Why DFW?

With recent advancements in deep learning, the capabilities of automatic face recognition have been significantly increased. However, face recognition in an unconstrained environment with non-cooperative users is still a research challenge, pertinent for users such as law enforcement agencies. While several covariates such as pose, expression, illumination, aging, and low resolution have received significant attention, “disguise” is still considered an arduous covariate of face recognition.

DFW Competition and Workshop 2019 will be held with ICCV 2019 : Call for Competition | Call for Papers

As shown in the figure below, disguise as a covariate involves both intentional and unintentional changes on a face through which one can either obfuscate his/her identity or impersonate someone else’s identity. The problem can be further exacerbated due to an unconstrained environment or “in the wild” scenarios. However, disguise in the wild has not been studied in a comprehensive way, primarily due to unavailability of such a database.

Guess Who the Real Lady Gaga is:

Is this Neil Patrick Harris?

As part of this workshop, we will conduct a competition in which participants will be asked to show their results on the proposed disguised faces in the wild (DFW) database. Top performing algorithms will be invited to submit their papers in the workshop and selected papers will be invited for presentation. Authors who have not participated in the competition can also submit the paper.

We invite researchers to participate in the Disguised Faces in the Wild competition and workshop@ICCV2019!
Call for Competition (DFW@ICCV2019)
Call for Papers (DFW@ICCV2019)


Face recognition with disguise variations
Methods for impersonating identities using disguise
Methods for detecting disguise variations
Face recognition with makeup variations
Recognizing partially occluded faces