A Robust Distance with Correlated Metric Learning for Multi-Instance Multi-Label Data
Citations
24 citations
Cites background from "A Robust Distance with Correlated M..."
...In [37], a novel metric learning framework was presented to integrate class-specific distance metrics and explicitly take into account inter-class correlations for multi-label prediction....
[...]
15 citations
7 citations
5 citations
Cites background from "A Robust Distance with Correlated M..."
...In order to properly classify the bags, several distance measures including bag to bag, class to bag or bag to class (Verma and Jawahar, 2016) are introduced....
[...]
References
4,433 citations
4,157 citations
"A Robust Distance with Correlated M..." refers background or methods in this paper
...We optimize OP1 in the primal form itself using a batch gradient-descent and projection method similar to [18]....
[...]
..., L}, we follow the approach of metric learning using pair-wise comparisons [18, 4, 5, 13]....
[...]
...While metric learning for single-instance data (single-label [5, 4, 18] or multi-label [7, 13]) is a well-studied topic, there have been few attempts that perform metric learning for multiinstance data....
[...]
2,767 citations
"A Robust Distance with Correlated M..." refers background in this paper
...Whereas, in case of multi-label data where each bag may be labeled with one or more classes, there may be an overlap among different super-bags; i.e., (i) ∑|D| j=1 nj ≤ ∑L l=1ml, and (ii) |Ug ∩ Uh| ≥ 0, ∀ g 6= h. Based on this, now we present the RB2C-distance for MIL....
[...]
...And third, by the definition of MIL, an object bag is assigned to a class if at least one of its instances belongs to that class....
[...]
...This demonstrates the effectiveness of this classical MIL method, and also reflects the need of revisiting such methods for developing better methods....
[...]
...Under the MIL setting, for a given bag Xi, if ∃j ∈ {1, . . . , ni} such that the instance xij belongs to the lth class (1 ≤ l ≤ L), then the whole bag Xi belongs to the lth class and yi(l) = 1; otherwise yi(l) = 0....
[...]
...Multiple Instance Learning (MIL) [2] is a machine learning paradigm that has lately achieved significant attention [17, 8, 10, 11, 1, 19, 14, 16, 15]....
[...]
1,765 citations
"A Robust Distance with Correlated M..." refers methods in this paper
...We use two popular multi-instance multi-label datasets Corel-5K [3] and IAPR TC-12 [6]....
[...]
...Here, µ is set to be the (rounded) average number of classes per bag in training data (µ = 2 for Corel-5K dataset, and µ = 3 for IAPR TC-12 dataset)....
[...]
...Corel-5K dataset consists of 4500 training images, 500 testing images, and a vocabulary of 260 classes....
[...]
...To validate our approach, we extensively experiment on two popular multi-label datasets: Corel-5K [3] and IAPR TC-12 [6]....
[...]
...For RB2C and its variants, we keep K1 = 5 and K2 = 8 for Corel-5K dataset, and K1 = 10 and K2 = 4 for IAPR TC-12 dataset....
[...]
1,048 citations
"A Robust Distance with Correlated M..." refers background in this paper
...We define the correlation between k and l class as [12]:...
[...]