Enormous waves of technological innovations over the past several years, marked by the advances in AI technologies, are profoundly reshaping the industry and the society. However, down the road, a key challenge awaits us, that is, our capability of meeting rapidly-growing scenario-specific demands is severely limited by the cost of acquiring a commensurate amount of training data. This difficult situation is in essence due to limitations of the mainstream learning paradigm: we need to train a new model for each new scenario, based on a large quantity of well-annotated data and commonly from scratch. In tackling this fundamental problem, we move beyond and develop a new learning paradigm named INTERN. By learning with supervisory signals from multiple sources in multiple stages, the model being trained will develop strong generalizability. We evaluate our model on 26 well-known datasets that cover four categories of tasks in computer vision. In most cases, our models, adapted with only 10% of the training data in the target domain, outperform the counterparts trained with the full set of data, often by a significant margin. This is an important step towards a promising prospect where such a model with general vision capability can dramatically reduce our reliance on data, thus expediting the adoption of AI technologies. Furthermore, revolving around our new paradigm, we also introduce a new data system, a new architecture, and a new benchmark, which, together, form a general vision ecosystem to support its future development in an open and inclusive manner.

Stevens–Johnson syndrome/toxic epidermal necrolysis (SJS/TEN) is a life-threatening mucocutaneous disease that is predominantly drug-induced. Warfarin is the most commonly used drug for long-term anti-coagulant therapy; however, warfarin-induced SJS/TEN is seldom reported. In this study, we presented the case of a 61-year-old man who developed SJS after receiving multiple-drug therapy following aortic valve replacement surgery. The patient was diagnosed with drug-induced liver injury (DILI) based on significantly abnormal liver function test results. Warfarin was identified as the culprit drug using the algorithm of drug causality for epidermal necrolysis (ALDEN) score, enzyme-linked immunospot (ELISPOT) assay, and Roussel Uclaf Causality Assessment Method (RUCAM). After warfarin discontinuation and corticosteroid therapy, the lesions and liver function test findings improved. Human leukocyte antigen typing was conducted to detect the risk allele. To our knowledge, this is the first reported case of warfarin-induced SJS/TEN with DILI. This case suggests that commonly used and safe pharmaceutical agents such as warfarin can potentially cause serious adverse events, including SJS/TEN and DILI. The application of ALDEN, the ELISPOT assay, and RUCAM could be useful in identifying culprit drugs.

No abstract

No abstract