Search Results for author:
Found 19 papers, 5 papers with code
Propagation Modeling for Physically Large Arrays: Measurements and Multipath Component Visibility
Based on a geometric model of the measurement environment, we analyze the visibility of specular components.
Doubly Stochastic Models: Learning with Unbiased Label Noises and Inference Stability
While previous studies primarily focus on the affects of label noises to the performance of learning, our work intends to investigate the implicit regularization effects of the label noises, under mini-batch sampling settings of stochastic gradient descent (SGD), with assumptions that label noises are unbiased.
Learning from Training Dynamics: Identifying Mislabeled Data Beyond Manually Designed Features
While mislabeled or ambiguously-labeled samples in the training set could negatively affect the performance of deep models, diagnosing the dataset and identifying mislabeled samples helps to improve the generalization power.
High-Resolution Channel Sounding and Parameter Estimation in Multi-Site Cellular Networks
Accurate understanding of electromagnetic propagation properties in real environments is necessary for efficient design and deployment of cellular systems.
$\textbf{P$^2$A}$: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos
While deep learning has been widely used for video analytics, such as video classification and action detection, dense action detection with fast-moving subjects from sports videos is still challenging.
Distilling Ensemble of Explanations for Weakly-Supervised Pre-Training of Image Segmentation Models
Though image classification datasets could provide the backbone networks with rich visual features and discriminative ability, they are incapable of fully pre-training the target model (i. e., backbone+segmentation modules) in an end-to-end manner.
Cross-Model Consensus of Explanations and Beyond for Image Classification Models: An Empirical Study
Existing interpretation algorithms have found that, even deep models make the same and right predictions on the same image, they might rely on different sets of input features for classification.
Practical Assessment of Generalization Performance Robustness for Deep Networks via Contrastive Examples
Incorporating with a set of randomized strategies for well-designed data transformations over the training set, ContRE adopts classification errors and Fisher ratios on the generated contrastive examples to assess and analyze the generalization performance of deep models in complement with a testing set.
From Distributed Machine Learning to Federated Learning: A Survey
Because of laws or regulations, the distributed data and computing resources cannot be directly shared among different regions or organizations for machine learning tasks.
Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond
Then, to understand the interpretation results, we also survey the performance metrics for evaluating interpretation algorithms.
Implicit Regularization Effects of Unbiased Random Label Noises with SGD
Random label noises (or observational noises) widely exist in practical machinelearning settings.
Can We Use Gradient Norm as a Measure of Generalization Error for Model Selection in Practice?
The recent theoretical investigation (Li et al., 2020) on the upper bound of generalization error of deep neural networks (DNNs) demonstrates the potential of using the gradient norm as a measure that complements validation accuracy for model selection in practice.
Democratizing Evaluation of Deep Model Interpretability through Consensus
Given any task/dataset, Consensus first obtains the interpretation results using existing tools, e. g., LIME (Ribeiro et al., 2016), for every model in the committee, then aggregates the results from the entire committee and approximates the “ground truth” of interpretations through voting.
Towards Accurate Knowledge Transfer via Target-awareness Representation Disentanglement
Fine-tuning deep neural networks pre-trained on large scale datasets is one of the most practical transfer learning paradigm given limited quantity of training samples.
Representation Transfer by Optimal Transport
We use optimal transport to quantify the match between two representations, yielding a distance that embeds some invariances inherent to the representation of deep networks.
Cross-Task Transfer for Geotagged Audiovisual Aerial Scene Recognition
With the help of this dataset, we evaluate three proposed approaches for transferring the sound event knowledge to the aerial scene recognition task in a multimodal learning framework, and show the benefit of exploiting the audio information for the aerial scene recognition.
Explicit Inductive Bias for Transfer Learning with Convolutional Networks
In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch.
Explicit Induction Bias for Transfer Learning with Convolutional Networks
In inductive transfer learning, fine-tuning pre-trained convolutional networks substantially outperforms training from scratch.
Deep Convolutional Neural Networks for Massive MIMO Fingerprint-Based Positioning
This paper provides an initial investigation on the application of convolutional neural networks (CNNs) for fingerprint-based positioning using measured massive MIMO channels.
