A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning

Domain:

natural language processing

Record type:

paperposter

A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning

Poster presented at the Deep Learning Indaba 2022 by Siobhan Hall

Visit

storage.googleapis.com

From Measurement to Mitigation: Exploring the Transferability of Debiasing Approaches to Gender Bias in Maltese Language Models

The advancement of Large Language Models (LLMs) has transformed Natural Language Processing (NLP), e

A Deep Search for Prompt Radio Emission from the Short GRB 150424A With The Murchison Widefield Array

We present a search for prompt radio emission associated with the short-duration gamma-ray burst (GR

Exploring the Racial Bias in Pain Detection with a Computer Vision Model

People detect painful expressions more easily in members of their racial ingroup than outgroup. Here

Zero‐shot animal behaviour classification with vision‐language foundation models

International audience Understanding the behaviour of animals in their natural habita

AtlasOCR: Building the First Open-Source Darija OCR Model with Vision Language Models

Darija, the Moroccan Arabic dialect, is rich in visual content yet lacks specialized Optical Charact

Adaptive Rank, Reduced Forgetting: Knowledge Retention in Continual Learning Vision-Language Models with Dynamic Rank-Selective LoRA

Continual learning (CL) aims to accumulate knowledge from sequential tasks without catastrophic forg