically, we repurpose the self-taught learning paradigm. To do so, we construct a (Generalized) Linear Model (LM/GLM) with incidental parameters to model the mapping from (un-)labeled features to their (pseudo-)labels, in which the sparsity of the incidental parameters indicates the credibility of corresponding pseudo-labeled instance. We rank the credibility of pseudo-labels of unlabeled instances along the regularization path of their corresponding incidental parameters, and the most trustworthy pseudo-labeled examples are preserved as the augmented labeled instances.This process is repeated until all the unlabeled samples are iteratively included in the expanded training set. Theoretically, under mild conditions of restricted eigenvalue, irrepresentability, and large error, our approach is guaranteed to collect all the correctly-predicted pseudo-labeled instances from the noisy pseudo-labeled set. Extensive experiments under two few-shot settings show that our approach can establish new state of the art on four widely used few-shot visual recognition benchmark datasets including miniImageNet, tieredImageNet, CIFAR-FS, and CUB.
The prediction and selection of lesion features are two important tasks in voxel-based neuroimage analysis. Existing multivariate learning models take two tasks equivalently and optimize simultaneously. However, in addition to lesion features, we observe that there is another type of feature, which is commonly introduced during the procedure of preprocessing steps, which can improve the prediction result. We call such a type of feature as procedural bias. Therefore, in this paper, we propose that the features/voxels in neuroimage data are consist of three orthogonal parts: lesion features, procedural bias, and null features. To stably select lesion features and leverage procedural bias into prediction, we propose an iterative algorithm (termed GSplit LBI) as a discretization of differential inclusion of inverse scale space, which is the combination of Variable Splitting scheme and Linearized Bregman Iteration (LBI). Specifically, with a variable the splitting term, two estimators are introduced and split apart, i.e. one is for feature selection (the sparse estimator) and the other is for prediction (the dense estimator). Implemented with Linearized Bregman Iteration (LBI), the solution path of both estimators can be returned with different sparsity levels on the sparse estimator for the selection of lesion features. Besides, the dense the estimator can additionally leverage procedural bias to further improve prediction results. To test the efficacy of our method, we conduct experiments on the simulated study and Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The validity and the benefit of our model can be shown by the improvement of prediction results and the interpretability of visualized procedural bias and lesion features.
Over-parameterization is ubiquitous nowadays in training neural networks to benefit both optimization in seeking global optima and generalization in reducing prediction error. However, compressive networks are desired in many real world applications and direct training of small networks may be trapped in local optima. In this paper, instead of pruning or distilling over-parameterized models to compressive ones, we propose a new approach based on differential inclusions of inverse scale spaces. Specifically, it generates a family of models from simple to complex ones that couples a pair of parameters to simultaneously train over-parameterized deep models and structural sparsity on weights of fully connected and convolutional layers. Such a differential inclusion scheme has a simple discretization, proposed as Deep structurally splitting Linearized Bregman Iteration (DessiLBI), whose global convergence analysis in deep learning is established that from any initializations, algorithmic iterations converge to a critical point of empirical risks. Experimental evidence shows that DessiLBI achieve comparable and even better performance than the competitive optimizers in exploring the structural sparsity of several widely used backbones on the benchmark datasets. Remarkably, with early stopping, DessiLBI unveils "winning tickets" in early epochs: the effective sparse structure with comparable test accuracy to fully trained over-parameterized models.
Human infants are able to acquire natural language seemingly easily at an early age. Their language learning seems to occur simultaneously with learning other cognitive functions as well as with playful interactions with the environment and caregivers. From a neuroscientific perspective, natural language is embodied, grounded in most, if not all, sensory and sensorimotor modalities, and acquired by means of crossmodal integration. However, characterising the underlying mechanisms in the brain is difficult and explaining the grounding of language in crossmodal perception and action remains challenging. In this paper, we present a neurocognitive model for language grounding which reflects bio-inspired mechanisms such as an implicit adaptation of timescales as well as end-to-end multimodal abstraction. It addresses developmental robotic interaction and extends its learning capabilities using larger-scale knowledge-based data. In our scenario, we utilise the humanoid robot NICO in obtaining the EMIL data collection, in which the cognitive robot interacts with objects in a children's playground environment while receiving linguistic labels from a caregiver. The model analysis shows that crossmodally integrated representations are sufficient for acquiring language merely from sensory input through interaction with objects in an environment. The representations self-organise hierarchically and embed temporal and spatial information through composition and decomposition. This model can also provide the basis for further crossmodal integration of perceptually grounded cognitive representations.
In self-supervised spatio-temporal representation learning, the temporal resolution and long-short term characteristics are not yet fully explored, which limits representation capabilities of learned models. In this paper, we propose a novel self-supervised method, referred to as video Playback Rate Perception (PRP), to learn spatio-temporal representation in a simple-yet-effective way. PRP roots in a dilated sampling strategy, which produces self-supervision signals about video playback rates for representation model learning. PRP is implemented with a feature encoder, a classification module, and a reconstructing decoder, to achieve spatio-temporal semantic retention in a collaborative discrimination-generation manner. The discriminative perception model follows a feature encoder to prefer perceiving low temporal resolution and long-term representation by classifying fast-forward rates. The generative perception model acts as a feature decoder to focus on comprehending high temporal resolution and short-term representation by introducing a motion-attention mechanism. PRP is applied on typical video target tasks including action recognition and video retrieval. Experiments show that PRP outperforms state-of-the-art self-supervised models with significant margins. Code is available at github.com/yuanyao366/PRP
Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among users. However, an adversary may still be able to infer the private training data by attacking the released model. Differential privacy(DP) provides a statistical guarantee against such attacks, at a privacy of possibly degenerating the accuracy or utility of the trained models. In this paper, we apply a utility enhancement scheme based on Laplacian smoothing for differentially-private federated learning (DP-Fed-LS), where the parameter aggregation with injected Gaussian noise is improved in statistical precision. We provide tight closed-form privacy bounds for both uniform and Poisson subsampling and derive corresponding DP guarantees for differential private federated learning, with or without Laplacian smoothing. Experiments over MNIST, SVHN and Shakespeare datasets show that the proposed method can improve model accuracy with DP-guarantee under both subsampling mechanisms.
Semantic human matting aims to estimate the per-pixel opacity of the foreground human regions. It is quite challenging and usually requires user interactive trimaps and plenty of high quality annotated data. Annotating such kind of data is labor intensive and requires great skills beyond normal users, especially considering the very detailed hair part of humans. In contrast, coarse annotated human dataset is much easier to acquire and collect from the public dataset. In this paper, we propose to use coarse annotated data coupled with fine annotated data to boost end-to-end semantic human matting without trimaps as extra input. Specifically, we train a mask prediction network to estimate the coarse semantic mask using the hybrid data, and then propose a quality unification network to unify the quality of the previous coarse mask outputs. A matting refinement network takes in the unified mask and the input image to predict the final alpha matte. The collected coarse annotated dataset enriches our dataset significantly, allows generating high quality alpha matte for real images. Experimental results show that the proposed method performs comparably against state-of-the-art methods. Moreover, the proposed method can be used for refining coarse annotated public dataset, as well as semantic segmentation methods, which reduces the cost of annotating high quality human data to a great extent.
The task of using machine learning to approximate the mapping $\mathbf{x}\mapsto\sum_{i=1}^d x_i^2$ with $x_i\in[-1,1]$ seems to be a trivial one. Given the knowledge of the separable structure of the function, one can design a sparse network to represent the function very accurately, or even exactly. When such structural information is not available, and we may only use a dense neural network, the optimization procedure to find the sparse network embedded in the dense network is similar to finding the needle in a haystack, using a given number of samples of the function. We demonstrate that the cost (measured by sample complexity) of finding the needle is directly related to the Barron norm of the function. While only a small number of samples is needed to train a sparse network, the dense network trained with the same number of samples exhibits large test loss and a large generalization gap. In order to control the size of the generalization gap, we find that the use of explicit regularization becomes increasingly more important as $d$ increases. The numerically observed sample complexity with explicit regularization scales as $\mathcal{O}(d^{2.5})$, which is in fact better than the theoretically predicted sample complexity that scales as $\mathcal{O}(d^{4})$. Without explicit regularization (also called implicit regularization), the numerically observed sample complexity is significantly higher and is close to $\mathcal{O}(d^{4.5})$.