Revisiting Multiple-Instance Learning Via Embedded Instance Selection
By James R. Foulds, Eibe Frank. 2008
147 citations recorded by the source corpus.
Subfields: Computer Vision and Pattern Recognition, Evaluation & Benchmarks
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Li Fei-Fei
- Luc Van Gool
- Dacheng Tao
- Chunhua Shen
- Trevor Darrell
- Cordelia Schmid
- Armand Joulin
- Xiaogang Wang
In Evaluation & Benchmarks
- Armand Joulin
- Yu-Feng Li
- Andrej Karpathy
- Li Fei-Fei
- Zhi-Hua Zhou
- Abhir H. Bhalerao
- Tomás Pevný
- Qiang Zhang
Citations in the corpus
- Deep Fragment Embeddings for Bidirectional Image Sentence Mapping (2014, methodology): “We now describe a Multiple Instance Learning (MIL) [38] extension of the objective C 0 that attempts to infer the latent alignment between fragments in corresponding image-sentence pairs.”
- Attention-based Deep Multiple Instance Learning (2018, neutral): “…et al., 2015b), embedding instances to a compact low-dimensional representation that is further fed to a bag-level classifier (Andrews et al., 2003; Chen et al., 2006), and combining responses of an instance-level classifier (Ramon & De Raedt, 2000; Raykar et al., 2008; Zhang et al., 2006).”
- Multiple instance classification: Review, taxonomy and comparative study (2013, methodology): “For the Musk1 , Musk2 , Text1 and Text2 databases, we used a ten-fold validation approach, as the majority of authors [1]: each round we take 90% of the data set for training and the remaining 10% for testing, and this is repeated ten times in order to test with all the bags.”
- Multi-instance learning by treating instances as non-I.I.D. samples (2008, methodology): “We use the same experimental routine as that described in [6].”
- Using Neural Network Formalism to Solve Multiple-Instance Problems (2016, methodology): “…NN ) [24]; bag-level paradigm: k -nearest neighbor with citation distance [21] using 5 nearest neighbors; and finally embedded-space paradigm: Miles [5] with Gaussian kernel, Bag dissimilarity [6] with minmin , meanmin , meanmean , Hausdorff , and Earth-moving distance (EMD), cov-coef [9] embedding…”
- Weakly-Supervised Evidence Pinpointing and Description (2017, methodology): “The evidence pinpointing task is reminiscent of the multiple-instance problem as described in [5] in which instances or features responsible for the classification are identified.”