A fusion of multiple classifiers improves indoor localization using visible light.
problem Indoor localization accuracy and robustness using visible light.
method Transmit different intensity modulated sinusoidal signals, capture peaks of PSD, train multiple classifiers, and combine their outputs using robust fusion algorithms.
result The proposed algorithms significantly improve localization accuracy and robustness compared to existing methods.
Paper develops data-driven compact models for diodes.
problem Manual and time-consuming compact model development.
method Machine Learning techniques for automation.
result Data-driven models accurately predict diode behavior.
Neural Photo Editor uses AI to edit photos accurately and coherently.
problem Achieving accurate reconstructions in photo editing.
method Introspective Adversarial Network (VAE-GAN hybrid) with weight-shared dilated convolutions and Orthogonal Regularization.
result Produces high-fidelity photo edits and reconstructions.
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.
A new object detector identifies fashion items from social media photos.
problem Difficult to parse and classify fashion items from social media content.
method Pretrained unsupervised object detector on 24 categories from Open Images V4.
result 72.7% mAP on test dataset of 2.4K photos, outperforming state-of-the-art.
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 identifies food types from Yelp photos using machine learning.
problem Ineffective labeling of food photos on Yelp.
method Image pre-processing, CNN feature extraction, and classification algorithms.
result Identifies up to 10 food types from raw photos with high accuracy.
The goal of cross-domain object matching (CDOM) is to find correspondence between two sets of objects in different domains in an unsupervised way. Photo album summarization is a typical application of CDOM, where photos are automatically aligned into a designed frame expressed in the Cartesian coordinate system. CDOM i…
Photo-identification technique improved for new dolphin individuals.
problem Traditional photo-identification of dolphins is laborious and manual.
method Metric embedding learning using triplet loss function in Euclidean space.
result Compact representation of fin images generalizes well to new identities.
Paper introduces DACAL for high-resolution photo and video enhancement.
problem Photo and video enhancement with weak supervision.
method Divide-and-conquer adversarial learning approach with hierarchical decomposition.
result State-of-the-art performance in high-resolution photo and video enhancement.
Develops a system to suggest multiple photo edits based on user preferences.
problem Photo editing is complicated and subjective, making it hard for novices.
method Uses deep generative models with hierarchical structure to learn from diverse users.
result The model outperforms other approaches in suggesting multiple high-quality edits.
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.
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.
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.
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.
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.
Deep learning aids UAVs in identifying disasters with high accuracy.
problem Monitoring disasters for effective mitigation.
method Deep learning applied to aerial photos from UAVs.
result 91% accuracy in disaster identification from 544 images.
Sym-NET detects human symmetries in photos, outperforming existing models.
problem Capturing human symmetry perception in real-world images.
method Deep-learning neural network (Sym-NET) trained on MS-COCO dataset with human labels.
result Sym-NET significantly outperforms existing algorithms on unseen MS-COCO photos.
Content based image retrieval, a technique which uses visual contents of image to search images from large scale image databases according to users' interests. This paper provides a comprehensive survey on recent technology used in the area of content based face image retrieval. Nowadays digital devices and photo shari…
This work introduces benchmarks for evaluating nanophotonic structures in design simulations.
problem Design and understanding of nanophotonic structures for various applications.
method Development of frameworks and benchmarks for evaluating nanophotonic structures in parametric design problems.
result Strategic use of evaluation fidelity in enhancing structure designs.
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.
Detect knots from photos using machine learning and traditional algorithms.
problem Automatically recognize knots from images.
method Combining CNN and transformer architectures for image recognition with traditional knot invariants.
result Lightweight machine learning models can recover meaningful structural information from images.
Large-scale surveys make huge amounts of photometric data available. Because of the sheer amount of objects, spectral data cannot be obtained for all of them. Therefore it is important to devise techniques for reliably estimating physical properties of objects from photometric information alone. These estimates are nee…
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.
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.
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.
Differentiable losses for combinatorial optimization problems in sequence modeling.
problem Mismatch between training and inference objectives in sequence models.
method Gradient descent over linear programs representing combinatorial optimization problems.
result Gradient descent can be applied to combinatorial optimization problems efficiently.
PICZL improves photometric redshifts for AGN in all-sky surveys.
problem Challenges in accurately computing photo-z for AGN due to interplay of SMBH and host galaxy emissions.
method PICZL uses an ensemble of CNNs with cross-channel integration of image and catalog data, leveraging Gaussian mixture models.
result PICZL achieves a photo-z variance of 4.5% and outlier fraction of 5.6% on a validation sample of 8098 AGN, outperforming previous methods.
Study uses PPG signals for detecting speech events and speaker characteristics.
problem Detecting speech events and speaker characteristics from PPG signals.
method End-to-end convolutional neural network architectures for gender and person verification.
result Promising results showing potential of PPG for speech processing tasks.
Paper proposes a method to encrypt faces while maintaining visual similarity.
problem Protecting personal data from unauthorized face recognition.
method Targeted identity-protection iterative method (TIP-IM) to generate adversarial identity masks.
result TIP-IM provides 95%+ protection success rate against face recognition models.
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.
The paper uses causal machine learning to optimize rework decisions in manufacturing.
problem Optimizing rework policies in manufacturing systems to balance yield improvement and rework costs.
method Proposes a causal model using double/debiased machine learning (DML) techniques to estimate conditional treatment effects and derive rework policies.
result Achieved a yield improvement of 2-3% during the color-conversion process of white LEDs.
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.
Paper presents a new method for cross-domain visual matching.
problem Cross-domain visual data matching in real-world vision tasks.
method Expands linear projections into affine transformations and combines Mahalanobis distance and Cosine similarity.
result Superior performance in cross-domain matching tasks over state-of-the-art methods.
Study uses CNNs to estimate BMI from photos.
problem Estimating BMI from photos with limited data.
method Used deep learning (CNNs) to process silhouette images.
result High correlation between estimated and actual BMI.
When dealing with subjective, noisy, or otherwise nebulous features, the "wisdom of crowds" suggests that one may benefit from multiple judgments of the same feature on the same object. We give theoretically-motivated `feature multi-selection' algorithms that choose, among a large set of candidate features, not only wh…
We extend GAN latent space projection for Gaussian priors.
problem Non-trivial latent space projection for GANs with Gaussian priors.
method Extend previous techniques to Gaussian priors.
result Demonstrated effectiveness of extended technique.
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.
Research connects physics and math through ceramic art of Riemann surfaces.
problem Classifying curves on Riemann surfaces using 'pairs of pants'.
method Exploring mathematical concepts through artistic ceramics.
result Illustrates the classification of curves on Riemann surfaces.
Paper improves geographic location embeddings using Flickr tags and structured data.
problem Lack of integration between Flickr metadata and structured scientific data.
method Learning vector space embeddings of geographic locations.
result Improved predictions of ecological features using the new method.
Generative model creates user-specified textures from datasets.
problem Creating detailed textures from raw data.
method Generative adversarial networks with user control and adversarial loss.
result Model generates descriptive texture manifolds and 3D textures.
Model learns individual preferences for photo aesthetics.
problem Lack of personalized aesthetics models in photography.
method Residual learning approach to adapt to individual preferences.
result Surpasses state-of-the-art methods in predicting aesthetic value.
Machine learning speeds up molecular photodynamics simulations to nanosecond scales.
problem High cost of quantum chemistry limits accurate long time scale simulations.
method Use machine learning to predict electronic properties from molecular geometry.
result Machine learning algorithms can simulate photodynamics with higher efficiency and accuracy.
New ONMF model minimizes KL divergence for better sparse data modeling.
problem Clustering and data modeling with sparse vectors.
method Developed KL-ONMF algorithm based on alternating optimization.
result KL-ONMF outperforms Frobenius-norm ONMF for document classification and hyperspectral image unmixing.
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.
Generates convincing swapped images of fashion articles on people.
problem Automatic swapping of clothing on fashion model photos.
method Conditional Analogy Generative Adversarial Network (CAGAN) based on adversarial training and deep convolutional neural networks.
result Plausible segmentation masks and convincing swapped 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.