Pseudo rehearsal uses non-photo-realistic images to save resources without sacrificing performance.
problem Catastrophic forgetting in neural networks when learning new tasks.
method Synthetically generate non-photo-realistic images to rehearse previous tasks.
result Non-photo-realistic images can be used for rehearsal without sacrificing performance and significantly reduce resource consumption.
StackGAN generates photo-realistic images from text descriptions.
problem Generating high-quality images from text descriptions is challenging.
method StackGAN uses a sketch-refinement process with two GAN stages and Conditioning Augmentation.
result StackGAN generates photo-realistic images with photo-realistic details and necessary details.
Paper proposes using synthetic data to improve face recognition accuracy.
problem Improving face recognition accuracy using real data alone.
method Proposes a GAN that disentangles identity attributes and generates photo-realistic synthetic images.
result Synthetic images generated by the model are photo-realistic and can increase face recognition accuracy.
VALAN is a framework for navigation agents in photo-realistic environments.
problem Developing agents for indoor navigation tasks.
method Deep reinforcement learning with SEED RL architecture.
result VALAN framework can solve a variety of RL problems.
Photo-realistic super-resolution using GANs for large upscaling factors.
problem Recovering fine texture details at large upscaling factors.
method SRGAN, a GAN framework with adversarial and content losses.
result Significantly improved perceptual quality compared to state-of-the-art methods.
Paper proposes a new approach to improve WGAN training and achieves state-of-the-art results.
problem Difficulty in training GANs, especially Wasserstein GANs.
method Introduces a consistency term to enforce Lipschitz continuity in WGAN training.
result Achieves inception score of more than 5.0 with only 1,000 CIFAR-10 images and exceeds 90% accuracy on CIFAR-10 with 4,000 labeled images.
StackGAN++ generates high-quality images from text descriptions.
problem Generating high-quality photo-realistic images from text descriptions.
method Two-stage and multi-stage generative adversarial networks (GANs) with stacked architecture.
result StackGAN++ significantly outperforms other methods in generating photo-realistic images.
Improves GAN sample quality by refining the training dataset.
problem GANs generate unrealistic samples outside the data manifold.
method Instance selection to improve sample quality and reduce training time.
result Significantly reduces training time and improves sample fidelity.
This guide explains statistical distances for evaluating generative models.
problem Evaluating the quality of samples from generative models.
method Four statistical distances: SW, C2ST, MMD, FID.
result Different distances can yield varying results on similar data.
InvGAN combines generative and inference models for photo-realistic image manipulation.
problem GANs lack an inference model for image editing and downstream tasks.
method Train inference and generative models together to adapt and converge.
result InvGAN embeds real images into a high-quality generative model's latent space.
Efficiently generates high-resolution images with reduced sampling time using LEGO bricks.
problem Efficiently generating high-resolution images with reduced sampling time.
method Introduces LEGO bricks that integrate Local-feature Enrichment and Global-content Orchestration to create a test-time reconfigurable diffusion backbone.
result Significantly reduces sampling time compared to other methods.
IntroVAE synthesizes high-quality photos by self-evaluating and improving its outputs.
problem Generating high-quality photographic images with stable and realistic results.
method Introspective Variational Autoencoder (IntroVAE) that trains inference and generator models jointly, encouraging the inference model to distinguish between generated and real samples.
result Produces high-resolution photo-realistic images comparable to or better than state-of-the-art GANs.
Deep learning detects face swapping with high accuracy and uncertainty.
problem Photo-realistic face swapping without consent.
method Deep transfer learning for face swapping detection, human subject rankings for comparison.
result True positive rates >96% with minimal false alarms, uncertainty provided for each prediction.
Generative model predicts cell and nuclear structure from images.
problem Predicting subcellular structures from microscopy images.
method Conditional generative model using autoencoders.
result Photo-realistic cell images generated with probabilistic interpretation.
Unsupervised framework learns latent codes for controllable generation.
problem Challenging to achieve controllable generation with GANs.
method Self-training iterative feedback from discriminator to generator.
result Better disentanglement and semantic meaningful latent codes.
Synthetic data improves object detection with minimal real-world images.
problem Limited real-world data for object detection.
method Used domain randomization to generate synthetic data.
result 25% improvement in mAP metric with only 200 labelled images.
ExGANs use exemplar information to improve eye in-painting results.
problem Improving photo-realistic eye in-painting results.
method Conditional GAN with exemplar information at multiple points.
result ExGANs produce photo-realistic, personalized in-painting results.
Aims to learn from multiple unpredictable teachers with minimal interaction.
problem Learning from multiple non-deterministic teachers with low interaction cost.
method Develops a framework and an active learning algorithm to estimate a distribution over policy space.
result Significantly reduces interaction with teachers without compromising performance.
DCGANs generate realistic breast masses for mammography.
problem Lack of labelled data and imbalanced datasets in medical imaging.
method DCGANs trained on mammographic images to generate synthetic masses.
result DCGANs improve lesion detection in mammography by ~0.09 F1 score.
Automated testing improves deep learning model accuracy by 259.2%.
problem Ensuring robustness of deep learning models through automated testing.
method Jointly optimizing differential behaviors and neuron coverage; generating corner-cases; applying transformations and GANs.
result Deep learning model accuracy increased by 259.2% using automated generated corner cases.
FAMOS combines parametric and non-parametric methods for efficient image stylization.
problem Efficiently stylize images with limited data and compute resources.
method Fully Adversarial Mosaics (FAMOS) that integrates parametric and non-parametric approaches.
result Demonstrates the effectiveness of FAMOS in stylizing images with minimal data and compute resources.
Generative model creates realistic scenes from pixel-wise labels.
problem Creating photo-realistic scenes from pixel-wise labels.
method Semantic bottleneck GAN model combining conditional and unconditional generation networks.
result Model outperforms state-of-the-art models in unsupervised image synthesis.
Develops a deep model for joint image-text learning.
problem Bidirectional joint image-text modeling.
method Variational hetero-encoder randomized GAN (VHE-GAN).
result Achieves state-of-the-art performance in image-text learning and generation.
Researchers create virtual worlds for testing object tracking algorithms.
problem Expensive real-world data and manual labeling for object tracking.
method Generate photo-realistic virtual worlds using computer graphics.
result Deep learning models perform similarly in real and virtual worlds.
Paper proposes method to generate images from text using GANs trained on uncaptioned images.
problem Limited captioned image datasets for text-to-image synthesis.
method Conditional GANs trained on uncaptioned images with an Image Captioning Module.
result Promising preliminary results compared to unconditional GANs.
Generative model creates meal images from ingredient descriptions.
problem Synthesize photo-realistic meal images from ingredient descriptions.
method Attention-based ingredients-image association model, cycle-consistent constraint.
result Model generates meal images corresponding to ingredient descriptions.
New method controls generative models with continuous factors.
problem Lack of control over generative models and poor understanding of latent space.
method Introduces a method to find meaningful directions in latent space for precise control of generated images.
result Demonstrates effectiveness of method for GANs and variational auto-encoders.
Agent learns to navigate uncertain 3D maps using a hybrid planner.
problem Planning in 3D environments with uncertain topological maps.
method Hierarchical strategy combining graph planner and local policy, data-driven learning with neural network.
result Machine learning can overcome missing information in probabilistic topological maps.
StyleNeRF generates high-resolution images with 3D consistency and style control.
problem Generating high-resolution images with fine details and 3D consistency.
method Integrates NeRF into a style-based generator for efficient high-resolution image synthesis.
result Synthesizes high-resolution images at interactive rates with high 3D consistency and style control.
Sketch-BERT learns vector sketches using BERT-like self-supervised learning.
problem Lack of effective vector sketch representation for recognition and retrieval tasks.
method Generalized BERT to sketch domain with novel embedding networks and self-supervised sketch gestalt learning.
result Improved performance on sketch recognition, retrieval, and gestalt tasks.
Automatically infers high dynamic range illumination from a single indoor photo.
problem Predicting accurate indoor illumination from a single image.
method End-to-end deep neural network trained in three steps: lighting classifier, scene light localization, and fine-tuning for intensity prediction.
result Significantly outperforms previous methods in recovering high-quality HDR illumination.
Generative adversarial network synthesizes sketches into realistic images.
problem Improving the quality and realism of facial sketches.
method Hybrid GAN with quality guided encoder and identity preserving network.
result Synthesized images are more realistic and maintain identity.
DeepRacing uses neural networks to predict trajectories for autonomous racing in video games.
problem Training algorithms for high-speed autonomous racing in realistic environments.
method Developed a virtual testbed using F1 video games, trained neural networks to predict trajectories and control commands.
result Trajectory prediction outperforms end-to-end control methods in autonomous racing simulations.
Enhanced Sampling Scheme improves masked generative modeling.
problem Limitations of existing sampling schemes in masked non-autoregressive generative modeling.
method ESS consists of three stages: Naive Iterative Decoding, Critical Reverse Sampling, and Critical Resampling.
result ESS achieves significant performance gains in unconditional and class-conditional sampling.
PRS improves rejection sampling by learning better proposals.
problem High rejection rate in traditional rejection sampling.
method PRS uses a kernel estimator to learn better sampling proposals.
result PRS guarantees a low number of accepted samples.
This paper reviews various sampling methods from statistics and machine learning.
problem Addressing sampling methods in statistics and machine learning.
method Explains and reviews simple random sampling, bootstrapping, stratified sampling, cluster sampling, multistage sampling, network sampling, snowball sampling, and sampling from cumulative distribution function.
result Summarizes characteristics, pros, and cons of different sampling methods.
Adaptive sampling framework for varying probabilities.
problem Choosing good sampling probabilities for tasks and streams.
method Derives a general framework for adaptively changing sampling probabilities via thresholds.
result Shows when adaptive thresholds can be treated as independent samples.
RISA improves VFL by using imputed samples with low uncertainty.
problem Limited overlapping samples constrain VFL performance.
method Imputing non-overlapping samples and using evidence theory to select reliable imputed samples.
result Significant performance gains achieved, especially with limited overlapping samples.
Improved privacy-preserving methods for estimating multiple samples from distributions.
problem Estimating multiple samples from distributions while maintaining privacy.
method Developed new multi-sampling techniques for differentially private data estimation.
result Achieved significant reduction in sample complexity for multi-sampling from finite domains and Gaussian distributions.
Gradient-based sampling improves LS problem solving efficiency.
problem Computational difficulties in large sample size data analysis.
method Adaptive sampling dependent on input and output gradients.
result Gradient-based sampling improves statistical efficiency and computational saving.
Paper introduces a new sampling method combining Consistency Models with importance sampling.
problem Inherent errors in samples and high NFEs for high-quality samples in Boltzmann distributions.
method Combines Consistency Models with importance sampling to produce unbiased samples with minimal NFEs.
result Produces unbiased samples using only 6-25 NFEs, comparable to 100 NFEs for DDPMs.
Ensemble sampling extends Thompson sampling's applicability to complex models.
problem Limited applicability of Thompson sampling to complex models.
method Develops ensemble sampling to approximate Thompson sampling for complex models.
result Ensemble sampling expands the viability of Thompson sampling to more applications.
Wedge Sampling improves tensor completion with nearly-linear sample complexity.
problem Efficiently completing low-rank tensors from a subset of entries.
method Non-adaptive wedge sampling to promote structured connections in tensor completion.
result Polynomial-time algorithms achieve weak and exact recovery with nearly linear sample complexity.
Neural network accuracy improves with denser training samples.
problem Improving neural network accuracy on unseen test samples.
method Bounding empirical training error smoothed across activation regions and using it to discard high-risk test samples.
result Discarding high-risk test samples based on error bounds improves prediction accuracy by up to 20%.
Algorithm samples constrained stochastic differential equations.
problem Sampling stochastic differential equations with complex constraints.
method Pathspace Metropolis-adjusted manifold sampling.
result Demonstrated effectiveness in various constrained conditions.
Generative models map simple samples to complex target samples.
problem Improving Monte-Carlo sampling techniques.
method Variational learning of dynamical maps between base and target measures.
result Improved sampling efficiency through feedback loops.
New sampling algorithm for non-smooth potentials.
problem Sampling from non-smooth potentials.
method Proximal algorithm based on rejection sampling.
result Achieves better complexity than existing methods.
Efficiently samples sequences without replacement for machine learning models.
problem Generating diverse outputs from sequential models without duplicates.
method Incremental sampling procedure for randomized programs, including neural models.
result Efficacy and flexibility of incremental sampling for large output spaces.