Search Results for author: Lior Wolf

Found 216 papers, 102 papers with code

Still-Moving: Customized Video Generation without Customized Video Data

no code implementations11 Jul 2024 Hila Chefer, Shiran Zada, Roni Paiss, Ariel Ephrat, Omer Tov, Michael Rubinstein, Lior Wolf, Tali Dekel, Tomer Michaeli, Inbar Mosseri

We assume access to a customized version of the T2I model, trained only on still image data (e. g., using DreamBooth or StyleDrop).

Video Generation

DeciMamba: Exploring the Length Extrapolation Potential of Mamba

1 code implementation20 Jun 2024 Assaf Ben-Kish, Itamar Zimerman, Shady Abu-Hussein, Nadav Cohen, Amir Globerson, Lior Wolf, Raja Giryes

Long-range sequence processing poses a significant challenge for Transformers due to their quadratic complexity in input length.

Knowledge Editing in Language Models via Adapted Direct Preference Optimization

no code implementations14 Jun 2024 Amit Rozner, Barak Battash, Lior Wolf, Ofir Lindenbaum

We use the current knowledge as a negative sample and the new knowledge we want to introduce as a positive sample in a process called DPO.

knowledge editing World Knowledge

LLM Questionnaire Completion for Automatic Psychiatric Assessment

no code implementations9 Jun 2024 Gony Rosenman, Lior Wolf, Talma Hendler

We employ a Large Language Model (LLM) to convert unstructured psychological interviews into structured questionnaires spanning various psychiatric and personality domains.

Language Modelling Large Language Model

Factor Graph Optimization of Error-Correcting Codes for Belief Propagation Decoding

no code implementations9 Jun 2024 Yoni Choukroun, Lior Wolf

The design of optimal linear block codes capable of being efficiently decoded is of major concern, especially for short block lengths.

A Unified Implicit Attention Formulation for Gated-Linear Recurrent Sequence Models

1 code implementation26 May 2024 Itamar Zimerman, Ameen Ali, Lior Wolf

For the other architectures for which our method is the first to provide such a view, our method is effective and competitive in the relevant metrics compared to the results obtained by state-of-the-art transformer explainability methods.

Learning Linear Block Error Correction Codes

1 code implementation7 May 2024 Yoni Choukroun, Lior Wolf

In this work, we propose for the first time a unified encoder-decoder training of binary linear block codes.

Decoder

Obtaining Favorable Layouts for Multiple Object Generation

no code implementations1 May 2024 Barak Battash, Amit Rozner, Lior Wolf, Ofir Lindenbaum

To address this challenge, we propose a novel approach based on a guiding principle.

Object

The Hidden Attention of Mamba Models

1 code implementation3 Mar 2024 Ameen Ali, Itamar Zimerman, Lior Wolf

The Mamba layer offers an efficient selective state space model (SSM) that is highly effective in modeling multiple domains, including NLP, long-range sequence processing, and computer vision.

Backward Lens: Projecting Language Model Gradients into the Vocabulary Space

no code implementations20 Feb 2024 Shahar Katz, Yonatan Belinkov, Mor Geva, Lior Wolf

Understanding how Transformer-based Language Models (LMs) learn and recall information is a key goal of the deep learning community.

Language Modelling

Training-Free Consistent Text-to-Image Generation

1 code implementation5 Feb 2024 Yoad Tewel, Omri Kaduri, Rinon Gal, Yoni Kasten, Lior Wolf, Gal Chechik, Yuval Atzmon

Text-to-image models offer a new level of creative flexibility by allowing users to guide the image generation process through natural language.

Diversity Story Visualization +1

DiffMoog: a Differentiable Modular Synthesizer for Sound Matching

1 code implementation23 Jan 2024 Noy Uzrad, Oren Barkan, Almog Elharar, Shlomi Shvartzman, Moshe Laufer, Lior Wolf, Noam Koenigstein

We introduce an open-source platform that comprises DiffMoog and an end-to-end sound matching framework.

Audio Synthesis

Dynamic Layer Tying for Parameter-Efficient Transformers

no code implementations23 Jan 2024 Tamir David Hay, Lior Wolf

In the pursuit of reducing the number of trainable parameters in deep transformer networks, we employ Reinforcement Learning to dynamically select layers during training and tie them together.

PRILoRA: Pruned and Rank-Increasing Low-Rank Adaptation

no code implementations20 Jan 2024 Nadav Benedek, Lior Wolf

With the proliferation of large pre-trained language models (PLMs), fine-tuning all model parameters becomes increasingly inefficient, particularly when dealing with numerous downstream tasks that entail substantial training and storage costs.

Degree-based stratification of nodes in Graph Neural Networks

no code implementations16 Dec 2023 Ameen Ali, Hakan Cevikalp, Lior Wolf

Here, we propose a different approach that is based on a stratification of the graph nodes.

Graph Neural Network

On the Long Range Abilities of Transformers

no code implementations28 Nov 2023 Itamar Zimerman, Lior Wolf

Despite their dominance in modern DL and, especially, NLP domains, transformer architectures exhibit sub-optimal performance on long-range tasks compared to recent layers that are specifically designed for this purpose.

Inductive Bias

Diverse and Aligned Audio-to-Video Generation via Text-to-Video Model Adaptation

1 code implementation28 Sep 2023 Guy Yariv, Itai Gat, Sagie Benaim, Lior Wolf, Idan Schwartz, Yossi Adi

The proposed method is based on a lightweight adaptor network, which learns to map the audio-based representation to the input representation expected by the text-to-video generation model.

Text-to-Video Generation Video Generation

Multi-Dimensional Hyena for Spatial Inductive Bias

no code implementations24 Sep 2023 Itamar Zimerman, Lior Wolf

Our empirical findings indicate that the proposed Hyena N-D layer boosts the performance of various Vision Transformer architectures, such as ViT, Swin, and DeiT across multiple datasets.

Inductive Bias

Box-based Refinement for Weakly Supervised and Unsupervised Localization Tasks

1 code implementation ICCV 2023 Eyal Gomel, Tal Shaharabany, Lior Wolf

It has been established that training a box-based detector network can enhance the localization performance of weakly supervised and unsupervised methods.

Object Discovery Phrase Grounding

Zero-Shot Audio Captioning via Audibility Guidance

no code implementations7 Sep 2023 Tal Shaharabany, Ariel Shaulov, Lior Wolf

Instead, captioning occurs as an inference process that involves three networks that correspond to the three desired qualities: (i) A Large Language Model, in our case, for reasons of convenience, GPT-2, (ii) A model that provides a matching score between an audio file and a text, for which we use a multimodal matching network called ImageBind, and (iii) A text classifier, trained using a dataset we collected automatically by instructing GPT-4 with prompts designed to direct the generation of both audible and inaudible sentences.

Ranked #3 on Zero-shot Audio Captioning on AudioCaps (using extra training data)

Zero-shot Audio Captioning

Reconstructing the Hemodynamic Response Function via a Bimodal Transformer

no code implementations28 Jun 2023 Yoni Choukroun, Lior Golgher, Pablo Blinder, Lior Wolf

The relationship between blood flow and neuronal activity is widely recognized, with blood flow frequently serving as a surrogate for neuronal activity in fMRI studies.

Annotator Consensus Prediction for Medical Image Segmentation with Diffusion Models

1 code implementation15 Jun 2023 Tomer Amit, Shmuel Shichrur, Tal Shaharabany, Lior Wolf

A major challenge in the segmentation of medical images is the large inter- and intra-observer variability in annotations provided by multiple experts.

Image Segmentation Medical Image Segmentation +2

2-D SSM: A General Spatial Layer for Visual Transformers

1 code implementation11 Jun 2023 Ethan Baron, Itamar Zimerman, Lior Wolf

For example, vision transformers equipped with our layer exhibit effective performance even without positional encoding

Inductive Bias Position

AutoSAM: Adapting SAM to Medical Images by Overloading the Prompt Encoder

no code implementations10 Jun 2023 Tal Shaharabany, Aviad Dahan, Raja Giryes, Lior Wolf

The recently introduced Segment Anything Model (SAM) combines a clever architecture and large quantities of training data to obtain remarkable image segmentation capabilities.

Image Segmentation Segmentation +2

Decision S4: Efficient Sequence-Based RL via State Spaces Layers

no code implementations8 Jun 2023 Shmuel Bar-David, Itamar Zimerman, Eliya Nachmani, Lior Wolf

Recently, sequence learning methods have been applied to the problem of off-policy Reinforcement Learning, including the seminal work on Decision Transformers, which employs transformers for this task.

Centered Self-Attention Layers

no code implementations2 Jun 2023 Ameen Ali, Tomer Galanti, Lior Wolf

The self-attention mechanism in transformers and the message-passing mechanism in graph neural networks are repeatedly applied within deep learning architectures.

Weakly supervised segmentation

Anomaly Detection with Variance Stabilized Density Estimation

1 code implementation1 Jun 2023 Amit Rozner, Barak Battash, Henry Li, Lior Wolf, Ofir Lindenbaum

Then, we present a variance-stabilized density estimation problem for maximizing the likelihood of the observed samples while minimizing the variance of the density around normal samples.

Anomaly Detection Density Estimation

The Hidden Language of Diffusion Models

1 code implementation1 Jun 2023 Hila Chefer, Oran Lang, Mor Geva, Volodymyr Polosukhin, Assaf Shocher, Michal Irani, Inbar Mosseri, Lior Wolf

In this work, we present Conceptor, a novel method to interpret the internal representation of a textual concept by a diffusion model.

Bias Detection Image Manipulation

Focus Your Attention (with Adaptive IIR Filters)

no code implementations24 May 2023 Shahar Lutati, Itamar Zimerman, Lior Wolf

We present a new layer in which dynamic (i. e., input-dependent) Infinite Impulse Response (IIR) filters of order two are used to process the input sequence prior to applying conventional attention.

Long-range modeling

AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation

2 code implementations Interspeech 2023 Guy Yariv, Itai Gat, Lior Wolf, Yossi Adi, Idan Schwartz

In this paper, we propose a novel method utilizing latent diffusion models trained for text-to-image-generation to generate images conditioned on audio recordings.

audio-visual learning Text-to-Image Generation

Discriminative Class Tokens for Text-to-Image Diffusion Models

1 code implementation ICCV 2023 Idan Schwartz, Vésteinn Snæbjarnarson, Hila Chefer, Ryan Cotterell, Serge Belongie, Lior Wolf, Sagie Benaim

This approach has two disadvantages: (i) supervised datasets are generally small compared to large-scale scraped text-image datasets on which text-to-image models are trained, affecting the quality and diversity of the generated images, or (ii) the input is a hard-coded label, as opposed to free-form text, limiting the control over the generated images.

Improved Tree Search for Automatic Program Synthesis

no code implementations13 Mar 2023 Aran Carmon, Lior Wolf

In the task of automatic program synthesis, one obtains pairs of matching inputs and outputs and generates a computer program, in a particular domain-specific language (DSL), which given each sample input returns the matching output.

Program Synthesis valid

Energy Regularized RNNs for Solving Non-Stationary Bandit Problems

no code implementations12 Mar 2023 Michael Rotman, Lior Wolf

We consider a Multi-Armed Bandit problem in which the rewards are non-stationary and are dependent on past actions and potentially on past contexts.

Gradient Adjusting Networks for Domain Inversion

1 code implementation22 Feb 2023 Erez Sheffi, Michael Rotman, Lior Wolf

However, in order to manipulate a real-world image, one first needs to be able to retrieve its corresponding latent representation in StyleGAN's latent space that is decoded to an image as close as possible to the desired image.

Image Generation

Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models

2 code implementations31 Jan 2023 Hila Chefer, Yuval Alaluf, Yael Vinker, Lior Wolf, Daniel Cohen-Or

Recent text-to-image generative models have demonstrated an unparalleled ability to generate diverse and creative imagery guided by a target text prompt.

Generative Semantic Nursing

Domain-Generalizable Multiple-Domain Clustering

1 code implementation31 Jan 2023 Amit Rozner, Barak Battash, Lior Wolf, Ofir Lindenbaum

This work generalizes the problem of unsupervised domain generalization to the case in which no labeled samples are available (completely unsupervised).

Clustering Domain Generalization

Deep Quantum Error Correction

no code implementations27 Jan 2023 Yoni Choukroun, Lior Wolf

Quantum error correction codes (QECC) are a key component for realizing the potential of quantum computing.

Separate And Diffuse: Using a Pretrained Diffusion Model for Improving Source Separation

no code implementations25 Jan 2023 Shahar Lutati, Eliya Nachmani, Lior Wolf

Applying a diffusion model Vocoder that was pretrained to model single-speaker voices on the output of a deterministic separation model leads to state-of-the-art separation results.

Audio Source Separation Generalization Bounds +2

Similarity Maps for Self-Training Weakly-Supervised Phrase Grounding

1 code implementation CVPR 2023 Tal Shaharabany, Lior Wolf

A phrase grounding model receives an input image and a text phrase and outputs a suitable localization map.

Phrase Grounding

Generating 2D and 3D Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution

no code implementations25 Nov 2022 Tomer Friedlander, Ron Shmelkin, Lior Wolf

The results we present demonstrate that it is possible to obtain a considerable coverage of the identities in the LFW or RFW datasets with less than 10 master faces, for six leading deep face recognition systems.

3D Face Reconstruction Face Recognition +1

Describing Sets of Images with Textual-PCA

1 code implementation21 Oct 2022 Oded Hupert, Idan Schwartz, Lior Wolf

We seek to semantically describe a set of images, capturing both the attributes of single images and the variations within the set.

Semantic Similarity Semantic Textual Similarity

OCD: Learning to Overfit with Conditional Diffusion Models

1 code implementation2 Oct 2022 Shahar Lutati, Lior Wolf

We present a dynamic model in which the weights are conditioned on an input sample x and are learned to match those that would be obtained by finetuning a base model on x and its label y.

3D Reconstruction Denoising +3

Denoising Diffusion Error Correction Codes

no code implementations16 Sep 2022 Yoni Choukroun, Lior Wolf

Error correction code (ECC) is an integral part of the physical communication layer, ensuring reliable data transfer over noisy channels.

Decoder Denoising

Semi-supervised Learning of Partial Differential Operators and Dynamical Flows

no code implementations28 Jul 2022 Michael Rotman, Amit Dekel, Ran Ilan Ber, Lior Wolf, Yaron Oz

As a result, it successfully propagates initial conditions in continuous time steps by employing the general composition properties of the partial differential operators.

Zero-Shot Video Captioning with Evolving Pseudo-Tokens

1 code implementation22 Jul 2022 Yoad Tewel, Yoav Shalev, Roy Nadler, Idan Schwartz, Lior Wolf

We introduce a zero-shot video captioning method that employs two frozen networks: the GPT-2 language model and the CLIP image-text matching model.

Image Captioning Image-text matching +6

FewGAN: Generating from the Joint Distribution of a Few Images

no code implementations18 Jul 2022 Lior Ben-Moshe, Sagie Benaim, Lior Wolf

We then use a separate set of side images to model the structure of generated images using an autoregressive model trained on the learned patch embeddings of training images.

Quantization

Zero-Shot Voice Conditioning for Denoising Diffusion TTS Models

no code implementations5 Jun 2022 Alon Levkovitch, Eliya Nachmani, Lior Wolf

At the heart of the method lies a sampling process that combines the estimation of the denoising model with a low-pass version of the new speaker's sample.

Denoising

Optimizing Relevance Maps of Vision Transformers Improves Robustness

1 code implementation2 Jun 2022 Hila Chefer, Idan Schwartz, Lior Wolf

It has been observed that visual classification models often rely mostly on the image background, neglecting the foreground, which hurts their robustness to distribution changes.

Image Classification Out-of-Distribution Generalization

SepIt: Approaching a Single Channel Speech Separation Bound

no code implementations24 May 2022 Shahar Lutati, Eliya Nachmani, Lior Wolf

We present an upper bound for the Single Channel Speech Separation task, which is based on an assumption regarding the nature of short segments of speech.

Audio Source Separation Generalization Bounds +2

Neural Inverse Kinematics

1 code implementation22 May 2022 Raphael Bensadoun, Shir Gur, Nitsan Blau, Tom Shenkar, Lior Wolf

In this work, we propose a neural IK method that employs the hierarchical structure of the problem to sequentially sample valid joint angles conditioned on the desired position and on the preceding joints along the chain.

Position valid

On Disentangled and Locally Fair Representations

no code implementations5 May 2022 Yaron Gurovich, Sagie Benaim, Lior Wolf

This problem is tackled through the lens of disentangled and locally fair representations.

Attribute Fairness

No Token Left Behind: Explainability-Aided Image Classification and Generation

1 code implementation11 Apr 2022 Roni Paiss, Hila Chefer, Lior Wolf

To mitigate it, we present a novel explainability-based approach, which adds a loss term to ensure that CLIP focuses on all relevant semantic parts of the input, in addition to employing the CLIP similarity loss used in previous works.

Image Classification Image Generation +4

End to End Lip Synchronization with a Temporal AutoEncoder

1 code implementation30 Mar 2022 Yoav Shalev, Lior Wolf

We study the problem of syncing the lip movement in a video with the audio stream.

Error Correction Code Transformer

1 code implementation27 Mar 2022 Yoni Choukroun, Lior Wolf

Error correction code is a major part of the communication physical layer, ensuring the reliable transfer of data over noisy channels.

Inductive Bias

Dynamically-Scaled Deep Canonical Correlation Analysis

1 code implementation23 Mar 2022 Tomer Friedlander, Lior Wolf

Canonical Correlation Analysis (CCA) is a method for feature extraction of two views by finding maximally correlated linear projections of them.

Retrieval

Dynamic Dual-Output Diffusion Models

no code implementations CVPR 2022 Yaniv Benny, Lior Wolf

In this paper, we reveal some of the causes that affect the generation quality of diffusion models, especially when sampling with few iterations, and come up with a simple, yet effective, solution to mitigate them.

Denoising Image Generation

fMRI Neurofeedback Learning Patterns are Predictive of Personal and Clinical Traits

1 code implementation21 Dec 2021 Rotem Leibovitz, Jhonathan Osin, Lior Wolf, Guy Gurevitch, Talma Hendler

We obtain a personal signature of a person's learning progress in a self-neuromodulation task, guided by functional MRI (fMRI).

Self-Supervised Transformers for fMRI representation

2 code implementations10 Dec 2021 Itzik Malkiel, Gony Rosenman, Lior Wolf, Talma Hendler

We present TFF, which is a Transformer framework for the analysis of functional Magnetic Resonance Imaging (fMRI) data.

Gender Prediction

Locally Shifted Attention With Early Global Integration

1 code implementation9 Dec 2021 Shelly Sheynin, Sagie Benaim, Adam Polyak, Lior Wolf

The separation of the attention layer into local and global counterparts allows for a low computational cost in the number of patches, while still supporting data-dependent localization already at the first layer, as opposed to the static positioning in other visual transformers.

Image Classification

Learning Personal Representations from fMRIby Predicting Neurofeedback Performance

no code implementations6 Dec 2021 Jhonathan Osin, Lior Wolf, Guy Gurevitch, Jackob Nimrod Keynan, Tom Fruchtman-Steinbok, Ayelet Or-Borichev, Shira Reznik Balter, Talma Hendler

We present a deep neural network method for learning a personal representation for individuals that are performing a self neuromodulation task, guided by functional MRI (fMRI).

End-to-End Segmentation via Patch-wise Polygons Prediction

no code implementations5 Dec 2021 Tal Shaharabany, Lior Wolf

The leading segmentation methods represent the output map as a pixel grid.

Segmentation

Learning Query Expansion over the Nearest Neighbor Graph

no code implementations5 Dec 2021 Benjamin Klein, Lior Wolf

In this work, a hierarchical model, Graph Query Expansion (GQE), is presented, which is learned in a supervised manner and performs aggregation over an extended neighborhood of the query, thus increasing the information used from the database when computing the query expansion, and using the structure of the nearest neighbors graph.

Image Retrieval Retrieval

SegDiff: Image Segmentation with Diffusion Probabilistic Models

1 code implementation1 Dec 2021 Tomer Amit, Tal Shaharbany, Eliya Nachmani, Lior Wolf

Since the diffusion model is probabilistic, it is applied multiple times, and the results are merged into a final segmentation map.

Decoder Image Generation +3

ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic

1 code implementation CVPR 2022 Yoad Tewel, Yoav Shalev, Idan Schwartz, Lior Wolf

While such models can provide a powerful score for matching and subsequent zero-shot tasks, they are not capable of generating caption given an image.

Contrastive Learning Descriptive +6

Learning a Weight Map for Weakly-Supervised Localization

no code implementations28 Nov 2021 Tal Shaharabany, Lior Wolf

In the weakly supervised localization setting, supervision is given as an image-level label.

Weakly supervised segmentation

A-Muze-Net: Music Generation by Composing the Harmony based on the Generated Melody

no code implementations25 Nov 2021 Or Goren, Eliya Nachmani, Lior Wolf

The Midi is represented in a way that is invariant to the musical scale, and the melody is represented, for the purpose of conditioning the harmony, by the content of each bar, viewed as a chord.

Music Generation

Geometric Transformer for End-to-End Molecule Properties Prediction

1 code implementation26 Oct 2021 Yoni Choukroun, Lior Wolf

Transformers have become methods of choice in many applications thanks to their ability to represent complex interactions between elements.

Property Prediction

Image-Based CLIP-Guided Essence Transfer

1 code implementation24 Oct 2021 Hila Chefer, Sagie Benaim, Roni Paiss, Lior Wolf

We make the distinction between (i) style transfer, in which a source image is manipulated to match the textures and colors of a target image, and (ii) essence transfer, in which one edits the source image to include high-level semantic attributes from the target.

Domain Adaptation Style Transfer

Video and Text Matching with Conditioned Embeddings

1 code implementation21 Oct 2021 Ameen Ali, Idan Schwartz, Tamir Hazan, Lior Wolf

Traditionally video and text matching is done by learning a shared embedding space and the encoding of one modality is independent of the other.

Machine Translation Sentence +4

Denoising Diffusion Gamma Models

no code implementations10 Oct 2021 Eliya Nachmani, Robin San Roman, Lior Wolf

Generative diffusion processes are an emerging and effective tool for image and speech generation.

Denoising

Meta Internal Learning

1 code implementation NeurIPS 2021 Raphael Bensadoun, Shir Gur, Tomer Galanti, Lior Wolf

Internal learning for single-image generation is a framework, where a generator is trained to produce novel images based on a single image.

Image Generation Meta-Learning +1

Local-Global Shifting Vision Transformers

no code implementations29 Sep 2021 Shelly Sheynin, Sagie Benaim, Adam Polyak, Lior Wolf

Due to the expensive quadratic cost of the attention mechanism, either a large patch size is used, resulting in coarse-grained global interactions, or alternatively, attention is applied only on a local region of the image at the expense of long-range interactions.

Image Classification

Anomaly Detection for Tabular Data with Internal Contrastive Learning

1 code implementation ICLR 2022 Tom Shenkar, Lior Wolf

We consider the task of finding out-of-class samples in tabular data, where little can be assumed on the structure of the data.

Anomaly Detection Contrastive Learning

Caption Enriched Samples for Improving Hateful Memes Detection

1 code implementation EMNLP 2021 Efrat Blaier, Itzik Malkiel, Lior Wolf

The recently introduced hateful meme challenge demonstrates the difficulty of determining whether a meme is hateful or not.

Image Captioning

Mixing between the Cross Entropy and the Expectation Loss Terms

no code implementations12 Sep 2021 Barak Battash, Lior Wolf, Tamir Hazan

The cross entropy loss is widely used due to its effectiveness and solid theoretical grounding.

Generating Master Faces for Dictionary Attacks with a Network-Assisted Latent Space Evolution

no code implementations1 Aug 2021 Ron Shmelkin, Tomer Friedlander, Lior Wolf

A master face is a face image that passes face-based identity-authentication for a large portion of the population.

Face Recognition

In Defense of the Learning Without Forgetting for Task Incremental Learning

no code implementations26 Jul 2021 Guy Oren, Lior Wolf

Catastrophic forgetting is one of the major challenges on the road for continual learning systems, which are presented with an on-line stream of tasks.

Continual Learning Incremental Learning +1

Non Gaussian Denoising Diffusion Models

1 code implementation14 Jun 2021 Eliya Nachmani, Robin San Roman, Lior Wolf

Moreover, we show that using a mixture of Gaussian noise variables in the diffusion process improves the performance over a diffusion process that is based on a single distribution.

Denoising

Recovering AES Keys with a Deep Cold Boot Attack

no code implementations9 Jun 2021 Itamar Zimerman, Eliya Nachmani, Lior Wolf

In this work, we combine a novel cryptographic variant of a deep error correcting code technique with a modified SAT solver scheme to apply the attack on AES keys.

Cryptanalysis Scheduling

Identity and Attribute Preserving Thumbnail Upscaling

no code implementations30 May 2021 Noam Gat, Sagie Benaim, Lior Wolf

We consider the task of upscaling a low resolution thumbnail image of a person, to a higher resolution image, which preserves the person's identity and other attributes.

Attribute

HyperHyperNetworks for the Design of Antenna Arrays

1 code implementation9 May 2021 Shahar Lutati, Lior Wolf

Our experiments demonstrate that our approach is able to design novel antennas and antenna arrays that are compliant with the design requirements, considerably better than the baseline methods.

A Hierarchical Transformation-Discriminating Generative Model for Few Shot Anomaly Detection

2 code implementations ICCV 2021 Shelly Sheynin, Sagie Benaim, Lior Wolf

We demonstrate the superiority of our method on both the one-shot and few-shot settings, on the datasets of Paris, CIFAR10, MNIST and FashionMNIST as well as in the setting of defect detection on MVTec.

Anomaly Detection Defect Detection

Noise Estimation for Generative Diffusion Models

no code implementations6 Apr 2021 Robin San-Roman, Eliya Nachmani, Lior Wolf

Generative diffusion models have emerged as leading models in speech and image generation.

Denoising Image Generation +1

Adaptive Gradient Balancing for UndersampledMRI Reconstruction and Image-to-Image Translation

1 code implementation5 Apr 2021 Itzik Malkiel, Sangtae Ahn, Valentina Taviani, Anne Menini, Lior Wolf, Christopher J. Hardy

Recent accelerated MRI reconstruction models have used Deep Neural Networks (DNNs) to reconstruct relatively high-quality images from highly undersampled k-space data, enabling much faster MRI scanning.

Generative Adversarial Network Image-to-Image Translation +2

Maximal Multiverse Learning for Promoting Cross-Task Generalization of Fine-Tuned Language Models

no code implementations EACL 2021 Itzik Malkiel, Lior Wolf

Language modeling with BERT consists of two phases of (i) unsupervised pre-training on unlabeled text, and (ii) fine-tuning for a specific supervised task.

Language Modelling Unsupervised Pre-training

Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers

1 code implementation ICCV 2021 Hila Chefer, Shir Gur, Lior Wolf

Transformers are increasingly dominating multi-modal reasoning tasks, such as visual question answering, achieving state-of-the-art results thanks to their ability to contextualize information using the self-attention and co-attention mechanisms.

Decoder Image Segmentation +5

Weakly Supervised Recovery of Semantic Attributes

no code implementations22 Mar 2021 Ameen Ali, Tomer Galanti, Evgeniy Zheltonozhskiy, Chaim Baskin, Lior Wolf

We consider the problem of the extraction of semantic attributes, supervised only with classification labels.

High Fidelity Speech Regeneration with Application to Speech Enhancement

no code implementations31 Jan 2021 Adam Polyak, Lior Wolf, Yossi Adi, Ori Kabeli, Yaniv Taigman

Speech enhancement has seen great improvement in recent years mainly through contributions in denoising, speaker separation, and dereverberation methods that mostly deal with environmental effects on vocal audio.

Denoising Speaker Separation +3

Autoregressive Belief Propagation for Decoding Block Codes

no code implementations23 Jan 2021 Eliya Nachmani, Lior Wolf

We revisit recent methods that employ graph neural networks for decoding error correcting codes and employ messages that are computed in an autoregressive manner.

Fidelity-based Deep Adiabatic Scheduling

no code implementations ICLR 2021 Eli Ovits, Lior Wolf

Adiabatic quantum computation is a form of computation that acts by slowly interpolating a quantum system between an easy to prepare initial state and a final state that represents a solution to a given computational problem.

Scheduling

Image Animation with Refined Masking

no code implementations1 Jan 2021 Yoav Shalev, Lior Wolf

Conditioned on the source image, the transformed mask is then decoded by a multi-scale generator that renders a realistic image, in which the content of the source frame is animated by the pose in the driving video.

Image Animation

Solving Non-Stationary Bandit Problems with an RNN and an Energy Minimization Loss

no code implementations1 Jan 2021 Michael Rotman, Lior Wolf

We consider a Multi-Armed Bandit problem in which the rewards are non-stationary and are dependent on past actions and potentially on past contexts.

HyperSeg: Patch-wise Hypernetwork for Real-time Semantic Segmentation

1 code implementation CVPR 2021 Yuval Nirkin, Lior Wolf, Tal Hassner

We present a novel, real-time, semantic segmentation network in which the encoder both encodes and generates the parameters (weights) of the decoder.

Decoder Dichotomous Image Segmentation +2

Transformer Interpretability Beyond Attention Visualization

3 code implementations CVPR 2021 Hila Chefer, Shir Gur, Lior Wolf

Self-attention techniques, and specifically Transformers, are dominating the field of text processing and are becoming increasingly popular in computer vision classification tasks.

General Classification text-classification +1

Visualization of Supervised and Self-Supervised Neural Networks via Attribution Guided Factorization

1 code implementation3 Dec 2020 Shir Gur, Ameen Ali, Lior Wolf

However, as we show, these methods are limited in their ability to identify the support for alternative classifications, an effect we name {\em the saliency bias} hypothesis.

Single-Shot Freestyle Dance Reenactment

no code implementations CVPR 2021 Oran Gafni, Oron Ashual, Lior Wolf

The task of motion transfer between a source dancer and a target person is a special case of the pose transfer problem, in which the target person changes their pose in accordance with the motions of the dancer.

Pose Transfer

Image Animation with Perturbed Masks

2 code implementations CVPR 2022 Yoav Shalev, Lior Wolf

We present a novel approach for image-animation of a source image by a driving video, both depicting the same type of object.

Image Animation

Single channel voice separation for unknown number of speakers under reverberant and noisy settings

2 code implementations4 Nov 2020 Shlomo E. Chazan, Lior Wolf, Eliya Nachmani, Yossi Adi

The proposed approach is composed of several separation heads optimized together with a speaker classification branch.

Classification General Classification

Generating Correct Answers for Progressive Matrices Intelligence Tests

no code implementations NeurIPS 2020 Niv Pekar, Yaniv Benny, Lior Wolf

Raven's Progressive Matrices are multiple-choice intelligence tests, where one tries to complete the missing location in a $3\times 3$ grid of abstract images.

Multiple-choice

Scene Graph to Image Generation with Contextualized Object Layout Refinement

no code implementations23 Sep 2020 Maor Ivgi, Yaniv Benny, Avichai Ben-David, Jonathan Berant, Lior Wolf

We empirically show on the COCO-STUFF dataset that our approach improves the quality of both the intermediate layout and the final image.

Image Generation Object

Scale-Localized Abstract Reasoning

2 code implementations CVPR 2021 Yaniv Benny, Niv Pekar, Lior Wolf

First, it searches for relational patterns in multiple resolutions, which allows it to readily detect visual relations, such as location, in higher resolution, while allowing the lower resolution module to focus on semantic relations, such as shape type.

Relational Reasoning

Hierarchical Timbre-Painting and Articulation Generation

1 code implementation30 Aug 2020 Michael Michelashvili, Lior Wolf

We present a fast and high-fidelity method for music generation, based on specified f0 and loudness, such that the synthesized audio mimics the timbre and articulation of a target instrument.

Music Generation

DeepFake Detection Based on the Discrepancy Between the Face and its Context

no code implementations27 Aug 2020 Yuval Nirkin, Lior Wolf, Yosi Keller, Tal Hassner

Our approach involves two networks: (i) a face identification network that considers the face region bounded by a tight semantic segmentation, and (ii) a context recognition network that considers the face context (e. g., hair, ears, neck).

DeepFake Detection Face Identification +2

Shuffling Recurrent Neural Networks

1 code implementation14 Jul 2020 Michael Rotman, Lior Wolf

We propose a novel recurrent neural network model, where the hidden state $h_t$ is obtained by permuting the vector elements of the previous hidden state $h_{t-1}$ and adding the output of a learned function $b(x_t)$ of the input $x_t$ at time $t$.

Data Augmenting Contrastive Learning of Speech Representations in the Time Domain

1 code implementation2 Jul 2020 Eugene Kharitonov, Morgane Rivière, Gabriel Synnaeve, Lior Wolf, Pierre-Emmanuel Mazaré, Matthijs Douze, Emmanuel Dupoux

Contrastive Predictive Coding (CPC), based on predicting future segments of speech based on past segments is emerging as a powerful algorithm for representation learning of speech signal.

Contrastive Learning Data Augmentation +1

MTAdam: Automatic Balancing of Multiple Training Loss Terms

1 code implementation EMNLP 2021 Itzik Malkiel, Lior Wolf

When training neural models, it is common to combine multiple loss terms.

A Novel Approach for Correcting Multiple Discrete Rigid In-Plane Motions Artefacts in MRI Scans

no code implementations24 Jun 2020 Michael Rotman, Rafi Brada, Israel Beniaminy, Sangtae Ahn, Christopher J. Hardy, Lior Wolf

Motion artefacts created by patient motion during an MRI scan occur frequently in practice, often rendering the scans clinically unusable and requiring a re-scan.

Wish You Were Here: Context-Aware Human Generation

no code implementations CVPR 2020 Oran Gafni, Lior Wolf

We present a novel method for inserting objects, specifically humans, into existing images, such that they blend in a photorealistic manner, while respecting the semantic context of the scene.

Pose Transfer

Masked Based Unsupervised Content Transfer

1 code implementation ICLR 2020 Ron Mokady, Sagie Benaim, Lior Wolf, Amit Bermano

We consider the problem of translating, in an unsupervised manner, between two domains where one contains some additional information compared to the other.

Translation Weakly supervised Semantic Segmentation +1

Evaluation Metrics for Conditional Image Generation

no code implementations26 Apr 2020 Yaniv Benny, Tomer Galanti, Sagie Benaim, Lior Wolf

We present two new metrics for evaluating generative models in the class-conditional image generation setting.

Conditional Image Generation

Structural-analogy from a Single Image Pair

1 code implementation5 Apr 2020 Sagie Benaim, Ron Mokady, Amit Bermano, Daniel Cohen-Or, Lior Wolf

In this paper, we explore the capabilities of neural networks to understand image structure given only a single pair of images, A and B.

Translation Unsupervised Image-To-Image Translation

On Infinite-Width Hypernetworks

1 code implementation NeurIPS 2020 Etai Littwin, Tomer Galanti, Lior Wolf, Greg Yang

{\em Hypernetworks} are architectures that produce the weights of a task-specific {\em primary network}.

Meta-Learning

Voice Separation with an Unknown Number of Multiple Speakers

4 code implementations ICML 2020 Eliya Nachmani, Yossi Adi, Lior Wolf

We present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously.

Speech Separation

ScopeFlow: Dynamic Scene Scoping for Optical Flow

1 code implementation CVPR 2020 Aviram Bar-Haim, Lior Wolf

We propose to modify the common training protocols of optical flow, leading to sizable accuracy improvements without adding to the computational complexity of the training process.

Optical Flow Estimation

A Critical View of the Structural Causal Model

no code implementations23 Feb 2020 Tomer Galanti, Ofir Nabati, Lior Wolf

In the multivariate case, where one can ensure that the complexities of the cause and effect are balanced, we propose a new adversarial training method that mimics the disentangled structure of the causal model.

On the Modularity of Hypernetworks

1 code implementation NeurIPS 2020 Tomer Galanti, Lior Wolf

Besides, we show that for a structured target function, the overall number of trainable parameters in a hypernetwork is smaller by orders of magnitude than the number of trainable parameters of a standard neural network and an embedding method.

Molecule Property Prediction and Classification with Graph Hypernetworks

1 code implementation1 Feb 2020 Eliya Nachmani, Lior Wolf

In this work, we demonstrate that the replacement of the underlying networks with hypernetworks leads to a boost in performance, obtaining state of the art results in various benchmarks.

Classification General Classification +1

On Random Kernels of Residual Architectures

no code implementations28 Jan 2020 Etai Littwin, Tomer Galanti, Lior Wolf

We derive finite width and depth corrections for the Neural Tangent Kernel (NTK) of ResNets and DenseNets.

A Formal Approach to Explainability

no code implementations15 Jan 2020 Lior Wolf, Tomer Galanti, Tamir Hazan

We regard explanations as a blending of the input sample and the model's output and offer a few definitions that capture various desired properties of the function that generates these explanations.

Structured GANs

no code implementations15 Jan 2020 Irad Peleg, Lior Wolf

We present Generative Adversarial Networks (GANs), in which the symmetric property of the generated images is controlled.

Image Generation

A Sample Selection Approach for Universal Domain Adaptation

no code implementations14 Jan 2020 Omri Lifshitz, Lior Wolf

We study the problem of unsupervised domain adaption in the universal scenario, in which only some of the classes are shared between the source and target domains.

Diversity Pseudo Label +1

Emerging Disentanglement in Auto-Encoder Based Unsupervised Image Content Transfer

1 code implementation ICLR 2019 Ori Press, Tomer Galanti, Sagie Benaim, Lior Wolf

Thus, in the above example, we can create, for every person without glasses a version with the glasses observed in any face image.

Decoder Disentanglement

Microvascular Dynamics from 4D Microscopy Using Temporal Segmentation

no code implementations14 Jan 2020 Shir Gur, Lior Wolf, Lior Golgher, Pablo Blinder

Recently developed methods for rapid continuous volumetric two-photon microscopy facilitate the observation of neuronal activity in hundreds of individual neurons and changes in blood flow in adjacent blood vessels across a large volume of living brain at unprecedented spatio-temporal resolution.

Unsupervised Learning of the Set of Local Maxima

no code implementations ICLR 2019 Lior Wolf, Sagie Benaim, Tomer Galanti

Two functions are learned: (i) a set indicator c, which is a binary classifier, and (ii) a comparator function h that given two nearby samples, predicts which sample has the higher value of the unknown function v. Loss terms are used to ensure that all training samples x are a local maxima of v, according to h and satisfy c(x)=1.

General Classification One-Class Classification

Single Image Depth Estimation Trained via Depth from Defocus Cues

1 code implementation CVPR 2019 Shir Gur, Lior Wolf

We evaluate our method on data derived from five common datasets for depth estimation and lightfield images, and present results that are on par with supervised methods on KITTI and Make3D datasets and outperform unsupervised learning approaches.

Lightfield Monocular Depth Estimation

On the Convex Behavior of Deep Neural Networks in Relation to the Layers' Width

no code implementations ICML Workshop Deep_Phenomen 2019 Etai Littwin, Lior Wolf

The Hessian of neural networks can be decomposed into a sum of two matrices: (i) the positive semidefinite generalized Gauss-Newton matrix G, and (ii) the matrix H containing negative eigenvalues.

Relation

OneGAN: Simultaneous Unsupervised Learning of Conditional Image Generation, Foreground Segmentation, and Fine-Grained Clustering

no code implementations ECCV 2020 Yaniv Benny, Lior Wolf

We present a method for simultaneously learning, in an unsupervised manner, (i) a conditional image generator, (ii) foreground extraction and segmentation, (iii) clustering into a two-level class hierarchy, and (iv) object removal and background completion, all done without any use of annotation.

Clustering Conditional Image Generation +2

Supervised and Unsupervised Learning of Parameterized Color Enhancement

no code implementations30 Dec 2019 Yoav Chai, Raja Giryes, Lior Wolf

We treat the problem of color enhancement as an image translation task, which we tackle using both supervised and unsupervised learning.

Image Enhancement Translation

Meta Decision Trees for Explainable Recommendation Systems

no code implementations19 Dec 2019 Eyal Shulman, Lior Wolf

We build the trees by applying learned regression functions to obtain the decision rules as well as the values at the leaf nodes.

Attribute Collaborative Filtering +3

Spectra2pix: Generating Nanostructure Images from Spectra

no code implementations26 Nov 2019 Itzik Malkiel, Michael Mrejen, Lior Wolf, Haim Suchowski

Our model architecture is not limited to a closed set of nanostructure shapes, and can be trained for the design of any geometry.

Computational Ceramicology

no code implementations22 Nov 2019 Barak Itkin, Lior Wolf, Nachum Dershowitz

One method relies on the shape of the fracture outline of a sherd; the other is based on decorative features.

Data Augmentation

Live Face De-Identification in Video

no code implementations ICCV 2019 Oran Gafni, Lior Wolf, Yaniv Taigman

We propose a method for face de-identification that enables fully automatic video modification at high frame rates.

Decoder De-identification

Electric Analog Circuit Design with Hypernetworks and a Differential Simulator

no code implementations8 Nov 2019 Michael Rotman, Lior Wolf

A two-stage network is used, which first generates a chain of circuit components and then predicts their parameters.

A Gated Hypernet Decoder for Polar Codes

no code implementations8 Nov 2019 Eliya Nachmani, Lior Wolf

Hypernetworks were recently shown to improve the performance of message passing algorithms for decoding error correcting codes.

Decoder

MML: Maximal Multiverse Learning for Robust Fine-Tuning of Language Models

1 code implementation5 Nov 2019 Itzik Malkiel, Lior Wolf

In this work, we present a method that leverages BERT's fine-tuning phase to its fullest, by applying an extensive number of parallel classifier heads, which are enforced to be orthogonal, while adaptively eliminating the weaker heads during training.

Unsupervised Pre-training

Adaptive and Iteratively Improving Recurrent Lateral Connections

1 code implementation16 Oct 2019 Barak Battash, Lior Wolf

The current leading computer vision models are typically feed forward neural models, in which the output of one computational block is passed to the next one sequentially.

Action Recognition

Variable Complexity in the Univariate and Multivariate Structural Causal Model

no code implementations25 Sep 2019 Tomer Galanti, Ofir Nabati, Lior Wolf

Comparing the reconstruction errors of the two autoencoders, one for each variable, is shown to perform well on the accepted benchmarks of the field.

The Effect of Residual Architecture on the Per-Layer Gradient of Deep Networks

no code implementations25 Sep 2019 Etai Littwin, Lior Wolf

A critical part of the training process of neural networks takes place in the very first gradient steps post initialization.

Fast Search with Poor OCR

no code implementations17 Sep 2019 Taivanbat Badamdorj, Adiel Ben-Shalom, Nachum Dershowitz, Lior Wolf

The indexing and searching of historical documents have garnered attention in recent years due to massive digitization efforts of important collections worldwide.

Optical Character Recognition Optical Character Recognition (OCR)

Hyper-Graph-Network Decoders for Block Codes

1 code implementation NeurIPS 2019 Eliya Nachmani, Lior Wolf

Neural decoders were shown to outperform classical message passing techniques for short BCH codes.

Bidirectional One-Shot Unsupervised Domain Mapping

1 code implementation ICCV 2019 Tomer Cohen, Lior Wolf

We study the problem of mapping between a domain $A$, in which there is a single training sample and a domain $B$, for which we have a richer training set.

Decoder

Domain Intersection and Domain Difference

1 code implementation ICCV 2019 Sagie Benaim, Michael Khaitov, Tomer Galanti, Lior Wolf

We present a method for recovering the shared content between two visual domains as well as the content that is unique to each domain.

Deep Meta Functionals for Shape Representation

1 code implementation ICCV 2019 Gidi Littwin, Lior Wolf

We present a new method for 3D shape reconstruction from a single image, in which a deep neural network directly maps an image to a vector of network weights.

3D Shape Reconstruction

Mask Based Unsupervised Content Transfer

1 code implementation15 Jun 2019 Ron Mokady, Sagie Benaim, Lior Wolf, Amit Bermano

We consider the problem of translating, in an unsupervised manner, between two domains where one contains some additional information compared to the other.

Translation Weakly supervised Semantic Segmentation +1

Conditional WGANs with Adaptive Gradient Balancing for Sparse MRI Reconstruction

no code implementations2 May 2019 Itzik Malkiel, Sangtae Ahn, Valentina Taviani, Anne Menini, Lior Wolf, Christopher J. Hardy

Recent sparse MRI reconstruction models have used Deep Neural Networks (DNNs) to reconstruct relatively high-quality images from highly undersampled k-space data, enabling much faster MRI scanning.

Generative Adversarial Network MRI Reconstruction

Autoencoder-based Music Translation

no code implementations ICLR 2019 Noam Mor, Lior Wolf, Adam Polyak, Yaniv Taigman

We present a method for translating music across musical instruments and styles.

Translation

TTS Skins: Speaker Conversion via ASR

no code implementations18 Apr 2019 Adam Polyak, Lior Wolf, Yaniv Taigman

We present a fully convolutional wav-to-wav network for converting between speakers' voices, without relying on text.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Vid2Game: Controllable Characters Extracted from Real-World Videos

no code implementations ICLR 2020 Oran Gafni, Lior Wolf, Yaniv Taigman

The second network maps the current pose, the new pose, and a given background, to an output frame.

Speech Denoising by Accumulating Per-Frequency Modeling Fluctuations

1 code implementation16 Apr 2019 Michael Michelashvili, Lior Wolf

The method is completely unsupervised and only trains on the specific audio clip that is being denoised.

Audio Denoising Speech Denoising

Unsupervised Singing Voice Conversion

no code implementations13 Apr 2019 Eliya Nachmani, Lior Wolf

The proposed network is not conditioned on the text or on the notes, and it directly converts the audio of one singer to the voice of another.

Data Augmentation Decoder +1

Relative Attributing Propagation: Interpreting the Comparative Contributions of Individual Units in Deep Neural Networks

1 code implementation1 Apr 2019 Woo-Jeoung Nam, Shir Gur, Jaesik Choi, Lior Wolf, Seong-Whan Lee

As Deep Neural Networks (DNNs) have demonstrated superhuman performance in a variety of fields, there is an increasing interest in understanding the complex internal mechanisms of DNNs.

Unsupervised Polyglot Text To Speech

no code implementations6 Feb 2019 Eliya Nachmani, Lior Wolf

We present a TTS neural network that is able to produce speech in multiple languages.

Semi-Supervised Monaural Singing Voice Separation With a Masking Network Trained on Synthetic Mixtures

1 code implementation14 Dec 2018 Michael Michelashvili, Sagie Benaim, Lior Wolf

We study the problem of semi-supervised singing voice separation, in which the training data contains a set of samples of mixed music (singing and instrumental) and an unmatched set of instrumental music.

Music Source Separation Speech Separation

Regularizing by the Variance of the Activations' Sample-Variances

no code implementations NeurIPS 2018 Etai Littwin, Lior Wolf

Normalization techniques play an important role in supporting efficient and often more effective training of deep neural networks.

Visual Analogies between Atari Games for Studying Transfer Learning in RL

no code implementations29 Jul 2018 Doron Sobol, Lior Wolf, Yaniv Taigman

For example, given a video frame in the target game, we map it to an analogous state in the source game and then attempt to play using a trained policy learned for the source game.

Atari Games Transfer Learning +1

Risk Bounds for Unsupervised Cross-Domain Mapping with IPMs

no code implementations23 Jul 2018 Tomer Galanti, Sagie Benaim, Lior Wolf

The recent empirical success of unsupervised cross-domain mapping algorithms, between two domains that share common characteristics, is not well-supported by theoretical justifications.

One-Shot Unsupervised Cross Domain Translation

2 code implementations NeurIPS 2018 Sagie Benaim, Lior Wolf

Given a single image x from domain A and a set of images from domain B, our task is to generate the analogous of x in B.

Translation Unsupervised Image-To-Image Translation +1

NAM: Non-Adversarial Unsupervised Domain Mapping

1 code implementation ECCV 2018 Yedid Hoshen, Lior Wolf

NAM relies on a pre-trained generative model of the target domain, and aligns each source image with an image synthesized from the target domain, while jointly optimizing the domain mapping function.

Confidence Prediction for Lexicon-Free OCR

no code implementations28 May 2018 Noam Mor, Lior Wolf

Having a reliable accuracy score is crucial for real world applications of OCR, since such systems are judged by the number of false readings.

General Classification Multi-class Classification +1

A Universal Music Translation Network

4 code implementations21 May 2018 Noam Mor, Lior Wolf, Adam Polyak, Yaniv Taigman

We present a method for translating music across musical instruments, genres, and styles.

Translation

Unsupervised Correlation Analysis

no code implementations CVPR 2018 Yedid Hoshen, Lior Wolf

Linking between two data sources is a basic building block in numerous computer vision problems.

Learning the Multiple Traveling Salesmen Problem with Permutation Invariant Pooling Networks

no code implementations26 Mar 2018 Yoav Kaempfer, Lior Wolf

While there are optimal TSP solvers, as well as recent learning-based approaches, the generalization of the TSP to the Multiple Traveling Salesmen Problem is much less studied.

Fitting New Speakers Based on a Short Untranscribed Sample

no code implementations ICML 2018 Eliya Nachmani, Adam Polyak, Yaniv Taigman, Lior Wolf

Learning-based Text To Speech systems have the potential to generalize from one speaker to the next and thus require a relatively short sample of any new voice.

Speech Synthesis

Non-Adversarial Unsupervised Word Translation

4 code implementations EMNLP 2018 Yedid Hoshen, Lior Wolf

We present a novel method that first aligns the second moment of the word distributions of the two languages and then iteratively refines the alignment.

Translation Word Translation

Identifying Analogies Across Domains

no code implementations ICLR 2018 Yedid Hoshen, Lior Wolf

We further show that the cross-domain mapping task can be broken into two parts: domain alignment and learning the mapping function.

Translation

Estimating the Success of Unsupervised Image to Image Translation

1 code implementation ECCV 2018 Sagie Benaim, Tomer Galanti, Lior Wolf

While in supervised learning, the validation error is an unbiased estimator of the generalization (test) error and complexity-based generalization bounds are abundant, no such bounds exist for learning a mapping in an unsupervised way.

Generalization Bounds Translation +1