English
Related papers

Related papers: Rethinking ImageNet Pre-training

200 papers

Model initialization techniques are vital for improving the performance and reliability of deep learning models in medical computer vision applications. While much literature exists on non-medical images, the impacts on medical images,…

Computer Vision and Pattern Recognition · Computer Science 2023-09-21 Sivaramakrishnan Rajaraman , Ghada Zamzmi , Feng Yang , Zhaohui Liang , Zhiyun Xue , Sameer Antani

Self-supervised methods have achieved remarkable success in transfer learning, often achieving the same or better accuracy than supervised pre-training. Most prior work has done so by increasing pre-training computation by adding complex…

Computer Vision and Pattern Recognition · Computer Science 2022-10-20 Skanda Koppula , Yazhe Li , Evan Shelhamer , Andrew Jaegle , Nikhil Parthasarathy , Relja Arandjelovic , João Carreira , Olivier Hénaff

Mask R-CNN has recently achieved great success in the field of instance segmentation. However, weaknesses of the algorithm have been repeatedly pointed out as well, especially in the segmentation of long, sparse objects whose orientation is…

Computer Vision and Pattern Recognition · Computer Science 2022-03-09 Moritz Zink , Martin Schiele , Pengcheng Fan , Stephan Gasterstädt

Despite recent advancements in text-to-image models, achieving semantically accurate images in text-to-image diffusion models is a persistent challenge. While existing initial latent optimization methods have demonstrated impressive…

Computer Vision and Pattern Recognition · Computer Science 2024-11-27 Aravindan Sundaram , Ujjayan Pal , Abhimanyu Chauhan , Aishwarya Agarwal , Srikrishna Karanam

Deep neural networks demonstrate to have a high performance on image classification tasks while being more difficult to train. Due to the complexity and vanishing gradient problem, it normally takes a lot of time and more computational…

Computer Vision and Pattern Recognition · Computer Science 2018-05-02 Mohammad Sadegh Ebrahimi , Hossein Karkeh Abadi

Neural net classifiers trained on data with annotated class labels can also capture apparent visual similarity among categories without being directed to do so. We study whether this observation can be extended beyond the conventional…

Computer Vision and Pattern Recognition · Computer Science 2018-05-08 Zhirong Wu , Yuanjun Xiong , Stella Yu , Dahua Lin

Usually, Neural Networks models are trained with a large dataset of images in homogeneous backgrounds. The issue is that the performance of the network models trained could be significantly degraded in a complex and heterogeneous…

Computer Vision and Pattern Recognition · Computer Science 2020-03-02 Vinorth Varatharasan , Hyo-Sang Shin , Antonios Tsourdos , Nick Colosimo

This work proposes a novel method for object co-segmentation, i.e. pixel-level localization of a common object in a set of images, that uses no pixel-level supervision for training. Two pre-trained Vision Transformer (ViT) models are…

Computer Vision and Pattern Recognition · Computer Science 2024-10-18 Nikolaos-Antonios Ypsilantis , Ondřej Chum

Deep learning has transformed computer vision but relies heavily on large labeled datasets and computational resources. Transfer learning, particularly fine-tuning pretrained models, offers a practical alternative; however, models…

Computer Vision and Pattern Recognition · Computer Science 2025-05-23 Iván Matas , Carmen Serrano , Miguel Nogales , David Moreno , Lara Ferrándiz , Teresa Ojeda , Begoña Acha

We introduce a generic framework that reduces the computational cost of object detection while retaining accuracy for scenarios where objects with varied sizes appear in high resolution images. Detection progresses in a coarse-to-fine…

Computer Vision and Pattern Recognition · Computer Science 2018-03-28 Mingfei Gao , Ruichi Yu , Ang Li , Vlad I. Morariu , Larry S. Davis

To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level prediction and…

Computer Vision and Pattern Recognition · Computer Science 2021-04-06 Xinlong Wang , Rufeng Zhang , Chunhua Shen , Tao Kong , Lei Li

Annotating a large number of training images is very time-consuming. In this background, this paper focuses on learning from easy-to-acquire web data and utilizes the learned model for fine-grained image classification in labeled datasets.…

Computer Vision and Pattern Recognition · Computer Science 2018-12-24 Xiaoxiao Sun , Liang Zheng , Yu-Kun Lai , Jufeng Yang

Optical neural networks are emerging as powerful machine learning and information processing tools because of their potential advantages in speed and energy efficiency. The training methods of these physical models, however, remain…

Optics · Physics 2026-05-11 Xudong Lv , Yuxiang Sun , Shuo Wang , Nanxing Chen , Jun Guan , Jingtian Hu

Transformers have become the dominant model in natural language processing, owing to their ability to pretrain on massive amounts of data, then transfer to smaller, more specific tasks via fine-tuning. The Vision Transformer was the first…

Computer Vision and Pattern Recognition · Computer Science 2020-12-21 Josh Beal , Eric Kim , Eric Tzeng , Dong Huk Park , Andrew Zhai , Dmitry Kislyuk

Weakly supervised learning has emerged as a compelling tool for object detection by reducing the need for strong supervision during training. However, major challenges remain: (1) differentiation of object instances can be ambiguous; (2)…

Computer Vision and Pattern Recognition · Computer Science 2020-10-22 Zhongzheng Ren , Zhiding Yu , Xiaodong Yang , Ming-Yu Liu , Yong Jae Lee , Alexander G. Schwing , Jan Kautz

In this study, a novel deep learning algorithm for object detection, named MelNet, was introduced. MelNet underwent training utilizing the KITTI dataset for object detection. Following 300 training epochs, MelNet attained an mAP (mean…

Computer Vision and Pattern Recognition · Computer Science 2024-02-01 Yashar Azadvatan , Murat Kurt

Finetuning from a pretrained deep model is found to yield state-of-the-art performance for many vision tasks. This paper investigates many factors that influence the performance in finetuning for object detection. There is a long-tailed…

Computer Vision and Pattern Recognition · Computer Science 2016-04-15 Wanli Ouyang , Xiaogang Wang , Cong Zhang , Xiaokang Yang

Recent advances in deep learning have led to significant progress in the computer vision field, especially for visual object recognition tasks. The features useful for object classification are learned by feed-forward deep convolutional…

Computer Vision and Pattern Recognition · Computer Science 2016-01-08 Panqu Wang , Garrison W. Cottrell

Self-supervised representation learning approaches have recently surpassed their supervised learning counterparts on downstream tasks like object detection and image classification. Somewhat mysteriously the recent gains in performance come…

Computer Vision and Pattern Recognition · Computer Science 2020-07-30 Senthil Purushwalkam , Abhinav Gupta

Deep image prior (DIP) was recently introduced as an effective unsupervised approach for image restoration tasks. DIP represents the image to be recovered as the output of a deep convolutional neural network, and learns the network's…

Image and Video Processing · Electrical Eng. & Systems 2023-02-10 Riccardo Barbano , Johannes Leuschner , Maximilian Schmidt , Alexander Denker , Andreas Hauptmann , Peter Maaß , Bangti Jin