English
Related papers

Related papers: Fine-tuning Vision Classifiers On A Budget

200 papers

This study explores the impact of scaling semantic categories on the image classification performance of vision transformers (ViTs). In this specific case, the CLIP server provided by Jina AI is used for experimentation. The research…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Anthony Lamelas , Harrison Muchnic

For state-of-the-art semantic segmentation task, training convolutional neural networks (CNNs) requires dense pixelwise ground truth (GT) labeling, which is expensive and involves extensive human effort. In this work, we study the…

Computer Vision and Pattern Recognition · Computer Science 2016-10-05 Siva Karthik Mustikovela , Michael Ying Yang , Carsten Rother

Scale-invariance is an open problem in many computer vision subfields. For example, object labels should remain constant across scales, yet model predictions diverge in many cases. This problem gets harder for tasks where the ground-truth…

Computer Vision and Pattern Recognition · Computer Science 2022-12-13 Oliver Wiedemann , Vlad Hosu , Shaolin Su , Dietmar Saupe

Adopting a two-stage paradigm of pretraining followed by fine-tuning, Pretrained Language Models (PLMs) have achieved substantial advancements in the field of natural language processing. However, in real-world scenarios, data labels are…

Computation and Language · Computer Science 2023-11-03 Song Wang , Zhen Tan , Ruocheng Guo , Jundong Li

Large training datasets almost always contain examples with inaccurate or incorrect labels. Deep Neural Networks (DNNs) tend to overfit training label noise, resulting in poorer model performance in practice. To address this problem, we…

Computer Vision and Pattern Recognition · Computer Science 2022-03-01 Chen Gong , Kong Bin , Eric J. Seibel , Xin Wang , Youbing Yin , Qi Song

Although deep learning-based computer-aided diagnosis systems have recently achieved expert-level performance, developing a robust deep learning model requires large, high-quality data with manual annotation, which is expensive to obtain.…

Image and Video Processing · Electrical Eng. & Systems 2022-10-12 Sangjoon Park , Gwanghyun Kim , Yujin Oh , Joon Beom Seo , Sang Min Lee , Jin Hwan Kim , Sungjun Moon , Jae-Kwang Lim , Chang Min Park , Jong Chul Ye

Synthetic image translation has significant potentials in autonomous transportation systems. That is due to the expense of data collection and annotation as well as the unmanageable diversity of real-words situations. The main issue with…

Computer Vision and Pattern Recognition · Computer Science 2018-12-06 Sebastian Bujwid , Miquel Martí , Hossein Azizpour , Alessandro Pieropan

In a standard classification framework a set of trustworthy learning data are employed to build a decision rule, with the final aim of classifying unlabelled units belonging to the test set. Therefore, unreliable labelled observations,…

Applications · Statistics 2019-11-20 Andrea Cappozzo , Francesca Greselin , Thomas Brendan Murphy

In this paper we propose augmenting Vision Transformer models with learnable memory tokens. Our approach allows the model to adapt to new tasks, using few parameters, while optionally preserving its capabilities on previously learned tasks.…

Computer Vision and Pattern Recognition · Computer Science 2022-03-31 Mark Sandler , Andrey Zhmoginov , Max Vladymyrov , Andrew Jackson

For the task of fine-grained entity typing (FET), due to the use of a large number of entity types, it is usually considered too costly to manually annotating a training dataset that contains an ample number of examples for each type. A…

Computation and Language · Computer Science 2023-12-12 Hongliang Dai , Ziqian Zeng

Machine learning classification systems are susceptible to poor performance when trained with incorrect ground truth labels, even when data is well-curated by expert annotators. As machine learning becomes more widespread, it is…

Machine Learning · Computer Science 2026-01-16 Zan Chaudhry , Noam H. Rotenberg , Brian Caffo , Craig K. Jones , Haris I. Sair

Recent studies show that pretraining a deep neural network with fine-grained labeled data, followed by fine-tuning on coarse-labeled data for downstream tasks, often yields better generalization than pretraining with coarse-labeled data.…

Machine Learning · Computer Science 2024-12-11 Guan Zhe Hong , Yin Cui , Ariel Fuxman , Stanley Chan , Enming Luo

Prompt tuning, which involves training a small set of parameters, effectively enhances the pre-trained Vision-Language Models (VLMs) to downstream tasks. However, they often come at the cost of flexibility and adaptability when the tuned…

Computer Vision and Pattern Recognition · Computer Science 2024-07-08 Mushui Liu , Bozheng Li , Yunlong Yu

Data is the engine of modern computer vision, which necessitates collecting large-scale datasets. This is expensive, and guaranteeing the quality of the labels is a major challenge. In this paper, we investigate efficient annotation…

Computer Vision and Pattern Recognition · Computer Science 2021-04-27 Yuan-Hong Liao , Amlan Kar , Sanja Fidler

Transportation mode detection with personal devices has been investigated for over ten years due to its importance in monitoring ones' activities, understanding human mobility, and assisting traffic management. However, two main limitations…

Computers and Society · Computer Science 2017-03-21 Yuren Zhou , Jin Wang , Peng Shi , Daniel Dahlmeier , Nils Tippenhauer , Erik Wilhelm

In many machine learning applications, labeled data is scarce and obtaining more labels is expensive. We introduce a new approach to supervising neural networks by specifying constraints that should hold over the output space, rather than…

Artificial Intelligence · Computer Science 2016-09-20 Russell Stewart , Stefano Ermon

A recently-proposed technique called self-adaptive training augments modern neural networks by allowing them to adjust training labels on the fly, to avoid overfitting to samples that may be mislabeled or otherwise non-representative. By…

Machine Learning · Computer Science 2020-06-16 Daniel Chiu , Franklyn Wang , Scott Duke Kominers

Current state-of-the-art deep learning systems for visual object recognition and detection use purely supervised training with regularization such as dropout to avoid overfitting. The performance depends critically on the amount of labeled…

Computer Vision and Pattern Recognition · Computer Science 2015-04-16 Scott Reed , Honglak Lee , Dragomir Anguelov , Christian Szegedy , Dumitru Erhan , Andrew Rabinovich

We present a framework to take advantage of existing labels at inference, called \textit{exemplars}, in order to improve the performance of object detection in medical images. The method, \textit{exemplar diffusion}, leverages existing…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Victor Wåhlstrand , Jennifer Alvén , Ida Häggström

Deep neural networks have demonstrated remarkable performance in various vision tasks, but their success heavily depends on the quality of the training data. Noisy labels are a critical issue in medical datasets and can significantly…

Computer Vision and Pattern Recognition · Computer Science 2024-12-03 Yeonguk Yu , Minhwan Ko , Sungho Shin , Kangmin Kim , Kyoobin Lee