Yaniv Nemcovsky, Matan Jacoby, Alex M. Bronstein et al.
Deep neural networks are known to be susceptible to adversarial perturbations -- small perturbations that alter the output of the network and exist under strict norm limitations. While such perturbations are usually discussed as tailored to a specific input, a universal perturbation can be constructed to alter the model's output on a set of inputs. Universal perturbations present a more realistic case of adversarial attacks, as awareness of the model's exact input is not required. In addition, the universal attack setting raises the subject of generalization to unseen data, where given a set of inputs, the universal perturbations aim to alter the model's output on out-of-sample data. In this work, we study physical passive patch adversarial attacks on visual odometry-based autonomous navigation systems. A visual odometry system aims to infer the relative camera motion between two corresponding viewpoints, and is frequently used by vision-based autonomous navigation systems to estimate their state. For such navigation systems, a patch adversarial perturbation poses a severe security issue, as it can be used to mislead a system onto some collision course. To the best of our knowledge, we show for the first time that the error margin of a visual odometry model can be significantly increased by deploying patch adversarial attacks in the scene. We provide evaluation on synthetic closed-loop drone navigation data and demonstrate that a comparable vulnerability exists in real data. A reference implementation of the proposed method and the reported experiments is provided at https://github.com/patchadversarialattacks/patchadversarialattacks.
Dynamic Magnetic Resonance Imaging (MRI) is known to be a powerful and reliable technique for the dynamic imaging of internal organs and tissues, making it a leading diagnostic tool. A major difficulty in using MRI in this setting is the relatively long acquisition time (and, hence, increased cost) required for imaging in high spatio-temporal resolution, leading to the appearance of related motion artifacts and decrease in resolution. Compressed Sensing (CS) techniques have become a common tool to reduce MRI acquisition time by subsampling images in the k-space according to some acquisition trajectory. Several studies have particularly focused on applying deep learning techniques to learn these acquisition trajectories in order to attain better image reconstruction, rather than using some predefined set of trajectories. To the best of our knowledge, learning acquisition trajectories has been only explored in the context of static MRI. In this study, we consider acquisition trajectory learning in the dynamic imaging setting. We design an end-to-end pipeline for the joint optimization of multiple per-frame acquisition trajectories along with a reconstruction neural network, and demonstrate improved image reconstruction quality in shorter acquisition times. The code for reproducing all experiments is accessible at https://github.com/tamirshor7/MultiPILOT.
Deep Neural Networks (DNNs) are highly sensitive to imperceptible malicious perturbations, known as adversarial attacks. Following the discovery of this vulnerability in real-world imaging and vision applications, the associated safety concerns have attracted vast research attention, and many defense techniques have been developed. Most of these defense methods rely on adversarial training (AT) -- training the classification network on images perturbed according to a specific threat model, which defines the magnitude of the allowed modification. Although AT leads to promising results, training on a specific threat model fails to generalize to other types of perturbations. A different approach utilizes a preprocessing step to remove the adversarial perturbation from the attacked image. In this work, we follow the latter path and aim to develop a technique that leads to robust classifiers across various realizations of threat models. To this end, we harness the recent advances in stochastic generative modeling, and means to leverage these for sampling from conditional distributions. Our defense relies on an addition of Gaussian i.i.d noise to the attacked image, followed by a pretrained diffusion process -- an architecture that performs a stochastic iterative process over a denoising network, yielding a high perceptual quality denoised outcome. The obtained robustness with this stochastic preprocessing step is validated through extensive experiments on the CIFAR-10 dataset, showing that our method outperforms the leading defense methods under various threat models.
Robust classification methods predominantly concentrate on algorithms that address a specific threat model, resulting in ineffective defenses against other threat models. Real-world applications are exposed to this vulnerability, as malicious attackers might exploit alternative threat models. In this work, we propose a novel test-time threat model agnostic algorithm that enhances Adversarial-Trained (AT) models. Our method operates through COnditional image transformation and DIstance-based Prediction (CODIP) and includes two main steps: First, we transform the input image into each dataset class, where the input image might be either clean or attacked. Next, we make a prediction based on the shortest transformed distance. The conditional transformation utilizes the perceptually aligned gradients property possessed by AT models and, as a result, eliminates the need for additional models or additional training. Moreover, it allows users to choose the desired balance between clean and robust accuracy without training. The proposed method achieves state-of-the-art results demonstrated through extensive experiments on various models, AT methods, datasets, and attack types. Notably, applying CODIP leads to substantial robust accuracy improvement of up to $+23\%$, $+20\%$, $+26\%$, and $+22\%$ on CIFAR10, CIFAR100, ImageNet and Flowers datasets, respectively.
Aviv A. Rosenberg, Sanketh Vedula, Yaniv Romano et al.
Quantile regression (QR) is a powerful tool for estimating one or more conditional quantiles of a target variable $\mathrm{Y}$ given explanatory features $\boldsymbol{\mathrm{X}}$. A limitation of QR is that it is only defined for scalar target variables, due to the formulation of its objective function, and since the notion of quantiles has no standard definition for multivariate distributions. Recently, vector quantile regression (VQR) was proposed as an extension of QR for vector-valued target variables, thanks to a meaningful generalization of the notion of quantiles to multivariate distributions via optimal transport. Despite its elegance, VQR is arguably not applicable in practice due to several limitations: (i) it assumes a linear model for the quantiles of the target $\boldsymbol{\mathrm{Y}}$ given the features $\boldsymbol{\mathrm{X}}$; (ii) its exact formulation is intractable even for modestly-sized problems in terms of target dimensions, number of regressed quantile levels, or number of features, and its relaxed dual formulation may violate the monotonicity of the estimated quantiles; (iii) no fast or scalable solvers for VQR currently exist. In this work we fully address these limitations, namely: (i) We extend VQR to the non-linear case, showing substantial improvement over linear VQR; (ii) We propose {vector monotone rearrangement}, a method which ensures the quantile functions estimated by VQR are monotone functions; (iii) We provide fast, GPU-accelerated solvers for linear and nonlinear VQR which maintain a fixed memory footprint, and demonstrate that they scale to millions of samples and thousands of quantile levels; (iv) We release an optimized python package of our solvers as to widespread the use of VQR in real-world applications.
Hyperparameter tuning is a common technique for improving the performance of neural networks. Most techniques for hyperparameter search involve an iterated process where the model is retrained at every iteration. However, the expected accuracy improvement from every additional search iteration, is still unknown. Calculating the expected improvement can help create stopping rules for hyperparameter tuning and allow for a wiser allocation of a project's computational budget. In this paper, we establish an empirical estimate for the expected accuracy improvement from an additional iteration of hyperparameter search. Our results hold for any hyperparameter tuning method which is based on random search \cite{bergstra2012random} and samples hyperparameters from a fixed distribution. We bound our estimate with an error of $O\left(\sqrt{\frac{\log k}{k}}\right)$ w.h.p. where $k$ is the current number of iterations. To the best of our knowledge this is the first bound on the expected gain from an additional iteration of hyperparameter search. Finally, we demonstrate that the optimal estimate for the expected accuracy will still have an error of $\frac{1}{k}$.
Barak Gahtan, Reuven Cohen, Alex M. Bronstein et al.
We study the problem of real-time scheduling in a multi-hop millimeter-wave (mmWave) mesh. We develop a model-free deep reinforcement learning algorithm called Adaptive Activator RL (AARL), which determines the subset of mmWave links that should be activated during each time slot and the power level for each link. The most important property of AARL is its ability to make scheduling decisions within the strict time slot constraints of typical 5G mmWave networks. AARL can handle a variety of network topologies, network loads, and interference models, it can also adapt to different workloads. We demonstrate the operation of AARL on several topologies: a small topology with 10 links, a moderately-sized mesh with 48 links, and a large topology with 96 links. We show that for each topology, we compare the throughput obtained by AARL to that of a benchmark algorithm called RPMA (Residual Profit Maximizer Algorithm). The most important advantage of AARL compared to RPMA is that it is much faster and can make the necessary scheduling decisions very rapidly during every time slot, while RPMA cannot. In addition, the quality of the scheduling decisions made by AARL outperforms those made by RPMA.
Marco Pegoraro, Sanketh Vedula, Aviv A. Rosenberg et al.
Quantile regression (QR) is a statistical tool for distribution-free estimation of conditional quantiles of a target variable given explanatory features. QR is limited by the assumption that the target distribution is univariate and defined on an Euclidean domain. Although the notion of quantiles was recently extended to multi-variate distributions, QR for multi-variate distributions on manifolds remains underexplored, even though many important applications inherently involve data distributed on, e.g., spheres (climate and geological phenomena), and tori (dihedral angles in proteins). By leveraging optimal transport theory and c-concave functions, we meaningfully define conditional vector quantile functions of high-dimensional variables on manifolds (M-CVQFs). Our approach allows for quantile estimation, regression, and computation of conditional confidence sets and likelihoods. We demonstrate the approach's efficacy and provide insights regarding the meaning of non-Euclidean quantiles through synthetic and real data experiments.
Eyal Rozenberg, Aviv Karnieli, Ofir Yesharim et al.
We propose a novel, physically-constrained and differentiable approach for the generation of D-dimensional qudit states via spontaneous parametric down-conversion (SPDC) in quantum optics. We circumvent any limitations imposed by the inherently stochastic nature of the physical process and incorporate a set of stochastic dynamical equations governing its evolution under the SPDC Hamiltonian. We demonstrate the effectiveness of our model through the design of structured nonlinear photonic crystals (NLPCs) and shaped pump beams; and show, theoretically and experimentally, how to generate maximally entangled states in the spatial degree of freedom. The learning of NLPC structures offers a promising new avenue for shaping and controlling arbitrary quantum states and enables all-optical coherent control of the generated states. We believe that this approach can readily be extended from bulky crystals to thin Metasurfaces and potentially applied to other quantum systems sharing a similar Hamiltonian structures, such as superfluids and superconductors.
Vision-Transformers are widely used in various vision tasks. Meanwhile, there is another line of works starting with the MLP-mixer trying to achieve similar performance using mlp-based architectures. Interestingly, until now those mlp-based architectures have not been adapted for NLP tasks. Additionally, until now, mlp-based architectures have failed to achieve state-of-the-art performance in vision tasks. In this paper, we analyze the expressive power of mlp-based architectures in modeling dependencies between multiple different inputs simultaneously, and show an exponential gap between the attention and the mlp-based mechanisms. Our results suggest a theoretical explanation for the mlp inability to compete with attention-based mechanisms in NLP problems, they also suggest that the performance gap in vision tasks may be due to the mlp relative weakness in modeling dependencies between multiple different locations, and that combining smart input permutations with mlp architectures may not be enough to close the performance gap alone.
Dynamic Magnetic Resonance Imaging (MRI) is a crucial non-invasive method used to capture the movement of internal organs and tissues, making it a key tool for medical diagnosis. However, dynamic MRI faces a major challenge: long acquisition times needed to achieve high spatial and temporal resolution. This leads to higher costs, patient discomfort, motion artifacts, and lower image quality. Compressed Sensing (CS) addresses this problem by acquiring a reduced amount of MR data in the Fourier domain, based on a chosen sampling pattern, and reconstructing the full image from this partial data. While various deep learning methods have been developed to optimize these sampling patterns and improve reconstruction, they often struggle with slow optimization and inference times or are limited to specific temporal dimensions used during training. In this work, we introduce a novel deep-compressed sensing approach that uses 3D window attention and flexible, temporally extendable acquisition trajectories. Our method significantly reduces both training and inference times compared to existing approaches, while also adapting to different temporal dimensions during inference without requiring additional training. Tests with real data show that our approach outperforms current state-of-theart techniques. The code for reproducing all experiments will be made available upon acceptance of the paper.
Evgenii Zheltonozhskii, Chaim Baskin, Avi Mendelson et al.
The success of learning with noisy labels (LNL) methods relies heavily on the success of a warm-up stage where standard supervised training is performed using the full (noisy) training set. In this paper, we identify a "warm-up obstacle": the inability of standard warm-up stages to train high quality feature extractors and avert memorization of noisy labels. We propose "Contrast to Divide" (C2D), a simple framework that solves this problem by pre-training the feature extractor in a self-supervised fashion. Using self-supervised pre-training boosts the performance of existing LNL approaches by drastically reducing the warm-up stage's susceptibility to noise level, shortening its duration, and improving extracted feature quality. C2D works out of the box with existing methods and demonstrates markedly improved performance, especially in the high noise regime, where we get a boost of more than 27% for CIFAR-100 with 90% noise over the previous state of the art. In real-life noise settings, C2D trained on mini-WebVision outperforms previous works both in WebVision and ImageNet validation sets by 3% top-1 accuracy. We perform an in-depth analysis of the framework, including investigating the performance of different pre-training approaches and estimating the effective upper bound of the LNL performance with semi-supervised learning. Code for reproducing our experiments is available at https://github.com/ContrastToDivide/C2D
We present Self-Classifier -- a novel self-supervised end-to-end classification learning approach. Self-Classifier learns labels and representations simultaneously in a single-stage end-to-end manner by optimizing for same-class prediction of two augmented views of the same sample. To guarantee non-degenerate solutions (i.e., solutions where all labels are assigned to the same class) we propose a mathematically motivated variant of the cross-entropy loss that has a uniform prior asserted on the predicted labels. In our theoretical analysis, we prove that degenerate solutions are not in the set of optimal solutions of our approach. Self-Classifier is simple to implement and scalable. Unlike other popular unsupervised classification and contrastive representation learning approaches, it does not require any form of pre-training, expectation-maximization, pseudo-labeling, external clustering, a second network, stop-gradient operation, or negative pairs. Despite its simplicity, our approach sets a new state of the art for unsupervised classification of ImageNet; and even achieves comparable to state-of-the-art results for unsupervised representation learning. Code is available at https://github.com/elad-amrani/self-classifier.
Evgenii Zheltonozhskii, Chaim Baskin, Alex M. Bronstein et al.
Unsupervised learning has always been appealing to machine learning researchers and practitioners, allowing them to avoid an expensive and complicated process of labeling the data. However, unsupervised learning of complex data is challenging, and even the best approaches show much weaker performance than their supervised counterparts. Self-supervised deep learning has become a strong instrument for representation learning in computer vision. However, those methods have not been evaluated in a fully unsupervised setting. In this paper, we propose a simple scheme for unsupervised classification based on self-supervised representations. We evaluate the proposed approach with several recent self-supervised methods showing that it achieves competitive results for ImageNet classification (39% accuracy on ImageNet with 1000 clusters and 46% with overclustering). We suggest adding the unsupervised evaluation to a set of standard benchmarks for self-supervised learning. The code is available at https://github.com/Randl/kmeans_selfsuper
One of the key factors of enabling machine learning models to comprehend and solve real-world tasks is to leverage multimodal data. Unfortunately, annotation of multimodal data is challenging and expensive. Recently, self-supervised multimodal methods that combine vision and language were proposed to learn multimodal representations without annotation. However, these methods often choose to ignore the presence of high levels of noise and thus yield sub-optimal results. In this work, we show that the problem of noise estimation for multimodal data can be reduced to a multimodal density estimation task. Using multimodal density estimation, we propose a noise estimation building block for multimodal representation learning that is based strictly on the inherent correlation between different modalities. We demonstrate how our noise estimation can be broadly integrated and achieves comparable results to state-of-the-art performance on five different benchmark datasets for two challenging multimodal tasks: Video Question Answering and Text-To-Video Retrieval. Furthermore, we provide a theoretical probabilistic error bound substantiating our empirical results and analyze failure cases. Code: https://github.com/elad-amrani/ssml.
Neural network quantization enables the deployment of large models on resource-constrained devices. Current post-training quantization methods fall short in terms of accuracy for INT4 (or lower) but provide reasonable accuracy for INT8 (or above). In this work, we study the effect of quantization on the structure of the loss landscape. Additionally, we show that the structure is flat and separable for mild quantization, enabling straightforward post-training quantization methods to achieve good results. We show that with more aggressive quantization, the loss landscape becomes highly non-separable with steep curvature, making the selection of quantization parameters more challenging. Armed with this understanding, we design a method that quantizes the layer parameters jointly, enabling significant accuracy improvement over current post-training quantization methods. Reference implementation is available at https://github.com/ynahshan/nn-quantization-pytorch/tree/master/lapq
Chaim Baskin, Brian Chmiel, Evgenii Zheltonozhskii et al.
Convolutional neural networks (CNNs) have become the dominant neural network architecture for solving visual processing tasks. One of the major obstacles hindering the ubiquitous use of CNNs for inference is their relatively high memory bandwidth requirements, which can be a main energy consumer and throughput bottleneck in hardware accelerators. Accordingly, an efficient feature map compression method can result in substantial performance gains. Inspired by quantization-aware training approaches, we propose a compression-aware training (CAT) method that involves training the model in a way that allows better compression of feature maps during inference. Our method trains the model to achieve low-entropy feature maps, which enables efficient compression at inference time using classical transform coding methods. CAT significantly improves the state-of-the-art results reported for quantization. For example, on ResNet-34 we achieve 73.1% accuracy (0.2% degradation from the baseline) with an average representation of only 1.79 bits per value. Reference implementation accompanies the paper at https://github.com/CAT-teams/CAT
Convolutional neural networks (CNNs) achieve state-of-the-art accuracy in a variety of tasks in computer vision and beyond. One of the major obstacles hindering the ubiquitous use of CNNs for inference on low-power edge devices is their high computational complexity and memory bandwidth requirements. The latter often dominates the energy footprint on modern hardware. In this paper, we introduce a lossy transform coding approach, inspired by image and video compression, designed to reduce the memory bandwidth due to the storage of intermediate activation calculation results. Our method does not require fine-tuning the network weights and halves the data transfer volumes to the main memory by compressing feature maps, which are highly correlated, with variable length coding. Our method outperform previous approach in term of the number of bits per value with minor accuracy degradation on ResNet-34 and MobileNetV2. We analyze the performance of our approach on a variety of CNN architectures and demonstrate that FPGA implementation of ResNet-18 with our approach results in a reduction of around 40% in the memory energy footprint, compared to quantized network, with negligible impact on accuracy. When allowing accuracy degradation of up to 2%, the reduction of 60% is achieved. A reference implementation is available at https://github.com/CompressTeam/TransformCodingInference
Barak Gahtan, Robert J. Shahla, Alex M. Bronstein et al.
The increasing adoption of the QUIC transport protocol has transformed encrypted web traffic, necessitating new methodologies for network analysis. However, existing datasets lack the scope, metadata, and decryption capabilities required for robust benchmarking in encrypted traffic research. We introduce VisQUIC, a large-scale dataset of 100,000 labeled QUIC traces from over 44,000 websites, collected over four months. Unlike prior datasets, VisQUIC provides SSL keys for controlled decryption, supports multiple QUIC implementations (Chromium QUIC, Facebooks mvfst, Cloudflares quiche), and introduces a novel image-based representation that enables machine learning-driven encrypted traffic analysis. The dataset includes standardized benchmarking tools, ensuring reproducibility. To demonstrate VisQUICs utility, we present a benchmarking task for estimating HTTP/3 responses in encrypted QUIC traffic, achieving 97% accuracy using only observable packet features. By publicly releasing VisQUIC, we provide an open foundation for advancing encrypted traffic analysis, QUIC security research, and network monitoring.
Sai Advaith Maddipatla, Nadav Bojan Sellam, Sanketh Vedula et al.
Proteins are dynamic, adopting ensembles of conformations. The nature of this conformational heterogenity is imprinted in the raw electron density measurements obtained from X-ray crystallography experiments. Fitting an ensemble of protein structures to these measurements is a challenging, ill-posed inverse problem. We propose a non-i.i.d. ensemble guidance approach to solve this problem using existing protein structure generative models and demonstrate that it accurately recovers complicated multi-modal alternate protein backbone conformations observed in certain single crystal measurements.
Fine-tuning Large Language Models (LLMs) typically involves updating at least a few billions of parameters. A more parameter-efficient approach is Prompt Tuning (PT), which updates only a few learnable tokens, and differently, In-Context Learning (ICL) adapts the model to a new task by simply including examples in the input without any training. When applying optimization-based methods, such as fine-tuning and PT for few-shot learning, the model is specifically adapted to the small set of training examples, whereas ICL leaves the model unchanged. This distinction makes traditional learning methods more prone to overfitting; in contrast, ICL is less sensitive to the few-shot scenario. While ICL is not prone to overfitting, it does not fully extract the information that exists in the training examples. This work introduces Context-aware Prompt Tuning (CPT), a method inspired by ICL, PT, and adversarial attacks. We build on the ICL strategy of concatenating examples before the input, but we extend this by PT-like learning, refining the context embedding through iterative optimization to extract deeper insights from the training examples. We carefully modify specific context tokens, considering the unique structure of input and output formats. Inspired by adversarial attacks, we adjust the input based on the labels present in the context, focusing on minimizing, rather than maximizing, the loss. Moreover, we apply a projected gradient descent algorithm to keep token embeddings close to their original values, under the assumption that the user-provided data is inherently valuable. Our method has been shown to achieve superior accuracy across multiple classification tasks using various LLM models.
We introduce XTRA, a vision model pre-trained with a novel auto-regressive objective that significantly enhances both sample and parameter efficiency compared to previous auto-regressive image models. Unlike contrastive or masked image modeling methods, which have not been demonstrated as having consistent scaling behavior on unbalanced internet data, auto-regressive vision models exhibit scalable and promising performance as model and dataset size increase. In contrast to standard auto-regressive models, XTRA employs a Block Causal Mask, where each Block represents k $\times$ k tokens rather than relying on a standard causal mask. By reconstructing pixel values block by block, XTRA captures higher-level structural patterns over larger image regions. Predicting on blocks allows the model to learn relationships across broader areas of pixels, enabling more abstract and semantically meaningful representations than traditional next-token prediction. This simple modification yields two key results. First, XTRA is sample-efficient. Despite being trained on 152$\times$ fewer samples (13.1M vs. 2B), XTRA ViT-H/14 surpasses the top-1 average accuracy of the previous state-of-the-art auto-regressive model across 15 diverse image recognition benchmarks. Second, XTRA is parameter-efficient. Compared to auto-regressive models trained on ImageNet-1k, XTRA ViT-B/16 outperforms in linear and attentive probing tasks, using 7-16$\times$ fewer parameters (85M vs. 1.36B/0.63B).
Barak Gahtan, Reuven Cohen, Alex M. Bronstein et al.
Remote control of robotic systems, also known as teleoperation, is crucial for the development of autonomous vehicle (AV) technology. It allows a remote operator to view live video from AVs and, in some cases, to make real-time decisions. The effectiveness of video-based teleoperation systems is heavily influenced by the quality of the cellular network and, in particular, its packet loss rate and latency. To optimize these parameters, an AV can be connected to multiple cellular networks and determine in real time over which cellular network each video packet will be transmitted. We present an algorithm, called Active Network Selector (ANS), which uses a time series machine learning approach for solving this problem. We compare ANS to a baseline non-learning algorithm, which is used today in commercial systems, and show that ANS performs much better, with respect to both packet loss and packet latency.
Nadav Bojan Sellam, Meital Bojan, Paul Schanda et al.
Accurate protein structures are essential for understanding biological function, yet incorporating experimental data into protein generative models remains a major challenge. Most predictors of experimental observables are non-differentiable, making them incompatible with gradient-based conditional sampling. This is especially limiting in nuclear magnetic resonance, where rich data such as chemical shifts are hard to directly integrate into generative modeling. We introduce a framework for non-differentiable guidance of protein generative models, coupling a continuous diffusion-based generator with any black-box objective via a tailored genetic algorithm. We demonstrate its effectiveness across three modalities: pairwise distance constraints, nuclear Overhauser effect restraints, and for the first time chemical shifts. These results establish chemical shift guided structure generation as feasible, expose key weaknesses in current predictors, and showcase a general strategy for incorporating diverse experimental signals. Our work points toward automated, data-conditioned protein modeling beyond the limits of differentiability.
Deep temporal architectures such as Temporal Convolutional Networks (TCNs) achieve strong predictive performance on sequential data, yet theoretical understanding of their generalization remains limited. We address this gap by providing both the first non-vacuous, architecture-aware generalization bounds for deep temporal models and a principled evaluation methodology. For exponentially $β$-mixing sequences, we derive bounds scaling as $ O\!\Bigl(R\,\sqrt{\tfrac{D\,p\,n\,\log N}{N}}\Bigr), $ where $D$ is network depth, $p$ kernel size, $n$ input dimension, and $R$ weight norm. Our delayed-feedback blocking mechanism transforms dependent samples into effectively independent ones while discarding only $O(1/\log N)$ of the data, yielding $\sqrt{D}$ scaling instead of exponential, implying that doubling depth requires approximately quadrupling the training data. We also introduce a fair-comparison methodology that fixes the effective sample size to isolate the effect of temporal structure from information content. Under $N_{\text{eff}}=2{,}000$, strongly dependent sequences ($ρ=0.8$) exhibit $\approx76\%$ smaller generalization gaps than weakly dependent ones ($ρ=0.2$), challenging the intuition that dependence is purely detrimental. Yet convergence rates diverge from theory: weak dependencies follow $N_{\text{eff}}^{-1.21}$ scaling and strong dependencies follow $N_{\text{eff}}^{-0.89}$, both steeper than the predicted $N^{-0.5}$. These findings reveal that temporal dependence can enhance learning under fixed information budgets, while highlighting gaps between theory and practice that motivate future research.
Implicit Neural Representations (INRs) have been recently garnering increasing interest in various research fields, mainly due to their ability to represent large, complex data in a compact and continuous manner. Past work further showed that numerous popular downstream tasks can be performed directly in the INR parameter-space. Doing so can substantially reduce the computational resources required to process the represented data in their native domain. A major difficulty in using modern machine-learning approaches, is their high susceptibility to adversarial attacks, which have been shown to greatly limit the reliability and applicability of such methods in a wide range of settings. In this work, we show that parameter-space models trained for classification are inherently robust to adversarial attacks -- without the need of any robust training. To support our claims, we develop a novel suite of adversarial attacks targeting parameter-space classifiers, and furthermore analyze practical considerations of attacking parameter-space classifiers.
Sanketh Vedula, Valentino Maiorca, Lorenzo Basile et al.
Aligning data from different domains is a fundamental problem in machine learning with broad applications across very different areas, most notably aligning experimental readouts in single-cell multiomics. Mathematically, this problem can be formulated as the minimization of disagreement of pair-wise quantities such as distances and is related to the Gromov-Hausdorff and Gromov-Wasserstein distances. Computationally, it is a quadratic assignment problem (QAP) that is known to be NP-hard. Prior works attempted to solve the QAP directly with entropic or low-rank regularization on the permutation, which is computationally tractable only for modestly-sized inputs, and encode only limited inductive bias related to the domains being aligned. We consider the alignment of metric structures formulated as a discrete Gromov-Wasserstein problem and instead of solving the QAP directly, we propose to learn a related well-scalable linear assignment problem (LAP) whose solution is also a minimizer of the QAP. We also show a flexible extension of the proposed framework to general non-metric dissimilarities through differentiable ranks. We extensively evaluate our approach on synthetic and real datasets from single-cell multiomics and neural latent spaces, achieving state-of-the-art performance while being conceptually and computationally simple.
Breast cancer is a prominent health concern worldwide, currently being the secondmost common and second-deadliest type of cancer in women. While current breast cancer diagnosis mainly relies on mammography imaging, in recent years the use of thermography for breast cancer imaging has been garnering growing popularity. Thermographic imaging relies on infrared cameras to capture body-emitted heat distributions. While these heat signatures have proven useful for computer-vision systems for accurate breast cancer segmentation and classification, prior work often relies on handcrafted feature engineering or complex architectures, potentially limiting the comparability and applicability of these methods. In this work, we present a novel algorithm for both breast cancer classification and segmentation. Rather than focusing efforts on manual feature and architecture engineering, our algorithm focuses on leveraging an informative, learned feature space, thus making our solution simpler to use and extend to other frameworks and downstream tasks, as well as more applicable to data-scarce settings. Our classification produces SOTA results, while we are the first work to produce segmentation regions studied in this paper.
A central challenge in building robotic prostheses is the creation of a sensor-based system able to read physiological signals from the lower limb and instruct a robotic hand to perform various tasks. Existing systems typically perform discrete gestures such as pointing or grasping, by employing electromyography (EMG) or ultrasound (US) technologies to analyze muscle states. While estimating finger gestures has been done in the past by detecting prominent gestures, we are interested in detection, or inference, done in the context of fine motions that evolve over time. Examples include motions occurring when performing fine and dexterous tasks such as keyboard typing or piano playing. We consider this task as an important step towards higher adoption rates of robotic prostheses among arm amputees, as it has the potential to dramatically increase functionality in performing daily tasks. To this end, we present an end-to-end robotic system, which can successfully infer fine finger motions. This is achieved by modeling the hand as a robotic manipulator and using it as an intermediate representation to encode muscles' dynamics from a sequence of US images. We evaluated our method by collecting data from a group of subjects and demonstrating how it can be used to replay music played or text typed. To the best of our knowledge, this is the first study demonstrating these downstream tasks within an end-to-end system.
Eyal Rozenberg, Aviv Karnieli, Ofir Yesharim et al.
Spontaneous parametric down-conversion in quantum optics is an invaluable resource for the realization of high-dimensional qudits with spatial modes of light. One of the main open challenges is how to directly generate a desirable qudit state in the SPDC process. This problem can be addressed through advanced computational learning methods; however, due to difficulties in modeling the SPDC process by a fully differentiable algorithm that takes into account all interaction effects, progress has been limited. Here, we overcome these limitations and introduce a physically-constrained and differentiable model, validated against experimental results for shaped pump beams and structured crystals, capable of learning every interaction parameter in the process. We avoid any restrictions induced by the stochastic nature of our physical model and integrate the dynamic equations governing the evolution under the SPDC Hamiltonian. We solve the inverse problem of designing a nonlinear quantum optical system that achieves the desired quantum state of down-converted photon pairs. The desired states are defined using either the second-order correlations between different spatial modes or by specifying the required density matrix. By learning nonlinear volume holograms as well as different pump shapes, we successfully show how to generate maximally entangled states. Furthermore, we simulate all-optical coherent control over the generated quantum state by actively changing the profile of the pump beam. Our work can be useful for applications such as novel designs of high-dimensional quantum key distribution and quantum information processing protocols. In addition, our method can be readily applied for controlling other degrees of freedom of light in the SPDC process, such as the spectral and temporal properties, and may even be used in condensed-matter systems having a similar interaction Hamiltonian.
Understating and controlling generative models' latent space is a complex task. In this paper, we propose a novel method for learning to control any desired attribute in a pre-trained GAN's latent space, for the purpose of editing synthesized and real-world data samples accordingly. We perform Sim2Real learning, relying on minimal samples to achieve an unlimited amount of continuous precise edits. We present an Autoencoder-based model that learns to encode the semantics of changes between images as a basis for editing new samples later on, achieving precise desired results - example shown in Fig. 1. While previous editing methods rely on a known structure of latent spaces (e.g., linearity of some semantics in StyleGAN), our method inherently does not require any structural constraints. We demonstrate our method in the domain of facial imagery: editing different expressions, poses, and lighting attributes, achieving state-of-the-art results.
Multiple-input multiple-output (MIMO) radar is one of the leading depth sensing modalities. However, the usage of multiple receive channels lead to relative high costs and prevent the penetration of MIMOs in many areas such as the automotive industry. Over the last years, few studies concentrated on designing reduced measurement schemes and image reconstruction schemes for MIMO radars, however these problems have been so far addressed separately. On the other hand, recent works in optical computational imaging have demonstrated growing success of simultaneous learning-based design of the acquisition and reconstruction schemes, manifesting significant improvement in the reconstruction quality. Inspired by these successes, in this work, we propose to learn MIMO acquisition parameters in the form of receive (Rx) antenna elements locations jointly with an image neural-network based reconstruction. To this end, we propose an algorithm for training the combined acquisition-reconstruction pipeline end-to-end in a differentiable way. We demonstrate the significance of using our learned acquisition parameters with and without the neural-network reconstruction.
Judith Hermanns, Anton Tsitsulin, Marina Munkhoeva et al.
What is the best way to match the nodes of two graphs? This graph alignment problem generalizes graph isomorphism and arises in applications from social network analysis to bioinformatics. Some solutions assume that auxiliary information on known matches or node or edge attributes is available, or utilize arbitrary graph features. Such methods fare poorly in the pure form of the problem, in which only graph structures are given. Other proposals translate the problem to one of aligning node embeddings, yet, by doing so, provide only a single-scale view of the graph. In this paper, we transfer the shape-analysis concept of functional maps from the continuous to the discrete case, and treat the graph alignment problem as a special case of the problem of finding a mapping between functions on graphs. We present GRASP, a method that first establishes a correspondence between functions derived from Laplacian matrix eigenvectors, which capture multiscale structural characteristics, and then exploits this correspondence to align nodes. Our experimental study, featuring noise levels higher than anything used in previous studies, shows that GRASP outperforms state-of-the-art methods for graph alignment across noise levels and graph types.
Nowadays, there is an abundance of data involving images and surrounding free-form text weakly corresponding to those images. Weakly Supervised phrase-Grounding (WSG) deals with the task of using this data to learn to localize (or to ground) arbitrary text phrases in images without any additional annotations. However, most recent SotA methods for WSG assume the existence of a pre-trained object detector, relying on it to produce the ROIs for localization. In this work, we focus on the task of Detector-Free WSG (DF-WSG) to solve WSG without relying on a pre-trained detector. We directly learn everything from the images and associated free-form text pairs, thus potentially gaining an advantage on the categories unsupported by the detector. The key idea behind our proposed Grounding by Separation (GbS) method is synthesizing `text to image-regions' associations by random alpha-blending of arbitrary image pairs and using the corresponding texts of the pair as conditions to recover the alpha map from the blended image via a segmentation network. At test time, this allows using the query phrase as a condition for a non-blended query image, thus interpreting the test image as a composition of a region corresponding to the phrase and the complement region. Using this approach we demonstrate a significant accuracy improvement, of up to $8.5\%$ over previous DF-WSG SotA, for a range of benchmarks including Flickr30K, Visual Genome, and ReferIt, as well as a significant complementary improvement (above $7\%$) over the detector-based approaches for WSG.
Eyal Rozenberg, Aviv Karnieli, Ofir Yesharim et al.
We introduce a systematic approach for designing 3D nonlinear photonic crystals and pump beams for generating desired quantum correlations between structured photon-pairs. Our model is fully differentiable, allowing accurate and efficient learning and discovery of novel designs.
Nowadays, many of the images captured are `observed' by machines only and not by humans, e.g., in autonomous systems. High-level machine vision models, such as object recognition or semantic segmentation, assume images are transformed into some canonical image space by the camera \ans{Image Signal Processor (ISP)}. However, the camera ISP is optimized for producing visually pleasing images for human observers and not for machines. Therefore, one may spare the ISP compute time and apply vision models directly to RAW images. Yet, it has been shown that training such models directly on RAW images results in a performance drop. To mitigate this drop, we use a RAW and RGB image pairs dataset, which can be easily acquired with no human labeling. We then train a model that is applied directly to the RAW data by using knowledge distillation such that the model predictions for RAW images will be aligned with the predictions of an off-the-shelf pre-trained model for processed RGB images. Our experiments show that our performance on RAW images for object classification and semantic segmentation is significantly better than models trained on labeled RAW images. It also reasonably matches the predictions of a pre-trained model on processed RGB images, while saving the ISP compute overhead.
Energy-saving LIDAR camera for short distances estimates an object's distance using temporally intensity-coded laser light pulses and calculates the maximum correlation with the back-scattered pulse. Though on low power, the backs-scattered pulse is noisy and unstable, which leads to inaccurate and unreliable depth estimation. To address this problem, we use GANs (Generative Adversarial Networks), which are two neural networks that can learn complicated class distributions through an adversarial process. We learn the LIDAR camera's hidden properties and behavior, creating a novel, fully unsupervised forward model that simulates the camera. Then, we use the model's differentiability to explore the camera parameter space and optimize those parameters in terms of depth, accuracy, and stability. To achieve this goal, we also propose a new custom loss function designated to the back-scattered code distribution's weaknesses and its circular behavior. The results are demonstrated on both synthetic and real data.
Mechanical image stabilization using actuated gimbals enables capturing long-exposure shots without suffering from blur due to camera motion. These devices, however, are often physically cumbersome and expensive, limiting their widespread use. In this work, we propose to digitally emulate a mechanically stabilized system from the input of a fast unstabilized camera. To exploit the trade-off between motion blur at long exposures and low SNR at short exposures, we train a CNN that estimates a sharp high-SNR image by aggregating a burst of noisy short-exposure frames, related by unknown motion. We further suggest learning the burst's exposure times in an end-to-end manner, thus balancing the noise and blur across the frames. We demonstrate this method's advantage over the traditional approach of deblurring a single image or denoising a fixed-exposure burst on both synthetic and real data.
Jonathan Alush-Aben, Linor Ackerman-Schraier, Tomer Weiss et al.
Magnetic Resonance Imaging (MRI) has long been considered to be among the gold standards of today's diagnostic imaging. The most significant drawback of MRI is long acquisition times, prohibiting its use in standard practice for some applications. Compressed sensing (CS) proposes to subsample the k-space (the Fourier domain dual to the physical space of spatial coordinates) leading to significantly accelerated acquisition. However, the benefit of compressed sensing has not been fully exploited; most of the sampling densities obtained through CS do not produce a trajectory that obeys the stringent constraints of the MRI machine imposed in practice. Inspired by recent success of deep learning based approaches for image reconstruction and ideas from computational imaging on learning-based design of imaging systems, we introduce 3D FLAT, a novel protocol for data-driven design of 3D non-Cartesian accelerated trajectories in MRI. Our proposal leverages the entire 3D k-space to simultaneously learn a physically feasible acquisition trajectory with a reconstruction method. Experimental results, performed as a proof-of-concept, suggest that 3D FLAT achieves higher image quality for a given readout time compared to standard trajectories such as radial, stack-of-stars, or 2D learned trajectories (trajectories that evolve only in the 2D plane while fully sampling along the third dimension). Furthermore, we demonstrate evidence supporting the significant benefit of performing MRI acquisitions using non-Cartesian 3D trajectories over 2D non-Cartesian trajectories acquired slice-wise.
David H. Silver, Martin Feder, Yael Gold-Zamir et al.
The process of fertilizing a human egg outside the body in order to help those suffering from infertility to conceive is known as in vitro fertilization (IVF). Despite being the most effective method of assisted reproductive technology (ART), the average success rate of IVF is a mere 20-40%. One step that is critical to the success of the procedure is selecting which embryo to transfer to the patient, a process typically conducted manually and without any universally accepted and standardized criteria. In this paper we describe a novel data-driven system trained to directly predict embryo implantation probability from embryogenesis time-lapse imaging videos. Using retrospectively collected videos from 272 embryos, we demonstrate that, when compared to an external panel of embryologists, our algorithm results in a 12% increase of positive predictive value and a 29% increase of negative predictive value.
Alex Karbachevsky, Chaim Baskin, Evgenii Zheltonozhskii et al.
Convolutional Neural Networks (CNNs) have become common in many fields including computer vision, speech recognition, and natural language processing. Although CNN hardware accelerators are already included as part of many SoC architectures, the task of achieving high accuracy on resource-restricted devices is still considered challenging, mainly due to the vast number of design parameters that need to be balanced to achieve an efficient solution. Quantization techniques, when applied to the network parameters, lead to a reduction of power and area and may also change the ratio between communication and computation. As a result, some algorithmic solutions may suffer from lack of memory bandwidth or computational resources and fail to achieve the expected performance due to hardware constraints. Thus, the system designer and the micro-architect need to understand at early development stages the impact of their high-level decisions (e.g., the architecture of the CNN and the amount of bits used to represent its parameters) on the final product (e.g., the expected power saving, area, and accuracy). Unfortunately, existing tools fall short of supporting such decisions. This paper introduces a hardware-aware complexity metric that aims to assist the system designer of the neural network architectures, through the entire project lifetime (especially at its early stages) by predicting the impact of architectural and micro-architectural decisions on the final product. We demonstrate how the proposed metric can help evaluate different design alternatives of neural network models on resource-restricted devices such as real-time embedded systems, and to avoid making design mistakes at early stages.
Some face recognition methods are designed to utilize geometric information extracted from depth sensors to overcome the weaknesses of single-image based recognition technologies. However, the accurate acquisition of the depth profile is an expensive and challenging process. Here, we introduce a novel method that learns to recognize faces from stereo camera systems without the need to explicitly compute the facial surface or depth map. The raw face stereo images along with the location in the image from which the face is extracted allow the proposed CNN to improve the recognition task while avoiding the need to explicitly handle the geometric structure of the face. This way, we keep the simplicity and cost efficiency of identity authentication from a single image, while enjoying the benefits of geometric data without explicitly reconstructing it. We demonstrate that the suggested method outperforms both existing single-image and explicit depth based methods on large-scale benchmarks, and even capable of recognize spoofing attacks. We also provide an ablation study that shows that the suggested method uses the face locations in the left and right images to encode informative features that improve the overall performance.
Leonid Karlinsky, Joseph Shtok, Amit Alfassy et al.
Few-shot detection and classification have advanced significantly in recent years. Yet, detection approaches require strong annotation (bounding boxes) both for pre-training and for adaptation to novel classes, and classification approaches rarely provide localization of objects in the scene. In this paper, we introduce StarNet - a few-shot model featuring an end-to-end differentiable non-parametric star-model detection and classification head. Through this head, the backbone is meta-trained using only image-level labels to produce good features for jointly localizing and classifying previously unseen categories of few-shot test tasks using a star-model that geometrically matches between the query and support images (to find corresponding object instances). Being a few-shot detector, StarNet does not require any bounding box annotations, neither during pre-training nor for novel classes adaptation. It can thus be applied to the previously unexplored and challenging task of Weakly Supervised Few-Shot Object Detection (WS-FSOD), where it attains significant improvements over the baselines. In addition, StarNet shows significant gains on few-shot classification benchmarks that are less cropped around the objects (where object localization is key).
Evgenii Zheltonozhskii, Chaim Baskin, Yaniv Nemcovsky et al.
Even though deep learning has shown unmatched performance on various tasks, neural networks have been shown to be vulnerable to small adversarial perturbations of the input that lead to significant performance degradation. In this work we extend the idea of adding white Gaussian noise to the network weights and activations during adversarial training (PNI) to the injection of colored noise for defense against common white-box and black-box attacks. We show that our approach outperforms PNI and various previous approaches in terms of adversarial accuracy on CIFAR-10 and CIFAR-100 datasets. In addition, we provide an extensive ablation study of the proposed method justifying the chosen configurations.
Neural network quantization methods often involve simulating the quantization process during training, making the trained model highly dependent on the target bit-width and precise way quantization is performed. Robust quantization offers an alternative approach with improved tolerance to different classes of data-types and quantization policies. It opens up new exciting applications where the quantization process is not static and can vary to meet different circumstances and implementations. To address this issue, we propose a method that provides intrinsic robustness to the model against a broad range of quantization processes. Our method is motivated by theoretical arguments and enables us to store a single generic model capable of operating at various bit-widths and quantization policies. We validate our method's effectiveness on different ImageNet models.
Few-Shot Learning (FSL) is a topic of rapidly growing interest. Typically, in FSL a model is trained on a dataset consisting of many small tasks (meta-tasks) and learns to adapt to novel tasks that it will encounter during test time. This is also referred to as meta-learning. Another topic closely related to meta-learning with a lot of interest in the community is Neural Architecture Search (NAS), automatically finding optimal architecture instead of engineering it manually. In this work, we combine these two aspects of meta-learning. So far, meta-learning FSL methods have focused on optimizing parameters of pre-defined network architectures, in order to make them easily adaptable to novel tasks. Moreover, it was observed that, in general, larger architectures perform better than smaller ones up to a certain saturation point (where they start to degrade due to over-fitting). However, little attention has been given to explicitly optimizing the architectures for FSL, nor to an adaptation of the architecture at test time to particular novel tasks. In this work, we propose to employ tools inspired by the Differentiable Neural Architecture Search (D-NAS) literature in order to optimize the architecture for FSL without over-fitting. Additionally, to make the architecture task adaptive, we propose the concept of `MetAdapt Controller' modules. These modules are added to the model and are meta-trained to predict the optimal network connections for a given novel task. Using the proposed approach we observe state-of-the-art results on two popular few-shot benchmarks: miniImageNet and FC100.
Deep Matrix Factorization (DMF) is an emerging approach to the problem of matrix completion. Recent works have established that gradient descent applied to a DMF model induces an implicit regularization on the rank of the recovered matrix. In this work we interpret the DMF model through the lens of spectral geometry. This allows us to incorporate explicit regularization without breaking the DMF structure, thus enjoying the best of both worlds. In particular, we focus on matrix completion problems with underlying geometric or topological relations between the rows and/or columns. Such relations are prevalent in matrix completion problems that arise in many applications, such as recommender systems and drug-target interaction. Our contributions enable DMF models to exploit these relations, and make them competitive on real benchmarks, while exhibiting one of the first successful applications of deep linear networks.
Localization of an object within an image is a common task in medical imaging. Learning to localize or detect objects typically requires the collection of data which has been labelled with bounding boxes or similar annotations, which can be very time consuming and expensive. A technique which could perform such learning with much less annotation would, therefore, be quite valuable. We present such a technique for localization with limited annotation, in which the number of images with bounding boxes can be a small fraction of the total dataset (e.g. less than 1%); all other images only possess a whole image label and no bounding box. We propose a novel loss function for tackling this problem; the loss is a continuous relaxation of a well-defined discrete formulation of weakly supervised learning and is numerically well-posed. Furthermore, we propose a new architecture which accounts for both patch dependence and shift-invariance, through the inclusion of CRF layers and anti-aliasing filters, respectively. We apply our technique to the localization of thoracic diseases in chest X-ray images and demonstrate state-of-the-art localization performance on the ChestX-ray14 dataset.
We introduce two constructions in geometric deep learning for 1) transporting orientation-dependent convolutional filters over a manifold in a continuous way and thereby defining a convolution operator that naturally incorporates the rotational effect of holonomy; and 2) allowing efficient evaluation of manifold convolution layers by sampling manifold valued random variables that center around a weighted diffusion mean. Both methods are inspired by stochastics on manifolds and geometric statistics, and provide examples of how stochastic methods -- here horizontal frame bundle flows and non-linear bridge sampling schemes, can be used in geometric deep learning. We outline the theoretical foundation of the two methods, discuss their relation to Euclidean deep networks and existing methodology in geometric deep learning, and establish important properties of the proposed constructions.
Magnetic Resonance Imaging (MRI) has long been considered to be among "the gold standards" of diagnostic medical imaging. The long acquisition times, however, render MRI prone to motion artifacts, let alone their adverse contribution to the relative high costs of MRI examination. Over the last few decades, multiple studies have focused on the development of both physical and post-processing methods for accelerated acquisition of MRI scans. These two approaches, however, have so far been addressed separately. On the other hand, recent works in optical computational imaging have demonstrated growing success of concurrent learning-based design of data acquisition and image reconstruction schemes. Such schemes have already demonstrated substantial effectiveness, leading to considerably shorter acquisition times and improved quality of image reconstruction. Inspired by this initial success, in this work, we propose a novel approach to the learning of optimal schemes for conjoint acquisition and reconstruction of MRI scans, with the optimization carried out simultaneously with respect to the time-efficiency of data acquisition and the quality of resulting reconstructions. To be of a practical value, the schemes are encoded in the form of general k-space trajectories, whose associated magnetic gradients are constrained to obey a set of predefined hardware requirements (as defined in terms of, e.g., peak currents and maximum slew rates of magnetic gradients). With this proviso in mind, we propose a novel algorithm for the end-to-end training of a combined acquisition-reconstruction pipeline using a deep neural network with differentiable forward- and back-propagation operators. We demonstrate its effectiveness on image reconstruction and image segmentation tasks, reporting substantial improvements in terms of acceleration factors as well as the quality of these tasks.