paper-with-me

홈 › Papers

Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning

2023-09-21 · NeurIPS 2023 11

In many real-world tasks, the concerned objects can be represented as a multi-instance bag associated with a candidate label set, which consists of one ground-truth label and several false positive labels. Multi-instance partial-label learning (MIPL) is a learning paradigm to deal with such tasks and has achieved favorable performances. Existing MIPL approach follows the instance-space paradigm by assigning augmented candidate label sets of bags to each instance and aggregating bag-level labels from instance-level labels. However, this scheme may be suboptimal as global bag-level information is ignored and the predicted labels of bags are sensitive to predictions of negative instances. In this paper, we study an alternative scheme where a multi-instance bag is embedded into a single vector representation. Accordingly, an intuitive algorithm named DEMIPL, i.e., Disambiguated attention Embedding for Multi-Instance Partial-Label learning, is proposed. DEMIPL employs a disambiguation attention mechanism to aggregate a multi-instance bag into a single vector representation, followed by a momentum-based disambiguation strategy to identify the ground-truth label from the candidate label set. Furthermore, we introduce a real-world MIPL dataset for colorectal cancer classification. Experimental results on benchmark and real-world datasets validate the superiority of DEMIPL against the compared MIPL and partial-label learning approaches.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Adversarial Partial Multi-Label Learning

2019-09-15 · Yan Yan, Yuhong Guo

Partial multi-label learning (PML), which tackles the problem of learning multi-label prediction models from instances with overcomplete noisy annotations, has recently started gaining attention from the research communi…

DecoderGenerative Adversarial NetworkMulti-Label Learning

Adversarial Paritial Multi-label Learning

2020-01-01 · ICLR 2020 1 · Yan Yan, Yuhong Guo

Partial multi-label learning (PML), which tackles the problem of learning multi-label prediction models from instances with overcomplete noisy annotations, has recently started gaining attention from the research communi…

DecoderGenerative Adversarial NetworkMulti-Label Learning

Disambiguated skip-gram model

2018-10-01 · EMNLP 2018 10 · Karol Grzegorczyk, Marcin Kurdziel

We present disambiguated skip-gram: a neural-probabilistic model for learning multi-sense distributed representations of words. Disambiguated skip-gram jointly estimates a skip-gram-like context word prediction model and…

Image CaptioningmodelWord EmbeddingsWord Sense Disambiguation+1

Candidate-aware Selective Disambiguation Based On Normalized Entropy for Instance-dependent Partial-label Learning

2023-01-01 · ICCV 2023 1 · Shuo He, Guowu Yang, Lei Feng

In partial-label learning (PLL), each training example has a set of candidate labels, among which only one is the true label. Most existing PLL studies focus on the instance-independent (II) case, where the generatio…

Partial Label Learning

Multi-Instance Partial-Label Learning: Towards Exploiting Dual Inexact Supervision

2022-12-18 · Wei Tang, Weijia Zhang, Min-Ling Zhang

Weakly supervised machine learning algorithms are able to learn from ambiguous samples or labels, e.g., multi-instance learning or partial-label learning. However, in some real-world tasks, each training sample is associ…

Gaussian ProcessesPartial Label Learning