Search Results for author:
Found 57 papers, 20 papers with code
Vcc: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens
Transformers are central in modern natural language processing and computer vision applications.
Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition
This work proposes POMP, a prompt pre-training method for vision-language models.
Ranked #1 on
Open Vocabulary Semantic Segmentation
on PascalVOC-20
(hIoU metric)
Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation with Cross-Scale Distortion Awareness
Based on the Manhattan World assumption, most existing indoor layout estimation schemes focus on recovering layouts from vertically compressed 1D sequences.
Decoupled Model Schedule for Deep Learning Training
Specifically, the schedule works on a PyTorch model and uses a set of schedule primitives to convert the model for common model training optimizations such as high-performance kernels, effective 3D parallelism, and efficient activation checkpointing.
SPT: Semi-Parametric Prompt Tuning for Multitask Prompted Learning
Pre-trained large language models can efficiently interpolate human-written prompts in a natural way.
SMILE: Scaling Mixture-of-Experts with Efficient Bi-level Routing
The mixture of Expert (MoE) parallelism is a recent advancement that scales up the model size with constant computational cost.
Technical Report of Mixing Local Patterns
Graph neural networks (GNNs) have shown remarkable performance on homophilic graph data while being far less impressive when handling non-homophilic graph data due to the inherent low-pass filtering property of GNNs.
A Survey of Deep Causal Models and Their Industrial Applications
The concept of causality plays a significant role in human cognition.
Removing Batch Normalization Boosts Adversarial Training
In addition, NoFrost achieves a $23. 56\%$ adversarial robustness against PGD attack, which improves the $13. 57\%$ robustness in BN-based AT.
Partial and Asymmetric Contrastive Learning for Out-of-Distribution Detection in Long-Tailed Recognition
However, in real-world applications, it is common for the training sets to have long-tailed distributions.
Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems
We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9. 3B, their subsequent distillation into smaller models ranging from 17M-170M parameters, and their application to the Natural Language Understanding (NLU) component of a virtual assistant system.
Cross-Lingual Natural Language Inference
intent-classification
+5
Multi-modal Graph Learning for Disease Prediction
For disease prediction tasks, most existing graph-based methods tend to define the graph manually based on specified modality (e. g., demographic information), and then integrated other modalities to obtain the patient representation by Graph Representation Learning (GRL).
Contractive error feedback for gradient compression
On-device memory concerns in distributed deep learning are becoming more severe due to i) the growth of model size in multi-GPU training, and ii) the adoption of neural networks for federated learning on IoT devices with limited storage.
Zero-shot Object Detection Through Vision-Language Embedding Alignment
Recent approaches have shown that training deep neural networks directly on large-scale image-text pair collections enables zero-shot transfer on various recognition tasks.
CETransformer: Casual Effect Estimation via Transformer Based Representation Learning
Treatment effect estimation, which refers to the estimation of causal effects and aims to measure the strength of the causal relationship, is of great importance in many fields but is a challenging problem in practice.
Multi-modal Graph Learning for Disease Prediction
However, it is not easy for these approaches to generalize to unseen samples.
Compressed Communication for Distributed Training: Adaptive Methods and System
Recently, there has been a growing interest in using gradient compression to reduce the communication overhead of the distributed training.
Deep Time Series Models for Scarce Data
Time series data have grown at an explosive rate in numerous domains and have stimulated a surge of time series modeling research.
Margin Preserving Self-paced Contrastive Learning Towards Domain Adaptation for Medical Image Segmentation
To bridge the gap between the source and target domains in unsupervised domain adaptation (UDA), the most common strategy puts focus on matching the marginal distributions in the feature space through adversarial learning.
Graph Representation Learning via Diversity-preserving Graph Refinement
For real-world graph data, the complex relationship between nodes is often represented as a hard binary link.
LID 2020: The Learning from Imperfect Data Challenge Results
The purpose of the Learning from Imperfect Data (LID) workshop is to inspire and facilitate the research in developing novel approaches that would harness the imperfect data and improve the data-efficiency during training.
Taking Modality-free Human Identification as Zero-shot Learning
There have been numerous methods proposed for human identification, such as face identification, person re-identification, and gait identification.
Dynamic Dispatching for Large-Scale Heterogeneous Fleet via Multi-agent Deep Reinforcement Learning
In this paper, we propose a novel Deep Reinforcement Learning approach to solve the dynamic dispatching problem in mining.
CSER: Communication-efficient SGD with Error Reset
The scalability of Distributed Stochastic Gradient Descent (SGD) is today limited by communication bottlenecks.
Accelerated Large Batch Optimization of BERT Pretraining in 54 minutes
Using the proposed LANS method and the learning rate scheme, we scaled up the mini-batch sizes to 96K and 33K in phases 1 and 2 of BERT pretraining, respectively.
Distribution-induced Bidirectional Generative Adversarial Network for Graph Representation Learning
Graph representation learning aims to encode all nodes of a graph into low-dimensional vectors that will serve as input of many compute vision tasks.
Convolutional Prototype Learning for Zero-Shot Recognition
The key to ZSL is to transfer knowledge from the seen to the unseen classes via auxiliary class attribute vectors.
Manufacturing Dispatching using Reinforcement and Transfer Learning
To address this, we enhance our deep RL model with an approach for dispatching policy transfer.
Generative Adversarial Networks for Failure Prediction
GAN-FP first utilizes two GAN networks to simultaneously generate training samples and build an inference network that can be used to predict failures for new samples.
Edge Heuristic GAN for Non-uniform Blind Deblurring
Non-uniform blur, mainly caused by camera shake and motions of multiple objects, is one of the most common causes of image quality degradation.
GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing
We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating).
Communication-Efficient Distributed Blockwise Momentum SGD with Error-Feedback
In particular, on distributed ResNet training with 7 workers on the ImageNet, the proposed algorithm achieves the same testing accuracy as momentum SGD using full-precision gradients, but with $46\%$ less wall clock time.
Blockwise Adaptivity: Faster Training and Better Generalization in Deep Learning
Stochastic methods with coordinate-wise adaptive stepsize (such as RMSprop and Adam) have been widely used in training deep neural networks.
Remaining Useful Life Estimation Using Functional Data Analysis
In this work, we propose a novel Functional Data Analysis (FDA) method called functional Multilayer Perceptron (functional MLP) for RUL estimation.
Give me a hint! Navigating Image Databases using Human-in-the-loop Feedback
In this paper, we introduce an attribute-based interactive image search which can leverage human-in-the-loop feedback to iteratively refine image search results.
ModaNet: A Large-Scale Street Fashion Dataset with Polygon Annotations
Understanding clothes from a single image has strong commercial and cultural impacts on modern societies.
Lightweight Stochastic Optimization for Minimizing Finite Sums with Infinite Data
The memory cost of SSAG does not depend on the sample size, while that of S-SAGA is the same as those of variance reduction methods on un- perturbed data.
Regularized Singular Value Decomposition and Application to Recommender System
Singular value decomposition (SVD) is the mathematical basis of principal component analysis (PCA).
Minimal Support Vector Machine
Support Vector Machine (SVM) is an efficient classification approach, which finds a hyperplane to separate data from different classes.
Fast End-to-End Trainable Guided Filter
To address the problem, we present a novel building block for FCNs, namely guided filtering layer, which is designed for efficiently generating a high-resolution output given the corresponding low-resolution one and a high-resolution guidance map.
Conditional Image-Text Embedding Networks
This paper presents an approach for grounding phrases in images which jointly learns multiple text-conditioned embeddings in a single end-to-end model.
Follow the Moving Leader in Deep Learning
Deep networks are highly nonlinear and difficult to optimize.
GP-GAN: Towards Realistic High-Resolution Image Blending
Concretely, we propose Gaussian-Poisson Equation to formulate the high-resolution image blending problem, which is a joint optimization constrained by the gradient and color information.
Conditional Image Generation
Vocal Bursts Intensity Prediction
A Projected Gradient Descent Method for CRF Inference allowing End-To-End Training of Arbitrary Pairwise Potentials
It is empirically demonstrated that such learned potentials can improve segmentation accuracy and that certain label class interactions are indeed better modelled by a non-Gaussian potential.
Kernel Alignment Inspired Linear Discriminant Analysis
The problem is to find a subspace to maximize the alignment between subspace-transformed data kernel and class indicator kernel.
A Harmonic Mean Linear Discriminant Analysis for Robust Image Classification
In null space based LDA (NLDA), a well-known LDA extension, between-class distance is maximized in the null space of the within-class scatter matrix.
A Closed Form Solution to Multi-View Low-Rank Regression
Real life data often includes information from different channels.
Fully-Trainable Deep Matching
Deep Matching (DM) is a popular high-quality method for quasi-dense image matching.
Accelerating Deep Learning with Shrinkage and Recall
Deep Learning is a very powerful machine learning model.
Stochastic Variance-Reduced ADMM
The alternating direction method of multipliers (ADMM) is a powerful optimization solver in machine learning.
Fast Nonsmooth Regularized Risk Minimization with Continuation
In regularized risk minimization, the associated optimization problem becomes particularly difficult when both the loss and regularizer are nonsmooth.
Higher Order Conditional Random Fields in Deep Neural Networks
Recent deep learning approaches have incorporated CRFs into Convolutional Neural Networks (CNNs), with some even training the CRF end-to-end with the rest of the network.
Ranked #55 on
Semantic Segmentation
on PASCAL Context
Joint Training of Generic CNN-CRF Models with Stochastic Optimization
We propose a new CNN-CRF end-to-end learning framework, which is based on joint stochastic optimization with respect to both Convolutional Neural Network (CNN) and Conditional Random Field (CRF) parameters.
Asynchronous Distributed Semi-Stochastic Gradient Optimization
With the recent proliferation of large-scale learning problems, there have been a lot of interest on distributed machine learning algorithms, particularly those that are based on stochastic gradient descent (SGD) and its variants.
Conditional Random Fields as Recurrent Neural Networks
Pixel-level labelling tasks, such as semantic segmentation, play a central role in image understanding.
Ranked #36 on
Semantic Segmentation
on PASCAL VOC 2012 test
Dense Semantic Image Segmentation with Objects and Attributes
The concepts of objects and attributes are both important for describing images precisely, since verbal descriptions often contain both adjectives and nouns (e. g. "I see a shiny red chair').
ImageSpirit: Verbal Guided Image Parsing
This allows us to formulate the image parsing problem as one of jointly estimating per-pixel object and attribute labels from a set of training images.
