Explanation on Pretraining Bias of Finetuned Vision Transformer
As the number of fine tuning of pretrained models increased, understanding the bias of pretrained model is essential. However, there is little tool to analyse transformer architecture and the interpretation of the attention maps is still challenging. To tackle the interpretability, we propose Input-Attribution and Attention Score Vector (IAV) which measures the similarity between attention map and input-attribution and shows the general trend of interpretable attention patterns. We empirically explain the pretraining bias of supervised and unsupervised pretrained ViT models, and show that each head in ViT has a specific range of agreement on the decision of the classification. We show that generalization, robustness and entropy of attention maps are not property of pretraining types. On the other hand, IAV trend can separate the pretraining types.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
What Happens During Finetuning of Vision Transformers: An Invariance Based Investigation
The pretrain-finetune paradigm usually improves downstream performance over training a model from scratch on the same task, becoming commonplace across many areas of machine learning. While pretraining is empirically obs…
TMI! Finetuned Models Leak Private Information from their Pretraining Data
Transfer learning has become an increasingly popular technique in machine learning as a way to leverage a pretrained model trained for one task to assist with building a finetuned model for a related task. This paradigm …
Transfer LearningVariation of Gender Biases in Visual Recognition Models Before and After Finetuning
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 enc…
Object RecognitionOPT-R: Exploring the Role of Explanations in Finetuning and Prompting for Reasoning Skills of Large Language Models
In this paper, we conduct a thorough investigation into the reasoning capabilities of Large Language Models (LLMs), focusing specifically on the Open Pretrained Transformers (OPT) models as a representative of such model…
ASiT: Local-Global Audio Spectrogram vIsion Transformer for Event Classification
Transformers, which were originally developed for natural language processing, have recently generated significant interest in the computer vision and audio communities due to their flexibility in learning long-range rel…
Keyword SpottingSelf-Supervised LearningSpeaker Identification