Preserves content while changing style in text.
problem Text style transfer often fails to preserve content.
method Leverages linguistic information in structured supervisions.
result Significant improvement in content preservation and style transfer.
A method for disentangling text representations without supervision.
problem Challenges in learning disentangled representations of natural language.
method Information-theoretic guidance to induce independent style and content embeddings.
result High quality disentangled representations in terms of content and style preservation.
Zero-shot contrastive loss improves text-guided image style transfer without extra training.
problem Stochastic nature of diffusion models leads to trade-offs between style transformation and content preservation.
method Proposes a zero-shot contrastive loss for diffusion models that doesn't require additional fine-tuning or auxiliary networks.
result Method outperforms existing methods while preserving content and requiring no additional training.
Improved TTS style transfer across disjoint datasets with adversarial cycle consistency.
problem Suboptimal TTS style transfer on disjoint datasets with underrepresented styles.
method Adversarial cycle consistency training with paired and unpaired triplets.
result 78% improvement in style transfer with minimal reduction in fidelity and naturalness.
A new method for image translation using disentangled style and content preservation.
problem Difficulty in maintaining original content during reverse diffusion in diffusion-based image translation.
method Disentangled style and content representation using intermediate keys from ViT model, CLIP loss, semantic divergence loss, and resampling strategy.
result Outperforms state-of-the-art models in text-guided and image-guided translation tasks.
XL-Editor improves sentence post-editing using XLNet's variable-length insertion probability.
problem Post-editing sentences to refine generated text.
method XL-Editor trains XLNet to estimate variable-length insertion probabilities and apply post-editing operations.
result XL-Editor outperforms XLNet on text insertion and deletion tasks, and achieves significant style transfer improvements.
Unified model for audio control and style transfer.
problem Explicit control and style transfer in music generation.
method Diffusion autoencoders for semantic feature extraction, disentanglement using adversarial criterion.
result Model generates audio matching timbre targets with specified structure.
Improved autoencoders guide latent sentence representations for better text generation and manipulation.
problem Current autoencoders struggle to maintain coherent latent spaces for meaningful text manipulations.
method Adversarial autoencoders with a denoising objective (DAAE) to guide latent space geometry.
result DAAE provides the best trade-off between generation quality and reconstruction capacity.
Efficiently transfers style to content without distorting the content structure.
problem Arbitrary style transfer in computer vision.
method Rigid alignment of style features to content features.
result High-quality stylized images with intact content structure.
MuLan links music audio to natural language tags.
problem Traditional music tagging systems use rigid attributes; MuLan aims to link audio directly to natural language.
method Joint audio-text embedding model trained on 44 million music recordings and text annotations.
result MuLan's embeddings enable zero-shot functionalities and transfer learning.
Proposes Gaussian optimal transport for image style transfer.
problem Image style transfer and mixing different artistic styles.
method Encoder/Decoder framework with optimal transport for Gaussian measures.
result Simple methodology for generating stylized content interpolating between many styles.
Deep learning improves handwriting style transfer and extraction.
problem Improving handwriting style transfer and extraction using deep neural networks.
method Used a deep conditioned autoencoder on IRON-OFF handwriting data-set to explore style transfer and extraction.
result Improved metrics of state-of-the-art methods by a large margin in style transfer and extraction experiments.
New method for one-shot timbre transfer in music.
problem One-shot timbre transfer in music.
method Self-supervised VQ-VAE extension for disentangled representations.
result Outperforms selected baselines on objective metrics.
Paper tackles artist style transfer using quadratic potential.
problem Applying a specific artist's style to real-world photographs.
method Adversarial training with quadratic potential divergence and integration of deep learning techniques.
result Demonstrates improved quality of artist stylized images.
MicAugment transfers audio style from few seconds of input to match target conditions.
problem Audio model robustness to diverse acquisition conditions.
method Identifies and applies transformations learned from target audio to input audio.
result MicAugment significantly improves model robustness in downstream tasks.
A new autoencoder speeds up audio style transfer.
problem Efficiently generating stylized audio from content audio.
method Autoencoder architecture for real-time audio style transfer.
result Single forward pass for stylized audio generation.
We introduce MIDI-VAE, a neural network model based on Variational Autoencoders that is capable of handling polyphonic music with multiple instrument tracks, as well as modeling the dynamics of music by incorporating note durations and velocities. We show that MIDI-VAE can perform style transfer on symbolic music by au…
New method transfers emotions in facial images.
problem Transforming facial images to different emotions.
method Infinite task learning and vector-valued reproducing kernel Hilbert spaces.
result Achieves low reconstruction cost and high emotion classification accuracy.
SASSL improves self-supervised learning by preserving image structure.
problem Distorted augmented samples in self-supervised learning.
method Neural Style Transfer to decouple semantic and stylistic attributes.
result Boosts ImageNet top-1 accuracy by up to 2 percentage points.
AI recovers lost art from x-rays.
problem Reconstructing lost artwork under layers of x-ray imaging.
method Neural style transfer applied to x-radiographs.
result Reconstructed lost artwork visible through x-rays.
Global Style Tokens (GSTs) are a recently-proposed method to learn latent disentangled representations of high-dimensional data. GSTs can be used within Tacotron, a state-of-the-art end-to-end text-to-speech synthesis system, to uncover expressive factors of variation in speaking style. In this work, we introduce the T…
Proposes a VAE with a discrete bottleneck for better text generation.
problem VAEs struggle with latent variable auto-regressive decoding in text generation.
method Introduces a discretized bottleneck to enforce latent feature matching in a compact space.
result Demonstrates improved text generation capabilities across various tasks.
SCR diversifies recommendations by applying style transfer to user profiles.
problem Diversify personalized recommendations without losing relevance.
method Style injection using Conditional Variational Autoencoder (CVAE) architecture.
result 12% improvement in NDCG@20 and 22% improvement in AUC across all classes.
TimbreTron transfers musical timbre using CQT and WaveNet.
problem Transfer musical timbre while preserving pitch, rhythm, and loudness.
method Apply image domain style transfer to CQT representation, then generate high-quality waveform with WaveNet.
result TimbreTron recognizably transfers timbre while preserving musical content.
Enhanced text-to-speech synthesizes expressive speech from a single example.
problem Creating a new expressive speech style from a single example of speech.
method Combines VAE and Normalizing Flows to improve disentanglement and naturalness.
result Reduces KL-divergence by 22% and improves perceptual metrics.
Enhances nighttime vehicle detection using style transfer and augmentation.
problem Nighttime object detection challenges due to lack of lighting and glare.
method Day-to-night style transfer and labeling-free augmentation with CARLA synthetic data.
result Significant improvements in nighttime vehicle detection with YOLO11 model.
The seminal work of Gatys et al. demonstrated the power of Convolutional Neural Networks (CNNs) in creating artistic imagery by separating and recombining image content and style. This process of using CNNs to render a content image in different styles is referred to as Neural Style Transfer (NST). Since then, NST has …
Improved GAN training stability through clipping and reweighting.
problem Inconsistent GAN training leading to inferior performance.
method Proposes a variational GAN framework with probability ratio clipping and sample reweighting.
result Significantly improved performance across various GAN tasks.
Deep learning system generates new Chinese fonts via style variables.
problem Efficiently design new Chinese fonts.
method End-to-end deep learning system generating new style fonts via interpolation of latent style-related embedding variables.
result Smooth transition between different font styles achieved.
New method reduces text classification errors by learning writing style instead of content.
problem Deep neural networks learn superficial patterns specific to training data.
method Adversarial training to unlearn confounding features.
result Model generalizes better and learns writing style features.
AUTOVC converts voices without parallel data, achieving state-of-the-art results.
problem Non-parallel many-to-many voice conversion and zero-shot voice conversion.
method Only an autoencoder with a carefully designed bottleneck is used, training on a self-reconstruction loss.
result AUTOVC achieves state-of-the-art results in many-to-many voice conversion with non-parallel data and performs zero-shot voice conversion.
Advances deep latent variable models for more flexible text generation.
problem Limited representation power of VAEs due to Gaussian assumptions and posterior collapse.
method Develops sample-based variational distributions and an LVM to directly match aggregated posterior to prior.
result Demonstrates improved text generation in various scenarios.
Method converts emotions in nonparallel speech data.
problem Lack of parallel data for speech emotion conversion.
method Unsupervised style transfer technique for nonparallel training.
result Effectiveness demonstrated on nonparallel corpora with four emotions.
RB-Modulation trains free diffusion models without external adapters.
problem Training-free personalization of diffusion models with style and content control.
method Stochastic optimal control with a style descriptor and cross-attention aggregation.
result Precise content and style extraction and control without external adapters.
Neural painters learn to generate brushstrokes from a non-deterministic painting program.
problem Training an agent to generate realistic brushstrokes from a non-differentiable painting program.
method A differentiable neural painter model trained on brushstrokes, optimizing for human-like strokes and intrinsic style transfer.
result Direct optimization of brushstrokes can visualize ImageNet categories and generate ideal paintings.
Paper generates personalized fonts from a few characters.
problem Creating personalized fonts from a limited set of characters.
method Designs a network framework to extract and recombine character content and style using various neural networks.
result Generated characters are structurally similar to real characters.
Unified framework improves NLP tasks by converting diverse problems into text-to-text format.
problem Improving natural language processing tasks through transfer learning.
method Unified text-to-text transformer framework, comparing various pre-training objectives and architectures.
result Achieved state-of-the-art results on multiple NLP benchmarks.
Study develops supervised algorithm for symbolic music style translation.
problem Transforming musical style while maintaining original content.
method Synthetic data generation for aligned training data, encoder-decoder model.
result Trained models produce meaningful accompaniments for real MIDI recordings.
Paper presents Transfer Portal model for accurate player performance predictions.
problem Predicting future player performance after a transfer.
method Personalized neural network and Bayesian updating framework.
result Model generates accurate predictions for player performance at new clubs.
Deep generative models such as Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs) have recently been applied to style and domain transfer for images, and in the case of VAEs, music. GAN-based models employing several generators and some form of cycle consistency loss have been among the most suc…
A new generator for GANs separates style and variation.
problem Improving GANs' ability to control and disentangle image attributes.
method Borrowing from style transfer, a new generator architecture.
result Improves GANs' quality and disentanglement of latent factors.
When training a deep neural network for image classification, one can broadly distinguish between two types of latent features of images that will drive the classification. We can divide latent features into (i) "core" or "conditionally invariant" features Xcore whose distribution Xcore∣Y, cond…
Deep learning-based style transfer between images has recently become a popular area of research. A common way of encoding "style" is through a feature representation based on the Gram matrix of features extracted by some pre-trained neural network or some other form of feature statistics. Such a definition is based on…
This paper presents a Semantic Attribute Modulation (SAM) for language modeling and style variation. The semantic attribute modulation includes various document attributes, such as titles, authors, and document categories. We consider two types of attributes, (title attributes and category attributes), and a flexible a…
Paper proposes a reinforcement learning framework for text summarization.
problem Transfer learning effectiveness in text summarization is not well explored.
method Reinforcement learning with a self-critic policy gradient approach.
result Achieves good generalization and state-of-the-art results on various datasets.
In this paper, we introduce an unsupervised learning approach to automatically discover, summarize, and manipulate artistic styles from large collections of paintings. Our method is based on archetypal analysis, which is an unsupervised learning technique akin to sparse coding with a geometric interpretation. When appl…
Ground-A-Video edits videos without training, preserving intended changes.
problem Complex multi-attribute video editing with omitted or wrong changes.
method Grounding-guided video-to-video translation with Cross-Frame Gated Attention.
result Zero-shot multi-attribute video editing with improved accuracy and frame consistency.
The paper tackles calibrating long-term behaviors with multiple styles using programmatic style-consistency.
problem Generating long-term sequential behaviors with multiple styles simultaneously.
method Leverage programmatic labeling functions to specify controllable styles and derive style-consistency as a learning objective.
result Learned policies can be calibrated for up to 1024 distinct style combinations.