Nested Multiple Instance Learning with Attention Mechanisms

Fuster, Saul; Eftestøl, Trygve; Engan, Kjersti

doi:10.48550/arxiv.2111.00947

Cited by 2 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several MIL models using the attention mechanism have been proposed in order to enhance classification accuracy, examples of the models are the following: SA-AbMILP (Self-Attention Attention-based MIL Pooling) [34], ProtoMIL (Multiple Instance Learning with Prototypical Parts) [26], MHAttnSurv (Multi-Head Attention for Survival Prediction) [24], AbDMIL [23], MILL (Multiple Instance Learning-based Landslide classification) [35], DSMIL (Dual-Stream Multiple Instance Learning) [36]. The attentionbased MIL models can also be found in [21,22,27,37,38]. The main peculiarity of the above-mentioned models is that they use neural networks and mainly deal with image data rather than small tabular data.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Multiple Instance Learning with Trainable Soft Decision Tree Ensembles

2023

View full text Add to dashboard Cite

A new random forest-based model for solving the Multiple Instance Learning problem under small tabular data, called the Soft Tree Ensemble Multiple Instance Learning, is proposed. A new type of soft decision trees is considered, which is similar to the well-known soft oblique trees, but with a smaller number of trainable parameters. In order to train the trees, it is proposed to convert them into neural networks of a specific form, which approximate the tree functions. It is also proposed to aggregate the instance and bag embeddings (output vectors) by using the attention mechanism. The whole Soft Tree Ensemble Multiple Instance Learning model, including soft decision trees, neural networks, the attention mechanism and a classifier, is trained in an end-to-end manner. Numerical experiments with well-known real tabular datasets show that the proposed model can outperform many existing multiple instance learning models. A code implementing the model is publicly available.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Most of the above models use such methods as the support vector machine, K nearest neighbors, convolutional neural networks, and decision trees. An interesting and efficient class of the MIL models applies the attention mechanism [21][22][23][24][25][26][27].…”

Section: Introductionmentioning

confidence: 99%

Multiple Instance Learning with Trainable Soft Decision Tree Ensembles

2023

View full text Add to dashboard Cite

show abstract

“…They, for example, include DeepAttnMISL (Deep Attention Multiple Instance Survival Learning) [12], MHAttnSurv (Multi-Head Attention for Survival Prediction) [23], ProtoMIL (Multiple Instance Learning with Prototypical Parts) [22], SA-AbMILP (Self-Attention Attention-based MIL Pooling) [46], the loss-attention MIL (the instance weights are calculated based on the loss function) [24], DSMIL (Dual-stream Multiple Instance Learning) [27] MILL (Multiple Instance Learning-based Landslide classification) [25], AbDMIL [29]. There are other MIL methods using the attention mechanism, which can be found in [26,47,28]. The aforementioned methods propose approaches to enhance the MIL classification quality by using the attention.…”

Section: Related Workmentioning

confidence: 99%

“…Following this work, several methods of MIL based on the attention mechanism have been developed, including Deep Attention Multiple Instance Survival Learning [12], Pro-toMIL [22], MHAttnSurv [23], the loss-attention MIL [24], MILL [25]. There are other MIL methods using the attention mechanism, which can be found in [26,27,28]. An interesting method for applying attention to the MIL problem is provided by Ilse et al [29].…”

Section: Introductionmentioning

confidence: 99%

Multi-Attention Multiple Instance Learning

Konstantinov¹,

Utkin²

2021

Preprint

View full text Add to dashboard Cite

A new multi-attention based method for solving the MIL problem (MAMIL), which takes into account the neighboring patches or instances of each analyzed patch in a bag, is proposed. In the method, one of the attention modules takes into account adjacent patches or instances, several attention modules are used to get a diverse feature representation of patches, and one attention module is used to unite different feature representations to provide an accurate classification of each patch (instance) and the whole bag. Due to MAMIL, a combined representation of patches and their neighbors in the form of embeddings of a small dimensionality for simple classification is realized. Moreover, different types of patches are efficiently processed, and a diverse feature representation of patches in a bag by using several attention modules is implemented. A simple approach for explaining the classification predictions of patches is proposed. Numerical experiments with various datasets illustrate the proposed method.

show abstract

Nested Multiple Instance Learning with Attention Mechanisms

Cited by 2 publications

References 0 publications

Multiple Instance Learning with Trainable Soft Decision Tree Ensembles

Multiple Instance Learning with Trainable Soft Decision Tree Ensembles

Multi-Attention Multiple Instance Learning

Contact Info

Product

Resources

About