training pipeline

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

CC BY

Machine Learning

Sound

Audio and Speech Processing

E2E-TTS: End-to-End Neural Text-to-Speech

JETS: Jointly Training FastSpeech2 and HiFi-GAN for End to End Text to Speech

We present end-to-end text-to-speech (e2e-tts) model which has a simplified training pipeline and outperforms a cascade of separately learned models.

Specifically, our proposed model is jointly trained fastspeech2 and hifi-gan with an accurate speech-text alignment module.

Machine Learning

Faster Neural Network Training with Data Echoing

In the twilight of Moore's law, GPUs and other specialized hardware accelerators have dramatically sped up neural network training. However, earlier stages of the training pipeline, such as disk I/O a

More...

Machine Learning

Distributed

Stats Machine Learning

Federated Transfer Learning with Dynamic Gradient Aggregation

In this paper, a Federated Learning (FL) simulation platform is introduced. The target scenario is Acoustic Model training based on this platform. To our knowledge, this is the first attempt to apply

More...

CC BY

Computer Vision

Exploiting saliency maps during segmentation training without re-training the classifier

Inferring the Class Conditional Response Map for Weakly Supervised Semantic Segmentation

Weakly supervised semantic segmentation (wsss) relies on classactivation maps (cams) for pseudo labels generation.

However, the generated pseudo labels are usually unsatisfactory to serve directly as supervision.

Machine Learning

Computer Vision

Joint Search of Data Augmentation Policies and Network Architectures

The common pipeline of training deep neural networks consists of several building blocks such as data augmentation and network architecture selection. AutoML is a research field that aims at automatic

More...

Computer Vision

Residual Mixture of Experts

Mixture of Experts (MoE) is able to scale up vision transformers effectively. However, it requires prohibiting computation resources to train a large MoE transformer. In this paper, we propose Residua

More...

Machine Learning

Neural and Evolutionary Computing

Rethinking Pretraining as a Bridge from ANNs to SNNs

Spiking neural networks (SNNs) are known as a typical kind of brain-inspired models with their unique features of rich neuronal dynamics, diverse coding schemes and low power consumption properties. H

More...

Machine Learning

Distributed

Stats Machine Learning

Reducing Communication in Graph Neural Network Training

Graph Neural Networks (GNNs) are powerful and flexible neural networks that use the naturally sparse connectivity information of the data. GNNs represent this connectivity as sparse matrices, which ha

More...

Machine Learning

Artificial Intelligence

High Energy Physics - Theory

Continual learning autoencoder training for a particle-in-cell simulation via streaming

The upcoming exascale era will provide a new generation of physics simulations. These simulations will have a high spatiotemporal resolution, which will impact the training of machine learning models

More...

Machine Learning

Computer Vision

Artificial Intelligence

Mask2Former for Video Instance Segmentation

We find Mask2Former also achieves state-of-the-art performance on video instance segmentation without modifying the architecture, the loss or even the training pipeline. In this report, we show univer

More...

Machine Learning

Computer Vision

Signal Processing

Stats Machine Learning

On Implicit Filter Level Sparsity in Convolutional Neural Networks

We investigate filter level sparsity that emerges in convolutional neural networks (CNNs) which employ Batch Normalization and ReLU activation, and are trained with adaptive gradient descent technique

More...

CC BY-SA

Artificial Intelligence

Robotics

Differentiable Simulation for Dynamic State Representation Learning

DiffSRL: Learning Dynamic-aware State Representation for Deformable Object Control with Differentiable Simulator

Dynamic state representation learning is an important task in robot learning and has wide application in areas such as accelerating model free reinforcement learning, closing the simulation to reality gap, as well as reducing the motion planning complexity.

However, current dynamic state representation learning methods scale poorly on complex dynamic systems such as deformable objects, and can not directly embed well defined simulation function into the training pipeline.

CC BY

Computer Vision

Mini-batch trimming for image classification

Some like it tough: Improving model generalization via progressively increasing the training difficulty

In this work, we propose to progressively increase the training difficulty during learning a neural network model via a novel strategy which we call mini-batch trimming.

Mini-batch trimming makes sure that the optimizer puts its focusin the later training stages on the more difficult samples, which we identify as the ones with the highest loss in the current mini-batch.

CC BY

Machine Learning

A Taxonomy of Algorithmically Efficient Deep Learning

Compute-Efficient Deep Learning: Algorithmic Trends and Opportunities

Deep learning has made great progress in recent years, but the exploding economic and environmental costs of training neural networks are becoming unsustainable.

To address this problem, there has been a great deal of research on *algorithmically-efficient deep learning*, which seeks to reduce trainingcosts not at the hardware or implementation level, but through changes in thesemantics of the training program.

Computer Vision

TridentAdapt: Learning Domain-invariance via Source-Target Confrontation and Self-induced Cross-domain Augmentation

Due to the difficulty of obtaining ground-truth labels, learning from virtual-world datasets is of great interest for real-world applications like semantic segmentation. From domain adaptation perspec

More...

CC BY

Computer Vision

F-VLM: A Simple Open-Vabulary Object Detection Method

F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models

We present a simple open-vocabulary object detection method built upon frozen vision and language models.

Surprisingly, we observe that a frozen vision model retains the locality-sensitive features necessary for detection, and 2) is a strong region classifier.

CC BY

Computer Vision

Image and Video Processing

An Asthma Microscopy Whole Slide Image Training Pipeline

Learning to be EXACT, Cell Detection for Asthma on Partially Annotated Whole Slide Images

We developed a training pipeline which can train a deep learning-based object detection model with partially annotated whole slide images (wsi) and compensate class imbalances on the fly.

With this approach we can freely sample from annotated areas and are not restricted to fullyannotated extracted sub-images of the wsi as with classical approaches.

Computer Vision

Computation and Language

Semantically Distributed Robust Optimization for Vision-and-Language Inference

Analysis of vision-and-language models has revealed their brittleness under linguistic phenomena such as paraphrasing, negation, textual entailment, and word substitutions with synonyms or antonyms. W

More...

Home

Discover

Bookmarks

◐ Recommended Follows

◐ Latest Activity