Related papers: Neural Passage Quality Estimation for Static Pruni…

Pruning provides a practical solution to reduce the resources required to run large language models (LLMs) to benefit from their effective capabilities as well as control their cost for training and inference. Research on LLM pruning often…

The article presents an online relevancy tuning method using explicit user feedback. The author developed and tested a method of words' weights modification based on search result evaluation by user. User decides whether the result is…

This paper describes our submission to the shared task on word/phrase level Quality Estimation (QE) in the First Conference on Statistical Machine Translation (WMT16). The objective of the shared task was to predict if the given word/phrase…

Neural architecture search (NAS) remains a challenging problem, which is attributed to the indispensable and time-consuming component of performance estimation (PE). In this paper, we provide a novel yet systematic rethinking of PE in a…

Instance segmentation with neural networks is an essential task in environment perception. In many works, it has been observed that neural networks can predict false positive instances with high confidence values and true positives with low…

Vision Transformer and its variants have been adopted in many visual tasks due to their powerful capabilities, which also bring significant challenges in computation and storage. Consequently, researchers have introduced various compression…

To solve ever more complex problems, Deep Neural Networks are scaled to billions of parameters, leading to huge computational costs. An effective approach to reduce computational requirements and increase efficiency is to prune unnecessary…

This paper presents an efficient technique to prune deep and/or wide convolutional neural network models by eliminating redundant features (or filters). Previous studies have shown that over-sized deep neural network models tend to produce…

Network pruning can significantly reduce the computation and memory footprint of large neural networks. To achieve a good trade-off between model size and performance, popular pruning techniques usually rely on hand-crafted heuristics and…

Invariance describes transformations that do not alter data's underlying semantics. Neural networks that preserve natural invariance capture good inductive biases and achieve superior performance. Hence, modern networks are handcrafted to…

Filter pruning is effective to reduce the computational costs of neural networks. Existing methods show that updating the previous pruned filter would enable large model capacity and achieve better performance. However, during the iterative…

This paper explores the use of Deep Learning methods for automatic estimation of quality of human translations. Automatic estimation can provide useful feedback for translation teaching, examination and quality control. Conventional methods…

Image restoration tasks have achieved tremendous performance improvements with the rapid advancement of deep neural networks. However, most prevalent deep learning models perform inference statically, ignoring that different images have…

Network pruning is an important research field aiming at reducing computational costs of neural networks. Conventional approaches follow a fixed paradigm which first trains a large and redundant network, and then determines which units…

Most existing channel pruning methods formulate the pruning task from a perspective of inefficiency reduction which iteratively rank and remove the least important filters, or find the set of filters that minimizes some reconstruction…

Structured pruning is a popular method to reduce the cost of convolutional neural networks, that are the state of the art in many computer vision tasks. However, depending on the architecture, pruning introduces dimensional discrepancies…

There is an ongoing effort to develop feature selection algorithms to improve interpretability, reduce computational resources, and minimize overfitting in predictive models. Neural networks stand out as architectures on which to build…

Deep neural networks (DNNs) have become ubiquitous thanks to their remarkable ability to model complex patterns across various domains such as computer vision, speech recognition, robotics, etc. While large DNN models are often more…

Relevance feedback techniques assume that users provide relevance judgments for the top k (usually 10) documents and then re-rank using a new query model based on those judgments. Even though this is effective, there has been little…

Pruning at initialization (PaI) reduces training costs by removing weights before training, which becomes increasingly crucial with the growing network size. However, current PaI methods still have a large accuracy gap with iterative…