23 papers · ranked by Valyu relevance
Nikita Kisel, Illia Volkov, Katerina Hanzelkova, Klára Janoušková + 1 more
'Jiřı́ Matas'] As models have improved in accuracy, issues related to label correctness have become increasingly apparent. In this blog post, we analyze the issues in the ImageNet-1k dataset, including incorrect labels, overlapping or ambiguous class definitions, training-evaluation domain shifts, and image duplicates.…
Syed Ali John Naqvi, Syed Bazil Ali
— We present a list of datasets and their best models with the goal of advancing the state-of-the-art in object detection by placing the question of object recognition in the context of the two types of state-of-the-art methods: one-stage methods and two stage-methods. We provided an in-depth statistical analysis of…
Ali Borji
Test sets are an integral part of evaluating models and gauging progress in object recognition, and more broadly in computer vision and AI. Existing test sets for object recognition, however, suffer from shortcomings such as bias towards the ImageNet characteristics and idiosyncrasies (e.g. ImageNet-V2), being limited…
Sou Yoshihara, Taiki Fukiage, Shin’ya Nishida
It is suggested that experiences of perceiving blurry images in addition to sharp images contribute to the development of robust human visual processing. To computationally investigate the effect of exposure to blurry images, we trained Convolutional Neural Networks (CNNs) on ImageNet object recognition with a variety…
Olawale Salaudeen, Moritz Hardt
We introduce ImageNot, a dataset designed to match the scale of ImageNet while differing drastically in other aspects. We show that key model architectures developed for ImageNet over the years rank identically when trained and evaluated on ImageNot to how they rank on ImageNet. This is true when training models from…
Muhammad Safdar Ali Khan, Arif Husen, Shafaq Nisar, Hasnain Ahmed + 3 more
'Syed Shah Muhammad' 'Shabib Aftab' 'Hongfei Hou'] Deep learning approaches are generally complex, requiring extensive computational resources and having high time complexity. Transfer learning is a state-of-the-art approach to reducing the requirements of high computational resources by using pre-trained models…
Shota Okazaki, Yuichi Mine, Yuki Yoshimi, Yuko Iwamoto + 9 more
'Tzu-Yu Peng' 'Taku Nishimura' 'Tomoya Suehiro' 'Yuma Koizumi' 'Ryota Nomura' 'Kotaro Tanimoto' 'Naoya Kakimoto' 'Takeshi Murayama'] Transfer learning (TL) is an alternative approach to the full training of deep learning (DL) models from scratch and can transfer knowledge gained from large-scale data to solve different…
Xueyan Mei, Zelong Liu, Philip M. Robson, Brett Marinelli + 11 more
'Mingqian Huang' 'Amish Doshi' 'Adam Jacobi' 'Chendi Cao' 'Katherine E. Link' 'Thomas Yang' 'Ying Wang' 'Hayit Greenspan' 'Timothy Deyer' 'Zahi A. Fayad' 'Yang Yang'] Purpose To demonstrate the value of pretraining with millions of radiologic images compared with ImageNet photographic images on downstream medical…
Alex Chengyu Fang, Simon Kornblith, Ludwig Schmidt
Does progress on ImageNet transfer to real-world datasets? We investigate this question by evaluating ImageNet pre-trained models with varying accuracy (57% - 83%) on six practical image classification datasets. In particular, we study datasets collected with the goal of solving real-world tasks (e.g., classifying…
Gaurav Malhotra, Marin Dujmović, Jeffrey S Bowers
A central problem in vision sciences is to understand how humans recognise objects under novel viewing conditions. Recently, statistical inference models such as Convolutional Neural Networks (CNNs) seem to have reproduced this ability by incorporating some architectural constraints of biological vision systems into…
Maad Ebrahim, Mohammad Alsmirat, Mahmoud Al-Ayyoub
Over recent years, researchers and practitioners have encountered massive and continuous improvements in the computational resources available for their use. This allowed the use of resource-hungry Machine learning (ML) algorithms to become feasible and practical. Moreover, several advanced techniques are being used to…
Niklas Müller, Cees G. M. Snoek, Iris I. A. Groen, H. Steven Scholte
Convolutional Neural Networks (CNNs) surpass human-level performance on visual object recognition and detection, but their behavior still differs from human behavior in important ways. One prominent example is that CNNs trained on ImageNet exhibit an image texture bias, while humans exhibit a strong bias toward object…
Adam Stančić, Vedran Vyroubal, Vedran Slijepčević, Pier Luigi Mazzeo
This paper presents the evaluation of 36 convolutional neural network (CNN) models, which were trained on the same dataset (ImageNet). The aim of this research was to evaluate the performance of pre-trained models on the binary classification of images in a “real-world” application. The classification of wildlife…
Bagher Sistaninejhad, Habib Rasi, Parisa Nayeri
Medical imaging refers to the process of obtaining images of internal organs for therapeutic purposes such as discovering or studying diseases. The primary objective of medical image analysis is to improve the efficacy of clinical research and treatment options. Deep learning has revamped medical image analysis…
Kohulan Rajan, Henning Otto Brinkhaus, M. Isabel Agea, Achim Zielesny + 1 more
The number of publications describing chemical structures has increased steadily over the last decades. However, the majority of published chemical information is currently not available in machine-readable form in public databases. It remains a challenge to automate the process of information extraction in a way that…
Authors not listed
This research presents a novel approach to obstacle detection during navigation using a combination of Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. The primary objective is to generate accurate image captions that describe the content of images, which is crucial for applications such…
Christian Tsvetkov, Gaurav Malhotra, Benjamin D. Evans, Jeffrey S. Bowers
Convolutional neural networks (CNNs) are often described as promising models of human vision, yet they show many differences from human abilities. We focus on a superhuman capacity of top-performing CNNs, namely, their ability to learn very large datasets of random patterns. We verify that human learning on such tasks…
Omisa Jinsi, Margaret M. Henderson, Michael J. Tarr
Humans are born with very low contrast sensitivity, meaning that developing infants experience the world “in a blur”. Is this solely a byproduct of maturational processes or is there some functional advantage for beginning life with poor vision? We explore whether reduced visual acuity as a consequence of low contrast…
Sebastian Stabinger, David Peer, Justus Piater, Antonio Rodrı́guez-Sánchez
'Antonio Rodrı́guez-Sánchez'] | Sebastian Stabinger | Universitat Innsbruck ¨ Technikerstrasse 21a, 6020 Innsbruck, Austria | ❖ | ✉ | | --- | --- | --- | --- | | David Peer | Universitat Innsbruck ¨ Technikerstrasse 21a, 6020 Innsbruck, Austria | ❖ | ✉ | | Justus Piater | Universitat Innsbruck ¨ Technikerstrasse 21a…
Authors not listed
Determining complete atomic structures directly from microscopy images remains a longstanding challenge in materials science. MicroscopyGPT is a vision-language model (VLM) that leverages multimodal generative pre-trained transformers to predict full atomic configurations including lattice parameters, element types…
Authors not listed
Infrared (IR) spectroscopy provides rich structural information but interpreting spectra at scale remains challenging. Here we introduce j-IR-vis, a vision-based neural model that learns chemically interpretable representations directly from IR spectra for functional-group prediction and downstream molecular…
Mallikharjuna Rao K, Harleen Kaur, Sanjam Kaur Bedi, M. A. Lekhana
- People with vocal and hearing disabilities use sign language to express themselves using visual gestures and signs. Although sign language is a solution for communication difficulties faced by deaf people, there are still problems as most of the general population cannot understand this language, creating a…
Hongyang Dong, Simon D.M. Jacques, Winfried Kockelmann, Stephen W. T. Price + 10 more
Hongyang Dong 3 , Simon D.M. Jacques 1 , Winfried Kockelmann 4 , Stephen W. T. Price 1 , Robert Emberson 5 , Dorota Matras 6,7 , Yaroslav Odarchenko 1 , Vesna Middelkoop 10 , Athanasios Giokaris 1 , Olof Gutowski 8 , Ann-Christin Dippel 8 , Martin v. Zimmermann 8 , Andrew M. Beale 3 , Keith T. Butler 9 , Antonis…