English
Related papers

Related papers: Self-Supervised YOLO: Leveraging Contrastive Learn…

200 papers

The success of deep learning heavily depends on the availability of large labeled training sets. However, it is hard to get large labeled datasets in medical image domain because of the strict privacy concern and costly labeling efforts.…

Computer Vision and Pattern Recognition · Computer Science 2021-09-30 Dewen Zeng , Yawen Wu , Xinrong Hu , Xiaowei Xu , Haiyun Yuan , Meiping Huang , Jian Zhuang , Jingtong Hu , Yiyu Shi

Recently, Semi-Supervised Learning (SSL) has shown much promise in leveraging unlabeled data while being provided with very few labels. In this paper, we show that ignoring the labels altogether for whole epochs intermittently during…

Computer Vision and Pattern Recognition · Computer Science 2020-12-02 Boaz Lerner , Guy Shiran , Daphna Weinshall

Single-stage detectors suffer from extreme foreground-background class imbalance, while two-stage detectors do not. Therefore, in semi-supervised object detection, two-stage detectors can deliver remarkable performance by only selecting…

Computer Vision and Pattern Recognition · Computer Science 2022-04-12 Yueming Zhang , Xingxu Yao , Chao Liu , Feng Chen , Xiaolin Song , Tengfei Xing , Runbo Hu , Hua Chai , Pengfei Xu , Guoshan Zhang

In this paper, we introduce a novel method designed to enhance label efficiency in satellite imagery analysis by integrating semi-supervised learning (SSL) with active learning strategies. Our approach utilizes contrastive learning together…

Computer Vision and Pattern Recognition · Computer Science 2024-06-26 David Pogorzelski , Peter Arlinghaus , Wenyan Zhang

Domain adaptive object detection (DAOD) aims to alleviate transfer performance degradation caused by the cross-domain discrepancy. However, most existing DAOD methods are dominated by outdated and computationally intensive two-stage Faster…

Computer Vision and Pattern Recognition · Computer Science 2022-11-29 Huayi Zhou , Fei Jiang , Hongtao Lu

This study introduces an innovative approach to analyzing unlabeled data in high-energy physics (HEP) through the application of self-supervised learning (SSL). Faced with the increasing computational cost of producing high-quality labeled…

High Energy Physics - Experiment · Physics 2024-08-20 Zihan Zhao , Farouk Mokhtar , Raghav Kansal , Haoyang Li , Javier Duarte

Object detection is a crucial component in autonomous vehicle systems. It enables the vehicle to perceive and understand its environment by identifying and locating various objects around it. By utilizing advanced imaging and deep learning…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Bsher Karbouj , Adam Michael Altenbuchner , Joerg Krueger

Synthetic datasets are often used to pretrain end-to-end optical flow networks, due to the lack of a large amount of labeled, real-scene data. But major drops in accuracy occur when moving from synthetic to real scenes. How do we better…

Computer Vision and Pattern Recognition · Computer Science 2022-12-06 Zhiqi Zhang , Nitin Bansal , Changjiang Cai , Pan Ji , Qingan Yan , Xiangyu Xu , Yi Xu

Accurate segmentation of retinal fluids in 3D Optical Coherence Tomography images is key for diagnosis and personalized treatment of eye diseases. While deep learning has been successful at this task, trained supervised models often fail…

Computer Vision and Pattern Recognition · Computer Science 2022-08-05 Alvaro Gomariz , Huanxiang Lu , Yun Yvonna Li , Thomas Albrecht , Andreas Maunz , Fethallah Benmansour , Alessandra M. Valcarcel , Jennifer Luu , Daniela Ferrara , Orcun Goksel

The utilization of deep learning-based object detection is an effective approach to assist visually impaired individuals in avoiding obstacles. In this paper, we implemented seven different YOLO object detection models \textit{viz}.,…

Computer Vision and Pattern Recognition · Computer Science 2023-12-14 Chenhao He , Pramit Saha

State-of-the-art natural language understanding classification models follow two-stages: pre-training a large language model on an auxiliary task, and then fine-tuning the model on a task-specific labeled dataset using cross-entropy loss.…

Computation and Language · Computer Science 2021-04-06 Beliz Gunel , Jingfei Du , Alexis Conneau , Ves Stoyanov

Self-supervised learning (SSL) has recently emerged as a powerful approach to learning representations from large-scale unlabeled data, showing promising results in time series analysis. The self-supervised representation learning can be…

Machine Learning · Computer Science 2024-03-18 Ziyu Liu , Azadeh Alavi , Minyi Li , Xiang Zhang

Self-supervised learning has been widely used to obtain transferrable representations from unlabeled images. Especially, recent contrastive learning methods have shown impressive performances on downstream image classification tasks. While…

Computer Vision and Pattern Recognition · Computer Science 2021-04-29 Byungseok Roh , Wuhyun Shin , Ildoo Kim , Sungwoong Kim

Under partial-label learning (PLL) where, for each training instance, only a set of ambiguous candidate labels containing the unknown true label is accessible, contrastive learning has recently boosted the performance of PLL on vision…

Computer Vision and Pattern Recognition · Computer Science 2023-05-11 Shiyu Xia , Jiaqi Lv , Ning Xu , Gang Niu , Xin Geng

Object detection, a pivotal task in computer vision, is frequently hindered by dataset imbalances, particularly the under-explored issue of foreground-foreground class imbalance. This lack of attention to foreground-foreground class…

Computer Vision and Pattern Recognition · Computer Science 2024-03-13 Nieves Crasto

Discriminating the traversability of terrains is a crucial task for autonomous driving in off-road environments. However, it is challenging due to the diverse, ambiguous, and platform-specific nature of off-road traversability. In this…

Robotics · Computer Science 2023-07-07 Hanzhang Xue , Xiaochang Hu , Rui Xie , Hao Fu , Liang Xiao , Yiming Nie , Bin Dai

The success of deep learning methods in medical image segmentation tasks heavily depends on a large amount of labeled data to supervise the training. On the other hand, the annotation of biomedical images requires domain knowledge and can…

Computer Vision and Pattern Recognition · Computer Science 2021-09-30 Xinrong Hu , Dewen Zeng , Xiaowei Xu , Yiyu Shi

The goal of contrastive learning based pre-training is to leverage large quantities of unlabeled data to produce a model that can be readily adapted downstream. Current approaches revolve around solving an image discrimination task: given…

Computer Vision and Pattern Recognition · Computer Science 2021-11-30 Chenhongyi Yang , Lichao Huang , Elliot J. Crowley

We introduce S$^2$VS, a video similarity learning approach with self-supervision. Self-Supervised Learning (SSL) is typically used to train deep models on a proxy task so as to have strong transferability on target tasks after fine-tuning.…

Computer Vision and Pattern Recognition · Computer Science 2023-06-19 Giorgos Kordopatis-Zilos , Giorgos Tolias , Christos Tzelepis , Ioannis Kompatsiaris , Ioannis Patras , Symeon Papadopoulos

To address the annotation burden in LiDAR-based 3D object detection, active learning (AL) methods offer a promising solution. However, traditional active learning approaches solely rely on a small amount of labeled data to train an initial…

Computer Vision and Pattern Recognition · Computer Science 2025-03-25 Zengran Wang , Yanan Zhang , Jiaxin Chen , Di Huang