Search Results for author: Josip Krapac

Found 5 papers, 2 papers with code

Task-Specific Embeddings for Ante-Hoc Explainable Text Classification

no code implementations30 Nov 2022 Kishaloy Halder, Josip Krapac, Alan Akbik, Anthony Brew, Matti Lyra

In a series of experiments, we show that this yields a number of interesting benefits: (1) The resulting order induced by distances in the embedding space can be used to directly explain classification decisions.

Classification Incremental Learning +2

Task-Aware Representation of Sentences for Generic Text Classification

1 code implementation COLING 2020 Kishaloy Halder, Alan Akbik, Josip Krapac, Roland Vollgraf

State-of-the-art approaches for text classification leverage a transformer architecture with a linear layer on top that outputs a class distribution for a given prediction problem.

Classification text-classification +2

Efficient Ladder-style DenseNets for Semantic Segmentation of Large Images

3 code implementations14 May 2019 Ivan Krešo, Josip Krapac, Siniša Šegvić

Recent progress of deep image classification models has provided great potential to improve state-of-the-art performance in related computer vision tasks.

Image Classification Semantic Segmentation

Read classification using semi-supervised deep learning

no code implementations23 Apr 2019 Tomislav Šebrek, Jan Tomljanović, Josip Krapac, Mile Šikić

In this paper, we propose a semi-supervised deep learning method for detecting the specific types of reads that impede the de novo genome assembly process.

Classification General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.