English
Related papers

Related papers: Towards Inadequately Pre-trained Models in Transfe…

200 papers

The transfer learning paradigm of model pre-training and subsequent fine-tuning produces high-accuracy models. While most studies recommend scaling the pre-training size to benefit most from transfer learning, a question remains: what data…

Computer Vision and Pattern Recognition · Computer Science 2023-03-02 Rahim Entezari , Mitchell Wortsman , Olga Saukh , M. Moein Shariatnia , Hanie Sedghi , Ludwig Schmidt

Cross-frequency transfer learning (CFTL) has emerged as a popular framework for curating large-scale time series datasets to pre-train foundation forecasting models (FFMs). Although CFTL has shown promise, current benchmarking practices…

Exemplar-Free Class Incremental Learning is a highly challenging setting where replay memory is unavailable. Methods relying on frozen feature extractors have drawn attention recently in this setting due to their impressive performances and…

Machine Learning · Computer Science 2025-02-28 Quentin Jodelet , Xin Liu , Yin Jun Phua , Tsuyoshi Murata

The widespread adoption of deep neural networks in computer vision applications has brought forth a significant interest in adversarial robustness. Existing research has shown that maliciously perturbed inputs specifically tailored for a…

Machine Learning · Computer Science 2022-09-16 Alexander Cann , Ian Colbert , Ihab Amer

Transfer learning is a critical technique in training deep neural networks for the challenging medical image segmentation task that requires enormous resources. With the abundance of medical image data, many research institutions release…

Computer Vision and Pattern Recognition · Computer Science 2023-07-25 Yuncheng Yang , Meng Wei , Junjun He , Jie Yang , Jin Ye , Yun Gu

Meta-learning offers a promising avenue for few-shot learning (FSL), enabling models to glean a generalizable feature embedding through episodic training on synthetic FSL tasks in a source domain. Yet, in practical scenarios where the…

Computer Vision and Pattern Recognition · Computer Science 2024-11-05 Fei Zhou , Peng Wang , Lei Zhang , Zhenghua Chen , Wei Wei , Chen Ding , Guosheng Lin , Yanning Zhang

A commonly accepted hypothesis is that models with higher accuracy on Imagenet perform better on other downstream tasks, leading to much research dedicated to optimizing Imagenet accuracy. Recently this hypothesis has been challenged by…

Computer Vision and Pattern Recognition · Computer Science 2022-04-21 Niv Nayman , Avram Golbert , Asaf Noy , Tan Ping , Lihi Zelnik-Manor

There exists a distribution discrepancy between training and testing, in the way images are fed to modern CNNs. Recent work tried to bridge this gap either by fine-tuning or re-training the network at different resolutions. However…

Computer Vision and Pattern Recognition · Computer Science 2022-01-21 Touqeer Ahmad , Mohsen Jafarzadeh , Akshay Raj Dhamija , Ryan Rabinowitz , Steve Cruz , Chunchun Li , Terrance E. Boult

Visual embeddings from Convolutional Neural Networks (CNN) trained on the ImageNet dataset for the ILSVRC challenge have shown consistently good performance for transfer learning and are widely used in several tasks, including image…

Information Retrieval · Computer Science 2018-09-26 Felipe del Rio , Pablo Messina , Vicente Dominguez , Denis Parra

In deep learning, transferring information from a pretrained network to a downstream task by finetuning has many benefits. The choice of task head plays an important role in fine-tuning, as the pretrained and downstream tasks are usually…

Machine Learning · Computer Science 2023-02-14 Yi Ren , Shangmin Guo , Wonho Bae , Danica J. Sutherland

The pretrain-finetune paradigm has shown outstanding performance on many applications of deep learning, where a model is pre-trained on a upstream large dataset (e.g. ImageNet), and is then fine-tuned to different downstream tasks. Though…

Computer Vision and Pattern Recognition · Computer Science 2022-03-15 Yutong Feng , Jianwen Jiang , Mingqian Tang , Rong Jin , Yue Gao

A multitude of prevalent pre-trained models mark a major milestone in the development of artificial intelligence, while fine-tuning has been a common practice that enables pretrained models to figure prominently in a wide array of target…

Computer Vision and Pattern Recognition · Computer Science 2023-11-14 Yunqiao Yang , Long-Kai Huang , Ying Wei

In many real-world scenarios, data to train machine learning models becomes available over time. Unfortunately, these models struggle to continually learn new concepts without forgetting what has been learnt in the past. This phenomenon is…

Computation and Language · Computer Science 2023-01-16 Beyza Ermis , Giovanni Zappella , Martin Wistuba , Aditya Rawal , Cedric Archambeau

In the era of transfer learning, training neural networks from scratch is becoming obsolete. Transfer learning leverages prior knowledge for new tasks, conserving computational resources. While its advantages are well-documented, we uncover…

Machine Learning · Computer Science 2023-11-17 Wojciech Masarczyk , Tomasz Trzciński , Mateusz Ostaszewski

Large-scale pre-training followed by downstream fine-tuning is an effective solution for transferring deep-learning-based models. Since finetuning all possible pre-trained models is computational costly, we aim to predict the…

Computer Vision and Pattern Recognition · Computer Science 2024-03-15 Zhao Wang , Aoxue Li , Zhenguo Li , Qi Dou

Few-shot transfer has been revolutionized by stronger pre-trained models and improved adaptation algorithms.However, there lacks a unified, rigorous evaluation protocol that is both challenging and realistic for real-world usage. In this…

Machine Learning · Computer Science 2026-03-03 Xu Luo , Ji Zhang , Lianli Gao , Heng Tao Shen , Jingkuan Song

In the low-data regime, it is difficult to train good supervised models from scratch. Instead practitioners turn to pre-trained models, leveraging transfer learning. Ensembling is an empirically and theoretically appealing way to construct…

Machine Learning · Computer Science 2020-10-20 Basil Mustafa , Carlos Riquelme , Joan Puigcerver , André Susano Pinto , Daniel Keysers , Neil Houlsby

There is growing interest in extending average treatment effect (ATE) estimation to incorporate non-tabular data, such as images and text, which may act as sources of confounding. Neglecting these effects risks biased results and flawed…

Machine Learning · Statistics 2025-10-23 Rickmer Schulte , David Rügamer , Thomas Nagler

We tackle the problem of feature unlearning from a pre-trained image generative model: GANs and VAEs. Unlike a common unlearning task where an unlearning target is a subset of the training set, we aim to unlearn a specific feature, such as…

Computer Vision and Pattern Recognition · Computer Science 2024-03-29 Saemi Moon , Seunghyuk Cho , Dongwoo Kim

In this paper, we study how the granularity of pretraining labels affects the generalization of deep neural networks in image classification tasks. We focus on the "fine-to-coarse" transfer learning setting, where the pretraining label…

Computer Vision and Pattern Recognition · Computer Science 2023-10-06 Guan Zhe Hong , Yin Cui , Ariel Fuxman , Stanley H. Chan , Enming Luo