Related papers: Adjusting Pretrained Backbones for Performativity
With excellent generalization ability, self-supervised speech models have shown impressive performance on various downstream speech tasks in the pre-training and fine-tuning paradigm. However, as the growing size of pre-trained models,…
Advances in self-supervised learning (SSL) for machine vision have improved representation robustness and model performance, giving rise to pre-trained backbones like \emph{ResNet} and \emph{ViT} models tuned with SSL methods such as…
The use of self-supervised pre-training has emerged as a promising approach to enhance the performance of many different visual tasks. In this context, recent approaches have employed the Masked Image Modeling paradigm, which pre-trains a…
Deep neural networks have been widely used in computer vision. There are several well trained deep neural networks for the ImageNet classification challenge, which has played a significant role in image recognition. However, little work has…
As one of the fundamental tasks in computer vision, semantic segmentation plays an important role in real world applications. Although numerous deep learning models have made notable progress on several mainstream datasets with the rapid…
With the rapid development of Deep Learning, more and more applications on the cloud and edge tend to utilize large DNN (Deep Neural Network) models for improved task execution efficiency as well as decision-making quality. Due to memory…
This paper focuses on the unsupervised domain adaptation of transferring the knowledge from the source domain to the target domain in the context of semantic segmentation. Existing approaches usually regard the pseudo label as the ground…
Model hubs with many pre-trained models (PTMs) have become a cornerstone of deep learning. Although built at a high cost, they remain \emph{under-exploited} -- practitioners usually pick one PTM from the provided model hub by popularity and…
This paper investigates the critical problem of representation similarity evolution during cross-domain transfer learning, with particular focus on understanding why pre-trained models maintain effectiveness when adapted to medical imaging…
While deep learning has revolutionized research and applications in NLP and computer vision, this has not yet been the case for behavioral modeling and behavioral health applications. This is because the domain's datasets are smaller, have…
There is growing evidence that converting targets to soft targets in supervised learning can provide considerable gains in performance. Much of this work has considered classification, converting hard zero-one values to soft labels---such…
We are considering in this paper the task of label-efficient fine-tuning of segmentation models: We assume that a large labeled dataset is available and allows to train an accurate segmentation model in one domain, and that we have to adapt…
Deep neural networks often rely on spurious features to make predictions, which makes them brittle under distribution shift and on samples where the spurious correlation does not hold (e.g., minority-group examples). Recent studies have…
Transfer learning has become a central paradigm in modern machine learning, yet it suffers from the long-standing problem of negative transfer, where leveraging source representations can harm rather than help performance on the target…
Eliminating the negative effect of non-stationary environmental noise is a long-standing research topic for automatic speech recognition that stills remains an important challenge. Data-driven supervised approaches, including ones based on…
Our goal is to improve reliability of Machine Learning (ML) systems deployed in the wild. ML models perform exceedingly well when test examples are similar to train examples. However, real-world applications are required to perform on any…
The pruning objective has recently extended beyond accuracy and sparsity to robustness in language models. Despite this, existing methods struggle to enhance robustness against adversarial attacks when continually increasing model sparsity…
We propose self-adaptive training---a new training algorithm that dynamically corrects problematic training labels by model predictions without incurring extra computational cost---to improve generalization of deep learning for potentially…
As foundation models become more popular, there is a growing need to efficiently finetune them for downstream tasks. Although numerous adaptation methods have been proposed, they are designed to be efficient only in terms of how many…
We consider unsupervised domain adaptation: given labelled examples from a source domain and unlabelled examples from a related target domain, the goal is to infer the labels of target examples. Under the assumption that features from…