Search Results for author:
Found 20 papers, 11 papers with code
Compress Polyphone Pronunciation Prediction Model with Shared Labels
In contrast to existing quantization with low precision data format and projection layer, we propose a novel method based on shared labels, which focuses on compressing the fully-connected layer before Softmax for models with a huge number of labels in TTS polyphone selection.
Point-to-Box Network for Accurate Object Detection via Single Point Supervision
However, the performance gap between point supervised object detection (PSOD) and bounding box supervised detection remains large.
Robust Medical Image Classification from Noisy Labeled Data with Global and Local Representation Guided Co-training
In this paper, we propose a novel collaborative training paradigm with global and local representation learning for robust medical image classification from noisy-labeled data to combat the lack of high quality annotated medical data.
Acknowledging the Unknown for Multi-label Learning with Single Positive Labels
Due to the difficulty of collecting exhaustive multi-label annotations, multi-label datasets often contain partial labels.
Object Localization under Single Coarse Point Supervision
In this study, we propose a POL method using coarse point annotations, relaxing the supervision signals from accurate key points to freely spotted points.
Foresee then Evaluate: Decomposing Value Estimation with Latent Future Prediction
Value function is the central notion of Reinforcement Learning (RL).
Improving Graph Representation Learning by Contrastive Regularization
Graph representation learning is an important task with applications in various areas such as online social networks, e-commerce networks, WWW, and semantic webs.
Unsupervised Curriculum Domain Adaptation for No-Reference Video Quality Assessment
From this adaptation, we split the data in target domain into confident and uncertain subdomains using the proposed uncertainty-based ranking function, through measuring their prediction confidences.
Noise against noise: stochastic label noise helps combat inherent label noise
The noise in stochastic gradient descent (SGD) provides a crucial implicit regularization effect, previously studied in optimization by analyzing the dynamics of parameter updates.
Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise
In this work, we present a theoretical hypothesis testing and prove that noise in real-world dataset is unlikely to be CCN, which confirms that label noise should depend on the instance and justifies the urgent need to go beyond the CCN assumption. The theoretical results motivate us to study the more general and practical-relevant instance-dependent noise (IDN).
Ranked #42 on
Image Classification
on Clothing1M
Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels
For validation, we prove that a noisy validation set is reliable, addressing the critical demand of model selection in scenarios like hyperparameter-tuning and early stopping.
Integrated Traffic Simulation-Prediction System using Neural Networks with Application to the Los Angeles International Airport Road Network
In this paper, we design an integrated simulation-prediction system which estimates the Origin-Destination (OD) matrix of a road network using only flow rate information and predicts the behavior of the road network in different simulation scenarios.
Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models
We introduce a new molecular dataset, named Alchemy, for developing machine learning models useful in chemistry and material science.
Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization
The IGNN model is based on an elegant and fundamental idea in information theory as explained in the main text, and it could be easily generalized beyond the contexts of molecular graphs considered in this work.
A Meta Approach to Defend Noisy Labels by the Manifold Regularizer PSDR
Most recent efforts have been devoted to defending noisy labels by discarding noisy samples from the training set or assigning weights to training samples, where the weight associated with a noisy sample is expected to be small.
Disentangling Dynamics and Returns: Value Function Decomposition with Future Prediction
Value functions are crucial for model-free Reinforcement Learning (RL) to obtain a policy implicitly or guide the policy updates.
Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks
Our work is based on an excellent idea that whitening the inputs of neural networks can achieve a fast convergence speed.
Understanding and Utilizing Deep Neural Networks Trained with Noisy Labels
Noisy labels are ubiquitous in real-world datasets, which poses a challenge for robustly training deep neural networks (DNNs) as DNNs usually have the high capacity to memorize the noisy labels.
Ranked #35 on
Image Classification
on mini WebVision 1.0
Log Hyperbolic Cosine Loss Improves Variational Auto-Encoder
In Variational Auto-Encoder (VAE), the default choice of reconstruction loss function between the decoded sample and the input is the squared $L_2$.
Understanding Convolution for Semantic Segmentation
This framework 1) effectively enlarges the receptive fields (RF) of the network to aggregate global information; 2) alleviates what we call the "gridding issue" caused by the standard dilated convolution operation.
Ranked #20 on
Semantic Segmentation
on PASCAL VOC 2012 test
