Related papers: Data Interpolating Prediction: Alternative Interpr…
We present Diffusion Model Patching (DMP), a simple method to boost the performance of pre-trained diffusion models that have already reached convergence, with a negligible increase in parameters. DMP inserts a small, learnable set of…
To improve the predictability of complex computational models in the experimentally-unknown domains, we propose a Bayesian statistical machine learning framework utilizing the Dirichlet distribution that combines results of several…
The Mixture of Experts architecture allows for outrageously large neural networks by scaling model parameter size independently from computational demand (FLOPs). However, current DNN frameworks cannot effectively support the dynamic data…
Data augmentation is a widely used technique and an essential ingredient in the recent advance in self-supervised representation learning. By preserving the similarity between augmented data, the resulting data representation can improve…
Deep networks have been revolutionary in improving performance of machine learning and artificial intelligence systems. Their high prediction accuracy, however, comes at a price of \emph{model irreproducibility\/} in very high levels that…
Respiratory sound classification plays a pivotal role in diagnosing respiratory diseases. While deep learning models have shown success with various respiratory sound datasets, our experiments indicate that models trained on one dataset…
Forecast combination integrates information from various sources by consolidating multiple forecast results from the target time series. Instead of the need to select a single optimal forecasting model, this paper introduces a deep learning…
In recent years, various deep learning techniques have been exploited in side channel attacks, with the anticipation of obtaining more appreciable attack results. Most of them concentrate on improving network architectures or putting…
Deep learning based methods have penetrated many image processing problems and become dominant solutions to these problems. A natural question raised here is "Is there any space for conventional methods on these problems?" In this paper,…
Imitation learning holds the promise of equipping robots with versatile skills by learning from expert demonstrations. However, policies trained on finite datasets often struggle to generalize beyond the training distribution. In this work,…
A multitude of classifiers can be trained on the same data to achieve similar performances during test time, while having learned significantly different classification patterns. This phenomenon, which we call prediction discrepancies, is…
Context: The effectiveness of data selection approaches in improving the performance of cross project defect prediction(CPDP) has been shown in multiple previous studies. Beside that, replication studies play an important role in the…
We consider lossless compression based on statistical data modeling followed by prediction-based encoding, where an accurate statistical model for the input data leads to substantial improvements in compression. We propose DZip, a…
Deep Neural Networks are well known for efficiently fitting training data, yet experiencing poor generalization capabilities whenever some kind of bias dominates over the actual task labels, resulting in models learning "shortcuts". In…
We investigate whether synthetic images generated by diffusion models can enhance multi-label classification of protein subcellular localization. Specifically, we implement a simplified class-conditional denoising diffusion probabilistic…
This paper shows that further evaluation metrics during model training are needed to decide about its applicability in inference. As an example, a LayoutLM-based model is trained for token classification in documents. The documents are…
There is growing interest in the challenging visual perception task of learning from long-tailed class distributions. The extreme class imbalance in the training dataset biases the model to prefer recognizing majority class data over…
Data augmentation methods have played an important role in the recent advance of deep learning models, and have become an indispensable component of state-of-the-art models in semi-supervised, self-supervised, and supervised training for…
Data Poisoning (DP) is an effective attack that causes trained classifiers to misclassify their inputs. DP attacks significantly degrade a classifier's accuracy by covertly injecting attack samples into the training set. Broadly applicable…
Knowledge transfer from a complex high performing model to a simpler and potentially low performing one in order to enhance its performance has been of great interest over the last few years as it finds applications in important problems…