• December 1st, 2020: The TOP-3 winners announced.

• October 10th, 2020: The challenge has started.

• August 25th, 2020: Workshop deadlines have been announced.

• July 20th, 2020: The workshop home page is launched.

• July 20th, 2020: List of confirmed invited speakers is here. More to follow!

Fine-grained categorization (a.k.a. subordinate categorization) lies in the continuum between basic-level categorization (object recognition) and the identification of individuals (e.g., face recognition, biometrics). The visual distinctions between similar categories are often quite subtle and therefore difficult to address with today’s general-purpose object recognition machinery. Our workshop associated with ACCV 2020 focuses on such an interesting and challenging problem, which consists of a challenge session (WebFG 2020) and a paper submission session.

The WebFG 2020 challenge pays attentions on the webly-supervised fine-grained recognition problem. Participants have to deal with the challenging subordinate fine-grained category classification task (totally 5,000 sub-categories) by leveraging the free but noisy web data (a.k.a. webly fine-grained images). This results in a more robust evaluation of the current state of the art, counteracts over-fitting to traditional fine-grained benchmarks, and allows insights into prevalent dataset bias, data noises and as well as long-tailed distribution of the webly fine-grained nature. The overall goal of the challenge is to evaluate the robustness and generalization capabilities of state-of-the-art algorithms.

Beyond that, our workshop will also consist of a paper submission session. We would like to peer-review paper submissions involving the fine-grained related topics, such as fine-grained categorization, fine-grained retrieval, novel fine-grained datasets, few-shot learning for fine-grained, self-supervised learning for fine-grained, semi-supervised learning for fine-grained, transfer-learning from known to novel subcategories, fine-grained categorization with humans in the loop, interpretable fine-grained models, multi-modal learning for fine-grained, diverse fine-grained applications (e.g., product recognition), etc.