Search Results for author:
Found 21 papers, 11 papers with code
Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach
This manual process has some limitations similar to those encountered in supervised learning, e. g., the crowd-sourced selection of data is costly and time-consuming, preventing scaling the dataset size.
Better (pseudo-)labels for semi-supervised instance segmentation
Despite the availability of large datasets for tasks like image classification and image-text alignment, labeled data for more complex recognition tasks, such as detection and segmentation, is less abundant.
Unlocking Pre-trained Image Backbones for Semantic Image Synthesis
Semantic image synthesis, i. e., generating images from user-provided semantic label maps, is an important conditional image generation task as it allows to control both the content as well as the spatial layout of generated images.
Guided Distillation for Semi-Supervised Instance Segmentation
Although instance segmentation methods have improved considerably, the dominant paradigm is to rely on fully-annotated training images, which are tedious to obtain.
Very high resolution canopy height maps from RGB imagery using self-supervised vision transformer and convolutional decoder trained on Aerial Lidar
The maps are generated by the extraction of features from a self-supervised model trained on Maxar imagery from 2017 to 2020, and the training of a dense prediction decoder against aerial lidar maps.
Unifying conditional and unconditional semantic image synthesis with OCO-GAN
To allow for more control, image synthesis can be conditioned on semantic segmentation maps that instruct the generator the position of objects in the image.
Efficient conditioned face animation using frontally-viewed embedding
As the quality of few shot facial animation from landmarks increases, new applications become possible, such as ultra low bandwidth video chat compression with a high degree of realism.
Low Bandwidth Video-Chat Compression using Deep Generative Models
To unlock video chat for hundreds of millions of people hindered by poor connectivity or unaffordable data costs, we propose to authentically reconstruct faces on the receiver's device using facial landmarks extracted at the sender's side and transmitted over the network.
Tarsier: Evolving Noise Injection in Super-Resolution GANs
More generally, our approach can be used to optimize any method based on noise injection.
Impact of base dataset design on few-shot image classification
In this paper, we systematically study the effect of variations in the training data by evaluating deep features trained on different image sets in a few-shot classification setting.
Inspirational Adversarial Image Generation
We design a simple optimization method to find the optimal latent parameters corresponding to the closest generation to any input inspirational image.
Learning Diverse Generations using Determinantal Point Processes
Embedded in an adversarial training and variational autoencoder, our Generative DPP approach shows a consistent resistance to mode-collapse on a wide-variety of synthetic data and natural image datasets including MNIST, CIFAR10, and CelebA, while outperforming state-of-the-art methods for data-efficiency, convergence-time, and generation quality.
Unsupervised Image Decomposition in Vector Layers
Deep image generation is becoming a tool to enhance artists and designers creativity potential.
GDPP: Learning Diverse Generations Using Determinantal Point Process
Generative models have proven to be an outstanding tool for representing high-dimensional probability distributions and generating realistic-looking images.
Deep Spatio-Temporal Random Fields for Efficient Video Segmentation
In this work we introduce a time- and memory-efficient method for structured prediction that couples neuron decisions across both space at time.
Ranked #9 on
Semantic Segmentation
on CamVid
DeSIGN: Design Inspiration from Generative Networks
Can an algorithm create original and compelling fashion designs to serve as an inspirational assistant?
Predicting Future Instance Segmentation by Forecasting Convolutional Features
We apply the "detection head'" of Mask R-CNN on the predicted features to produce the instance segmentation of future frames.
Predicting Deeper into the Future of Semantic Segmentation
The ability to predict and therefore to anticipate the future is an important attribute of intelligence.
BARCHAN: Blob Alignment for Robust CHromatographic ANalysis
Comprehensive Two dimensional gas chromatography (GCxGC) plays a central role into the elucidation of complex samples.
Semantic Segmentation using Adversarial Networks
Adversarial training has been shown to produce state of the art results for generative image modeling.
Deep multi-scale video prediction beyond mean square error
Learning to predict future images from a video sequence involves the construction of an internal representation that models the image evolution accurately, and therefore, to some degree, its content and dynamics.
