Variation of Gender Biases in Visual Recognition Models Before and After
Finetuning
- URL: http://arxiv.org/abs/2303.07615v1
- Date: Tue, 14 Mar 2023 03:42:47 GMT
- Title: Variation of Gender Biases in Visual Recognition Models Before and After
Finetuning
- Authors: Jaspreet Ranjit, Tianlu Wang, Baishakhi Ray, Vicente Ordonez
- Abstract summary: We introduce a framework to measure how biases change before and after fine-tuning a large scale visual recognition model for a downstream task.
We find that supervised models trained on datasets such as ImageNet-21k are more likely to retain their pretraining biases.
We also find that models finetuned on larger scale datasets are more likely to introduce new biased associations.
- Score: 29.55318393877906
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We introduce a framework to measure how biases change before and after
fine-tuning a large scale visual recognition model for a downstream task. Deep
learning models trained on increasing amounts of data are known to encode
societal biases. Many computer vision systems today rely on models typically
pretrained on large scale datasets. While bias mitigation techniques have been
developed for tuning models for downstream tasks, it is currently unclear what
are the effects of biases already encoded in a pretrained model. Our framework
incorporates sets of canonical images representing individual and pairs of
concepts to highlight changes in biases for an array of off-the-shelf
pretrained models across model sizes, dataset sizes, and training objectives.
Through our analyses, we find that (1) supervised models trained on datasets
such as ImageNet-21k are more likely to retain their pretraining biases
regardless of the target dataset compared to self-supervised models. We also
find that (2) models finetuned on larger scale datasets are more likely to
introduce new biased associations. Our results also suggest that (3) biases can
transfer to finetuned models and the finetuning objective and dataset can
impact the extent of transferred biases.
Related papers
- Understanding the Interplay of Scale, Data, and Bias in Language Models: A Case Study with BERT [4.807994469764776]
We study the influence of model scale and pre-training data on a language model's learnt social biases.
Our experiments show that pre-training data substantially influences how upstream biases evolve with model scale.
We shed light on the complex interplay of data and model scale, and investigate how it translates to concrete biases.
arXiv Detail & Related papers (2024-07-25T23:09:33Z) - Addressing Bias Through Ensemble Learning and Regularized Fine-Tuning [0.2812395851874055]
This paper proposes a comprehensive approach using multiple methods to remove bias in AI models.
We train multiple models with the counter-bias of the pre-trained model through data splitting, local training, and regularized fine-tuning.
We conclude our solution with knowledge distillation that results in a single unbiased neural network.
arXiv Detail & Related papers (2024-02-01T09:24:36Z) - Fast Model Debias with Machine Unlearning [54.32026474971696]
Deep neural networks might behave in a biased manner in many real-world scenarios.
Existing debiasing methods suffer from high costs in bias labeling or model re-training.
We propose a fast model debiasing framework (FMD) which offers an efficient approach to identify, evaluate and remove biases.
arXiv Detail & Related papers (2023-10-19T08:10:57Z) - Overwriting Pretrained Bias with Finetuning Data [36.050345384273655]
We investigate bias when conceptualized as both spurious correlations between the target task and a sensitive attribute as well as underrepresentation of a particular group in the dataset.
We find that models finetuned on top of pretrained models can indeed inherit their biases, but (2) this bias can be corrected for through relatively minor interventions to the finetuning dataset.
Our findings imply that careful curation of the finetuning dataset is important for reducing biases on a downstream task, and doing so can even compensate for bias in the pretrained model.
arXiv Detail & Related papers (2023-03-10T19:10:58Z) - Debiasing Vision-Language Models via Biased Prompts [79.04467131711775]
We propose a general approach for debiasing vision-language foundation models by projecting out biased directions in the text embedding.
We show that debiasing only the text embedding with a calibrated projection matrix suffices to yield robust classifiers and fair generative models.
arXiv Detail & Related papers (2023-01-31T20:09:33Z) - Dataless Knowledge Fusion by Merging Weights of Language Models [51.8162883997512]
Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models.
This creates a barrier to fusing knowledge across individual models to yield a better single model.
We propose a dataless knowledge fusion method that merges models in their parameter space.
arXiv Detail & Related papers (2022-12-19T20:46:43Z) - Synthetic Model Combination: An Instance-wise Approach to Unsupervised
Ensemble Learning [92.89846887298852]
Consider making a prediction over new test data without any opportunity to learn from a training set of labelled data.
Give access to a set of expert models and their predictions alongside some limited information about the dataset used to train them.
arXiv Detail & Related papers (2022-10-11T10:20:31Z) - Self-Distillation for Further Pre-training of Transformers [83.84227016847096]
We propose self-distillation as a regularization for a further pre-training stage.
We empirically validate the efficacy of self-distillation on a variety of benchmark datasets for image and text classification tasks.
arXiv Detail & Related papers (2022-09-30T02:25:12Z) - Revealing Secrets From Pre-trained Models [2.0249686991196123]
Transfer-learning has been widely adopted in many emerging deep learning algorithms.
We show that pre-trained models and fine-tuned models have significantly high similarities in weight values.
We propose a new model extraction attack that reveals the model architecture and the pre-trained model used by the black-box victim model.
arXiv Detail & Related papers (2022-07-19T20:19:03Z) - Learning from others' mistakes: Avoiding dataset biases without modeling
them [111.17078939377313]
State-of-the-art natural language processing (NLP) models often learn to model dataset biases and surface form correlations instead of features that target the intended task.
Previous work has demonstrated effective methods to circumvent these issues when knowledge of the bias is available.
We show a method for training models that learn to ignore these problematic correlations.
arXiv Detail & Related papers (2020-12-02T16:10:54Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.