Hybrid Knowledge Routed Modules for Large-scale Object Detection

Neural Information Processing Systems

Abstract The dominant object detection approaches treat the recognition of each region separately and overlook crucial semantic correlations between objects in one scene. This paradigm leads to substantial performance drop when facing heavy long-tail problems, where very few samples are available for rare classes and plenty of confusing categories exists. We exploit diverse human commonsense knowledge for reasoning over large-scale object categories and reaching semantic coherency within one image. Particularly, we present Hybrid Knowledge Routed Modules (HKRM) that incorporates the reasoning routed by two kinds of knowledge forms: an explicit knowledge module for structured constraints that are summarized with linguistic knowledge (e.g. shared attributes, relationships) about concepts; and an implicit knowledge module that depicts some implicit constraints (e.g. common spatial layouts). By functioning over a region-to-region graph, both modules can be individualized and adapted to coordinate with visual patterns in each image, guided by specific knowledge forms. HKRM are light-weight, general-purpose and extensible by easily incorporating multiple knowledge to endow any detection networks the ability of global semantic reasoning. Experiments on large-scale object detection benchmarks show HKRM obtains around 34.5% improvement on VisualGenome (1000 categories) and 30.4% on ADE in terms of mAP.

Report on the First International Conference on Knowledge Capture (K-CAP)

AI Magazine

The International Conference on Knowledge Capture (K-CAP) is a new forum for multidisciplinary research on capturing knowledge from a variety of sources and creating representations that are useful for reasoning. This article describes the first conference series, held in October 2001, and presents an invitation to the AI community to participate in K-CAP 2003.

Shifting toward the Knowledge Economy

Huffington Post - Tech news and opinion

However, the sheer magnitude and speed of these changes, as well as the inevitable displacement brought by greater automation and ongoing challenges such as uneven Internet connectivity in developing economies, run the risk of increasing the divide between those able to access, effectively use, and benefit from technology and knowledge, and those trying to catch up. After all, in addition to greater access to knowledge, it is the ability of enterprises, industries, governments, and individuals to effectively adopt and apply this knowledge, data, and technology that results in tangible economic and societal gains. And, some countries have economic foundations, infrastructure, and innovation ecosystems that are more conducive to embracing and supporting such changes.

Developing and Deploying Knowledge on a Global Scale

AI Magazine

To enhance the quality and consistency of its customer- support organization, Reuters embarked on a global knowledge development and reuse project. The system supports 38 Reuter products worldwide. This article presents a case study of Reuter experience in putting a global knowledge organization in place, building knowledge bases at multiple distributed sites, deploying these knowledge bases in multiple sites around the world, and maintaining and enhancing knowledge bases within a global organizational framework. This project is the first to address issues in multicountry knowledge development and maintenance and multicountry knowledge deployment.