Search Results for author:
Found 18 papers, 8 papers with code
TD-Paint: Faster Diffusion Inpainting Through Time Aware Pixel Conditioning
This technique allows the model to efficiently use known pixel values from the start, guiding the generation process toward the target manifold.
Adversarial Semi-Supervised Domain Adaptation for Semantic Segmentation: A New Role for Labeled Target Samples
Adversarial learning baselines for domain adaptation (DA) approaches in the context of semantic segmentation are under explored in semi-supervised framework.
SoccerNet 2023 Challenges Results
More information on the tasks, challenges, and leaderboards are available on https://www. soccer-net. org.
COMEDIAN: Self-Supervised Learning and Knowledge Distillation for Action Spotting using Transformers
We present COMEDIAN, a novel pipeline to initialize spatiotemporal transformers for action spotting, which involves self-supervised learning and knowledge distillation.
Ranked #1 on
Action Spotting
on SoccerNet-v2
Similarity Contrastive Estimation for Image and Video Soft Contrastive Self-Supervised Learning
A good data representation should contain relations between the instances, or semantic similarity and dissimilarity, that contrastive learning harms by considering all negatives as noise.
Ranked #1 on
Self-supervised Video Retrieval
on HMDB51
Physically-admissible polarimetric data augmentation for road-scene analysis
Polarimetric imaging, along with deep learning, has shown improved performances on different tasks including scene analysis.
Similarity Contrastive Estimation for Self-Supervised Soft Contrastive Learning
To circumvent this issue, we propose a novel formulation of contrastive learning using semantic similarity between instances called Similarity Contrastive Estimation (SCE).
Ranked #74 on
Self-Supervised Image Classification
on ImageNet
Open Set Domain Adaptation using Optimal Transport
We present a 2-step optimal transport approach that performs a mapping from a source distribution to a target distribution.
Pixel-wise Conditioned Generative Adversarial Networks for Image Synthesis and Completion
We investigate the influence of this regularization term on the quality of the generated images and the fulfillment of the given pixel constraints.
Pixel-wise Conditioning of Generative Adversarial Networks
In this paper, we study the effectiveness of conditioning GANs by adding an explicit regularization term to enforce pixel-wise conditions when very few pixel values are provided.
Dilated Spatial Generative Adversarial Networks for Ergodic Image Generation
In combination with convolutional (for the discriminator) and de-convolutional (for the generator) layers, they are particularly suitable for image generation, especially of natural scenes.
Gradient-based deterministic inversion of geophysical data with Generative Adversarial Networks: is it feasible?
Global probabilistic inversion within the latent space learned by Generative Adversarial Networks (GAN) has been recently demonstrated (Laloy et al., 2018).
Geophysics
An efficient supervised dictionary learning method for audio signal recognition
Motivated by this need of a principled framework across domain applications for machine listening, we propose a generic and data-driven representation learning approach.
Inversion using a new low-dimensional representation of complex binary geological media based on a deep neural network
Here, we use a deep neural network of the variational autoencoder type to construct a parametric low-dimensional base model parameterization of complex binary geological media.
Neural Networks Regularization Through Class-wise Invariant Representation Learning
In this work, we tackle the issue of training neural networks for classification task when few training samples are available.
Training-image based geostatistical inversion using a spatial generative adversarial neural network
After training, realizations containing a few millions of pixels/voxels can be produced in a matter of seconds.
Deep Neural Networks Regularization for Structured Output Prediction
The motivation of this work is to learn the output dependencies that may lie in the output data in order to improve the prediction accuracy.
Key point selection and clustering of swimmer coordination through Sparse Fisher-EM
To answer the existence of optimal swimmer learning/teaching strategies, this work introduces a two-level clustering in order to analyze temporal dynamics of motor learning in breaststroke swimming.
