A Note on Learning from Multiple-Instance Examples

By Avrim Blum, Adam Tauman Kalai. 2004

114 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning Theory for Distribution Regression (2014, methodology): ““Bag-of-objects” methods (MIL, classification): Despite the large number of MIL applications and the spate of heuristic solution techniques, there exist few theoretical results in the area (Auer, 1998; Long and Tan, 1998; Blum and Kalai, 1998; Babenko et al., 2011; Zhang et al., 2013; Sabato and Tis”
Distribution Kernel Methods for Multiple-Instance Learning (2013, background): “Other existing work describes when instance or bag concepts are learnable in the probably approximately correct (PAC) framework from MI data using instance classifiers (Auer, Long, and Srinivasan 1997; Blum and Kalai 1998; Sabato and Tishby 2012).”
Multi-instance clustering with applications to multi-instance prediction (2009, background): “Blum and Kalai [12] described a reduction from PAC-learning under the multi-instance learning framework to PAC-learning with one-sided or two-sided random classification noise.”
Supervised Learning of Semantic Classes for Image Annotation and Retrieval (2007, methodology): “We approach this question from a multiple instance learning perspective [2], [10], [20], [27], [28].”
Learning Neural Networks with Two Nonlinear Layers in Polynomial Time (2017, background): “lts for concrete schemes that do not rely on unproven assumptions. Comparison to Previous Work. Under the standard MI assumption, various results are known in the PAC learning setting. Blum and Kalai [BK98] showed a simple reduction from PAC learning MIL to PAC learning with one-sided noise under th”
Multi-instance learning with any hypothesis class (2011, methodology): “Identifying these cases and providing tighter analysis for them is an important topic for future work.”
Graph Convolutional Label Noise Cleaner: Train a Plug-And-Play Action Classifier for Anomaly Detection (2019, background): “…that the label Y = 0 is noiseless, since it means all snippets v i in the video V are normal: However, Y = 1 is noisy because in this case the video V is partially made up of anomalous clips: This is referred to as one-sided label noise [7, 9, 55], for the noise only appears along with Y = 1 .”
Multiple Instance Learning: Algorithms and Applications (2008, background): “Recall from Section 2.3 that the best known sample complexity bound for MIL is ˜ O ( d 2 m/ 2 ) [15].”
Multi-Instance Learning : A Survey (2004, background): “Unsupervised learning attempts to learn the structure of the underlying sources of instances, where the training instances are without known labels and therefore the ambiguity is the maximum.”
Multiple-Instance Learning of Real-Valued Data (2001, background): “There has also been some nice theoretical work on learning the multiple-instance concept class of axis-aligned boxes in n-dimensional space (Long and Tan, 1998; Auer et al., 1997; Blum and Kalai, 1998).”
MILES: Multiple-Instance Learning via Embedded Instance Selection (2006, methodology): “Anumber of theoretical results have been obtained following the APR framework [4], [10], [33].”
A brief introduction to weakly supervised learning (2018, background): “Earlytheoreticalresults[64–66]showthatmulti-instancelearningishardfor heterogeneous cases in which each instance in the bag is classified by a dif-ferentrule,whileitislearnablefor homogeneous cases in which all instances are classified by the same rule.”
Multi-instance multi-label learning (2008, background): “Blum and Kalai [10] described a reduction from Pac-learning under the multi-instance learning framework to Pac-learning with one-sided random classification noise.”
Image Categorization by Learning and Reasoning with Regions (2004, background): “This is in essence identical to the Multiple-Instance Learning (MIL) setting (Dietterich et al., 1997; Blum and Kalai, 1998; Maron and Lozano-Pérez, 1998; Zhang and Goldman, 2002) where images and regions are respectively called bags and instances.”
Multiple Instance Learning with Manifold Bags (2011, methodology): “For example, Blum & Kalai (1998) showed that if one has access to a noise tolerant learner and the bags are formed by drawing r independent samples from a fixed distribution over I, then the sample complexity grows linearly with r. Recently, Sabato & Tishby (2009) showed that if one can minimize…”
A Multiple Instance Learning Strategy for Combating Good Word Attacks on Spam Filters (2008, background): “Finally, we conclude our work and discuss future directions.”