Search Results for author:
Found 27 papers, 10 papers with code
Extending Video Masked Autoencoders to 128 frames
Nevertheless, the majority of prior works that leverage MAE pre-training have focused on relatively short video representations (16 / 32 frames in length) largely due to hardware memory and compute limitations that scale poorly with video length due to the dense memory-intensive self-attention decoding.
Ranked #1 on
Action Recognition
on Diving-48
(using extra training data)
Finite Scalar Quantization: VQ-VAE Made Simple
Each dimension is quantized to a small set of fixed values, leading to an (implicit) codebook given by the product of these sets.
High-Fidelity Image Compression with Score-based Generative Models
Despite the tremendous success of diffusion generative models in text-to-image generation, replicating this success in the domain of image compression has proven difficult.
M2T: Masking Transformers Twice for Faster Decoding
We show how bidirectional transformers trained for masked token prediction can be applied to neural image compression to achieve state-of-the-art results.
Multi-Realism Image Compression with a Conditional Generator
By optimizing the rate-distortion-realism trade-off, generative compression approaches produce detailed, realistic images, even at low bit rates, instead of the blurry reconstructions produced by rate-distortion optimized models.
VCT: A Video Compression Transformer
The resulting video compression transformer outperforms previous methods on standard video compression data sets.
Neural Video Compression using GANs for Detail Synthesis and Propagation
Our approach significantly outperforms previous neural and non-neural video compression methods in a user study, setting a new state-of-the-art in visual quality for neural methods.
On the advantages of stochastic encoders
Stochastic encoders have been used in rate-distortion theory and neural compression because they can be easier to handle.
High-Fidelity Generative Image Compression
We extensively study how to combine Generative Adversarial Networks and learned compression to obtain a state-of-the-art generative lossy compression system.
Universally Quantized Neural Compression
A popular approach to learning encoders for lossy compression is to use additive uniform noise during training as a differentiable approximation to test-time quantization.
Scale-Space Flow for End-to-End Optimized Video Compression
Despite considerable progress on end-to-end optimized deep networks for image compression, video coding remains a challenging task.
Interactive Full Image Segmentation by Considering All Regions Jointly
We propose an interactive, scribble-based annotation framework which operates on the whole image to produce segmentations for all regions.
Practical Full Resolution Learned Lossless Image Compression
We propose the first practical learned lossless image compression system, L3C, and show that it outperforms the popular engineered codecs, PNG, WebP and JPEG 2000.
Ranked #3 on
Image Compression
on ImageNet32
PIRM Challenge on Perceptual Image Enhancement on Smartphones: Report
This paper reviews the first challenge on efficient perceptual image enhancement with the focus on deploying deep learning models on smartphones.
Deep Generative Models for Distribution-Preserving Lossy Compression
We propose and study the problem of distribution-preserving lossy compression.
Generative Adversarial Networks for Extreme Learned Image Compression
We present a learned image compression system based on GANs, operating at extremely low bitrates.
Towards Image Understanding from Deep Compression without Decoding
Motivated by recent work on deep neural network (DNN)-based image compression methods showing potential improvements in image quality, savings in storage, and bandwidth reduction, we propose to perform image understanding tasks such as classification and segmentation directly on the compressed representations produced by these compression methods.
Conditional Probability Models for Deep Image Compression
During training, the auto-encoder makes use of the context model to estimate the entropy of its representation, and the context model is concurrently updated to learn the dependencies between the symbols in the latent representation.
ComboGAN: Unrestrained Scalability for Image Domain Translation
This year alone has seen unprecedented leaps in the area of learning-based image translation, namely CycleGAN, by Zhu et al.
Ranked #6 on
Facial Expression Translation
on CelebA
Logo Synthesis and Manipulation with Clustered Generative Adversarial Networks
We propose the use of synthetic labels obtained through clustering to disentangle and stabilize GAN training.
Optimal transport maps for distribution preserving operations on latent spaces of Generative Models
Generative models such as Variational Auto Encoders (VAEs) and Generative Adversarial Networks (GANs) are typically trained for a fixed prior distribution in the latent space, such as uniform or Gaussian.
Anchored Regression Networks Applied to Age Estimation and Super Resolution
We propose the Anchored Regression Network (ARN), a nonlinear regression network which can be seamlessly integrated into various networks or can be used stand-alone when the features have already been fixed.
WebVision Database: Visual Learning and Understanding from Web Data
Our new WebVision database and relevant studies in this work would benefit the advance of learning state-of-the-art visual models with minimum supervision based on web data.
WebVision Challenge: Visual Learning and Understanding With Web Data
The 2017 WebVision challenge consists of two tracks, the image classification task on WebVision test set, and the transfer learning task on PASCAL VOC 2012 dataset.
Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations
We present a new approach to learn compressible representations in deep architectures with an end-to-end training strategy.
k2-means for fast and accurate large scale clustering
k^2-means builds upon the standard k-means (Lloyd's algorithm) and combines a new strategy to accelerate the convergence with a new low time complexity divisive initialization.
Neighborhood Selection for Thresholding-based Subspace Clustering
Subspace clustering refers to the problem of clustering high-dimensional data points into a union of low-dimensional linear subspaces, where the number of subspaces, their dimensions and orientations are all unknown.
