Search for: All records

FSS (Few-shot segmentation) aims to segment a target class using a small number of labeled images (support set). To extract information relevant to the target class, a dominant approach in best performing FSS methods removes background features using a support mask. We observe that this feature excision through a limiting support mask introduces an information bottleneck in several challenging FSS cases, e.g., for small targets and/or inaccurate target boundaries. To this end, we present a novel method (MSI), which maximizes the support-set information by exploiting two complementary sources of features to generate super correlation maps. We validate the effectiveness of our approach by instantiating it into three recent and strong FSS methods. Experimental results on several publicly available FSS benchmarks show that our proposed method consistently improves performance by visible margins and leads to faster convergence. Our code and trained models are available at: https://github.com/moonsh/MSI-Maximize-Support-Set-Information 

Computational emotion, is naturally predicated on an operating theory of emotion. This paper seeks to explore the prevalence of three different approaches in the literature, namely basic emotion, dimensional emotion, and constructed emotion. Basic emotion maintains that there exists a discrete set of primitive emotions evolved as responses to certain stimuli; dimensional emotion sees different emotions as systematically related by two or more dimensions (typically valence and arousal); and constructed emotion describes emotional experience as a function of the brain’s general predictive faculties applied to learned social concepts of different emotions. In order to see how these approaches are represented in affective computing literature, we conduct a systematic survey spanning the IEEE, ACM, ScienceDirect, and Engineering Village databases. Out of 204 selected papers, 151 apply basic emotion theory, 48 apply dimensional emotion, and 5 apply constructed emotion. We find promising representation of the constructed emotion theory in the affective computing literature and conclude that it provides a theoretical basis worth pursuing for affective engagement human computer interaction (HCI) applications.