Related papers: Learnable Tree Filter for Structure-preserving Fea…

Transfer learning makes it possible to use large vision networks on a variety of domains, by specializing their models' general filters to new tasks. However, these networks assume the input images to have 3 input channels, making them…

Decision trees are well-known due to their ease of interpretability. To improve accuracy, we need to grow deep trees or ensembles of trees. These are hard to interpret, offsetting their original benefits. Shapley values have recently become…

Recent advances in unsupervised domain adaptation have shown the effectiveness of adversarial training to adapt features across domains, endowing neural networks with the capability of being tested on a target domain without requiring any…

Image segmentation is often ambiguous at the level of individual image patches and requires contextual information to reach label consensus. In this paper we introduce Segmenter, a transformer model for semantic segmentation. In contrast to…

Learning representation for source code is a foundation of many program analysis tasks. In recent years, neural networks have already shown success in this area, but most existing models did not make full use of the unique structural…

We are proposing an extension of the recursive neural network that makes use of a variant of the long short-term memory architecture. The extension allows information low in parse trees to be stored in a memory register (the `memory cell')…

Decision tree ensembles are widely used and competitive learning models. Despite their success, popular toolkits for learning tree ensembles have limited modeling capabilities. For instance, these toolkits support a limited number of loss…

Decision trees and random forest remain highly competitive for classification on medium-sized, standard datasets due to their robustness, minimal preprocessing requirements, and interpretability. However, a single tree suffers from high…

In many modern applications, including analysis of gene expression and text documents, the data are noisy, high-dimensional, and unordered--with no particular meaning to the given order of the variables. Yet, successful learning is often…

It is important to extract good features using an encoder to realize semantic segmentation with high accuracy. Although loss function is optimized in training deep neural network, far layers from the layers for computing loss function are…

Compared with expensive pixel-wise annotations, image-level labels make it possible to learn semantic segmentation in a weakly-supervised manner. Within this pipeline, the class activation map (CAM) is obtained and further processed to…

Neural networks with tree-based sentence encoders have shown better results on many downstream tasks. Most of existing tree-based encoders adopt syntactic parsing trees as the explicit structure prior. To study the effectiveness of…

Tree-like structures, such as blood vessels, often express complexity at very fine scales, requiring high-resolution grids to adequately describe their shape. Such sparse morphology can alternately be represented by locations of centreline…

The problem of feature selection has raised considerable interests in the past decade. Traditional unsupervised methods select the features which can faithfully preserve the intrinsic structures of data, where the intrinsic structures are…

This paper introduces Tree-NET, a novel framework for medical image segmentation that leverages bottleneck feature supervision to enhance both segmentation accuracy and computational efficiency. While previous studies have employed…

Contextual information is crucial for semantic segmentation. However, finding the optimal trade-off between keeping desired fine details and at the same time providing sufficiently large receptive fields is non trivial. This is even more…

We present a system for bottom-up cumulative learning of myriad concepts corresponding to meaningful character strings, and their part-related and prediction edges. The learning is self-supervised in that the concepts discovered are used as…

Aerial image segmentation is the basis for applications such as automatically creating maps or tracking deforestation. In true orthophotos, which are often used in these applications, many objects and regions can be approximated well by…

This paper addresses the issues of parameter redundancy, rigid structure, and limited task adaptability in the fine-tuning of large language models. It proposes an adapter-based fine-tuning method built on a structure-learnable mechanism.…

Fixed effects models are very flexible because they do not make assumptions on the distribution of effects and can also be used if the heterogeneity component is correlated with explanatory variables. A disadvantage is the large number of…