Search Results for author:
Found 20 papers, 8 papers with code
Breaking MLPerf Training: A Case Study on Optimizing BERT
Speeding up the large-scale distributed training is challenging in that it requires improving various components of training including load balancing, communication, optimizers, etc.
Geometry Transfer for Stylizing Radiance Fields
Shape and geometric patterns are essential in defining stylistic identity.
MetaMix: Meta-state Precision Searcher for Mixed-precision Activation Quantization
Mixed-precision quantization of efficient networks often suffer from activation instability encountered in the exploration of bit selections.
MFOS: Model-Free & One-Shot Object Pose Estimation
Existing learning-based methods for object pose estimation in RGB images are mostly model-specific or category based.
AnyFlow: Arbitrary Scale Optical Flow with Implicit Neural Representation
To apply optical flow in practice, it is often necessary to resize the input to smaller dimensions in order to reduce computational costs.
BASQ: Branch-wise Activation-clipping Search Quantization for Sub-4-bit Neural Networks
In this paper, we propose Branch-wise Activation-clipping Search Quantization (BASQ), which is a novel quantization method for low-bit activation.
Memory Efficient Patch-based Training for INR-based GANs
However, training existing approaches require a heavy computational cost proportional to the image resolution, since they compute an MLP operation for every (x, y) coordinate.
NIPQ: Noise proxy-based Integrated Pseudo-Quantization
Recently, pseudoquantization training has been proposed as an alternative approach to updating the learnable parameters using the pseudo-quantization noise instead of STE.
On the Overlooked Significance of Underutilized Contextual Features in Recent News Recommendation Models
Personalized news recommendation aims to provide attractive articles for readers by predicting their likelihood of clicking on a certain article.
Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimation
Self-supervised monocular depth estimation has been widely studied, owing to its practical importance and recent promising improvements.
Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing
Although manipulating the latent vectors controls the synthesized outputs, editing real images with GANs suffers from i) time-consuming optimization for projecting real images to the latent vectors, ii) or inaccurate embedding through an encoder.
A StyleMap-Based Generator for Real-Time Image Projection and Local Editing
State-of-the-art GAN-based methods for editing real images suffer from time-consuming operations in projecting real images to latent vectors.
MEANTIME: Mixture of Attention Mechanisms with Multi-temporal Embeddings for Sequential Recommendation
Following the custom from language processing, most of these models rely on a simple positional embedding to exploit the sequential nature of the user's history.
PROFIT: A Novel Training Method for sub-4-bit MobileNet Models
In the ablation study of the 3-bit quantization of MobileNet-v3, our proposed method outperforms the state-of-the-art method by a large margin, 12. 86 % of top-1 accuracy.
Tag2Pix: Line Art Colorization Using Text Tag With SECat and Changing Loss
A GAN approach is proposed, called Tag2Pix, of line art colorization which takes as input a grayscale line art and color tag information and produces a quality colored image.
Precision Highway for Ultra Low-Precision Quantization
We also report that the proposed method significantly outperforms the existing method in the 2-bit quantization of an LSTM for language modeling.
Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications
The application of deep learning techniques resulted in remarkable improvement of machine learning models.
Value-aware Quantization for Training and Inference of Neural Networks
We propose a novel value-aware quantization which applies aggressively reduced precision to the majority of data while separately handling a small amount of large data in high precision, which reduces total quantization errors under very low precision.
Weighted-Entropy-Based Quantization for Deep Neural Networks
Quantization is considered as one of the most effective methods to optimize the inference cost of neural network models for their deployment to mobile and embedded systems, which have tight resource constraints.
Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications
Although the latest high-end smartphone has powerful CPU and GPU, running deeper convolutional neural networks (CNNs) for complex tasks such as ImageNet classification on mobile devices is challenging.
