Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints
2017pp. 2979–2989
Citations Over TimeTop 1% of 2017 papers
Abstract
Language is increasingly being used to define rich visual recognition problems with supporting image collections sourced from the web. Structured prediction models are used in these tasks to take advantage of correlations between co-occurring labels and visual input but risk inadvertently encoding social biases found in web corpora.
Related Papers
- → DeepSpeed- Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale(2022)208 cited
- → Partitioned state encoding for low power in FPGAs(2005)24 cited
- → POSITIVE-NEGATIVE ASYMMETRY IN MENTAL STATE INFERENCE: REPLICATION AND EXTENSION(2006)1 cited
- Talking about the Development and Application of the Phonetic Compressed Encoding Method(2006)
- On the Probable Inference in Criminal Investigation(2004)