Multiple instance learning for soft bags via top instances

Abstract

A generalized formulation of the multiple instance learning problem is considered. Under this formulation, both positive and negative bags are soft, in the sense that negative bags can also contain positive instances. This reflects a problem setting commonly found in practical applications, where labeling noise appears on both positive and negative training samples. A novel bag-level representation is introduced, using instances that are most likely to be positive (denoted top instances), and its ability to separate soft bags, depending on their relative composition in terms of positive and negative instances, is studied. This study inspires a new large-margin algorithm for soft-bag classification, based on a latent support vector machine that efficiently explores the combinatorial space of bag compositions. Empirical evaluation on three datasets is shown to confirm the main findings of the theoretical analysis and the effectiveness of the proposed soft-bag classifier.

WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation

“…The corresponding parameters are described in Table 1. The standard max-pooling MIL approach [44] is obtained with only one element, and both top instance model [39], Learning with Label Proportion [65] and global average pooling [70] can be obtained with more. Drawing from negative evidence [47,12,13] we can incorporate minimum scoring regions to support classification and our spatial pooling function can reduce to the kMax+kMin layer of [13].…”

“…Max pooling [44] only selects the most informative region for the MIL prediction. Recent alternatives include Global Average Pooling (GAP) [70], soft max in LSE pooling [58], Learning from Label Proportion (LLP) [65,36], and top max scoring [39]. Negative evidence models [47,12,13] explicitly select regions accounting for the absence of the class.…”

“…We propose a new pooling strategy (right of Figure 2) which generalizes several approaches in the literature, including (top) max pooling [44,39], global average pooling [70] or negative evidence models [47,12,13].…”

Convex formulation of multiple instance learning from positive and unlabeled bags

“…Positive and Negative set kernels [20] sMIL [24] KI-SVM [22] miGraph [25] MI-SVM [15] MissSVM [26] soft-bag SVM [10] dMIL [11] Positive and Unlabeled PU-SKC (Sect. 3) puMIL [27]…”

“…Later, MIL has been considered as a graph-based learning problem [2,3,4,5,6]. In fact, MIL is applicable to a wide range of real-world problems such as molecule behavior prediction [7], drug activity prediction [1], domain theory [8], content-based image retrieval [9,10,11], visual tracking [12], object detection [13,14], text categorization [15], and medical diagnosis [16,17].…”