![](https://img-blog.csdnimg.cn/20190918140053667.png?x-oss-process=image/resize,m_fixed,h_224,w_224)
论文
文章平均质量分 93
多为2D小样本目标检测相关论文
小张好难瘦
计算机视觉方向的小菜鸡,还没有入门Ծ ̮ Ծ
持续性躺尸,间歇性学习_(:з」∠)_
间断性记录学习到的东西٩(ˊvˋ*)و
欢迎批评指正 友好交流(๑•̀ㅂ•́)و✧
展开
-
【论文翻译】RODEO: Replay for Online Object Detection
RODEO: Replay for Online Object Detection 用于在线目标检测的回放论文地址:https://arxiv.org/abs/2008.06439代码地址:GitHub - manoja328/rodeo: Official implementation of "RODEO: Replay for Online Object Detection", BMVC 2020摘要Humans can incrementally learn to do new vi.翻译 2022-05-27 10:53:13 · 1074 阅读 · 0 评论 -
【论文翻译】Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection
Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild 野外目标的小样本目标检测与视点估计论文地址:https://arxiv.org/pdf/2007.12107v1.pdf代码地址:GitHub - YoungXIAO13/FewShotDetection: (ECCV 2020) PyTorch implementation of paper "Few-Shot Object Detection翻译 2022-05-25 18:12:41 · 1072 阅读 · 3 评论 -
【论文翻译】Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild
Few-Shot Object Detection and Viewpoint Estimation for Objects in the Wild 野外目标的小样本目标检测与视点估计论文地址:https://arxiv.org/pdf/2007.12107v1.pdf代码地址:GitHub - YoungXIAO13/FewShotDetection: (ECCV 2020) PyTorch implementation of paper "Few-Shot Object Detection翻译 2022-05-10 22:53:40 · 1352 阅读 · 0 评论 -
【论文翻译】UniT: Unified Knowledge Transfer for Any-Shot Object Detection and Segmentation
UniT: Unified Knowledge Transfer for Any-Shot Object Detection and Segmentation UniT:任何样本目标检测和分割的统一知识转移论文地址:https://openaccess.thecvf.com/content/CVPR2021/papers/Khandelwal_UniT_Unified_Knowledge_Transfer_for_Any-Shot_Object_Detection_and_Segmentation_翻译 2022-05-04 03:01:46 · 1116 阅读 · 0 评论 -
【论文翻译】Few-Shot Object Detection via Classification Refinement and Distractor Retreatment
Few-Shot Object Detection via Classification Refinement and Distractor Retreatment基于分类细化和干扰物再处理的少样本目标检测论文地址:CVPR 2021 Open Access Repository1 摘要We aim to tackle the challenging Few-Shot Object Detection (FSOD), where data-scarce categories are pre.翻译 2022-04-30 12:04:05 · 1495 阅读 · 0 评论 -
【论文翻译】Few Sample Knowledge Distillation for Efficient Network Compression
Few Sample Knowledge Distillation for Efficient Network Compression用于高效网络压缩的少样本知识提取论文地址:https://arxiv.org/abs/1812.01839代码地址:GitHub - LTH14/FSKD摘要Deep neural network compression techniques such as pruning and weight tensor decomposition usually r翻译 2022-04-28 19:23:05 · 863 阅读 · 0 评论 -
【论文翻译】Progressive Network Grafting for Few-Shot Knowledge Distillation
Progressive Network Grafting for Few-Shot Knowledge Distillation渐进式网络移植技术在少样本知识提取中的应用论文地址:https://arxiv.org/pdf/2012.04915v2.pdf代码地址:https://github.com/zju-vipa/NetGraft摘要Knowledge distillation has demonstrated encouraging performances in deep mo翻译 2022-04-27 21:25:40 · 512 阅读 · 0 评论 -
【论文翻译】Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning
Task Difficulty Aware Parameter Allocation & Regularization for Lifelong Learning面向终身学习的任务难度感知参数分配与正则化摘要Recently, many parameter regularization or allocation methods have been proposed to overcome catastrophic forgetting in lifelong learning. How翻译 2022-04-20 19:31:37 · 1201 阅读 · 0 评论 -
【论文翻译】Meta R-CNN : Towards General Solver for Instance-level Low-shot Learning
Meta R-CNN : Towards General Solver for Instance-level Low-shot LearningMeta R-CNN:面向实例级少样本学习的通用解算器论文地址:代码地址:https://yanxp.github.io/metarcnn.htmlAbstractResembling the rapid learning capability of human, lowshot learning empowers vision systems t.翻译 2022-04-19 15:48:46 · 1375 阅读 · 1 评论 -
【论文翻译】Highlight Every Step: Knowledge Distillation via Collaborative Teaching
Highlight Every Step: Knowledge Distillation via Collaborative Teaching强调每一步:通过协作教学提炼知识摘要High storage and computational costs obstruct deep neural networks to be deployed on resource-constrained devices. Knowledge distillation (KD) aims to train a co翻译 2022-04-18 21:19:38 · 683 阅读 · 0 评论 -
【论文翻译】Many-Class Few-Shot Learning on Multi-Granularity Class Hierarchy
Many-Class Few-Shot Learning on Multi-Granularity Class Hierarchy 多粒度类层次上的多类少样本学习摘要We study many-class few-shot (MCFS) problem in both supervised learning and meta-learning settings. Compared to the well-studied many-class many-shot and few-class few-s翻译 2022-04-13 21:19:58 · 1152 阅读 · 0 评论 -
【论文翻译】Learning from Few Samples: A Survey 小样本学习综述
论文链接:https://arxiv.org/abs/2007.15484摘要Deep neural networks have been able to outperform humans in some cases like image recognition and image classification. However, with the emergence of various novel categories, the ability to continuously widen th翻译 2021-12-18 18:39:17 · 3505 阅读 · 0 评论 -
【论文翻译】Frustratingly Simple Few-Shot Object Detection
Frustratingly Simple Few-Shot Object Detection 简单小样本目标检测论文地址:https://arxiv.org/pdf/2003.06957.pdf代码地址:GitHub - ucbdrive/few-shot-object-detection: Implementations of few-shot object detection benchmarksAbstractDetecting rare objects from a few exam翻译 2021-12-08 21:25:06 · 2049 阅读 · 6 评论 -
【论文翻译】Faster ILOD:Incremental Learning for Object Detectors based on Faster RCNN
Faster ILOD:Incremental Learning for Object Detectors based on Faster RCNNFaster ILOD:基于Faster RCNN的目标检测器增量学习论文地址:https://arxiv.org/pdf/2003.03901.pdf代码地址:无AbstractThe human vision and perception system is inherently incremental where new knowled翻译 2021-12-07 16:01:46 · 1191 阅读 · 0 评论 -
【论文翻译】Universal-Prototype Enhancing for Few-Shot Object Detection
论文地址:https://arxiv.org/pdf/2103.01077v1.pdf代码地址:https://github. com/AMIGWU/UP-FSODAbstractFew-shot object detection (FSOD) aims to strengthen the performance of novel object detection with few labeled samples. To alleviate the constraint of few sampl翻译 2021-11-26 10:44:04 · 993 阅读 · 1 评论 -
【论文总结】Meta-Learning for semi-supervised few-shot classification(附翻译)
Meta-Learning for semi-supervised few-shot classification 半监督小样本分类的元学习AbstractIn few-shot classification, we are interested in learning algorithms that train a classifier from only a handful of labeled examples. Recent progress in few-shot classificat.原创 2021-11-24 17:03:48 · 3140 阅读 · 0 评论 -
【论文总结】Prototype Rectification for Few-Shot Learning(附翻译)
Prototype Rectification for Few-Shot Learning原创 2021-11-22 16:24:41 · 2841 阅读 · 0 评论 -
【论文翻译】Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection
Semantic Relation Reasoning for Shot-Stable Few-Shot Object Detection论文地址:https://arxiv.org/pdf/2103.01903.pdf代码地址:无o(╥﹏╥)otips:长尾:少数类(头类)占用大部分的数据,而大多数类(尾类)只有少量的数据摘要Few-shot object detection is an imperative and longlasting problem due to the翻译 2021-11-19 16:06:02 · 1545 阅读 · 0 评论 -
【论文翻译】Class-Incremental Few-Shot Object Detection
Class-Incremental Few-Shot Object Detection论文地址:https://arxiv.org/pdf/2105.07637.pdf摘要Conventional detection networks usually need abundant labeled training samples, while humans can learn new concepts incrementally with just a few examples. This pap翻译 2021-11-18 20:09:28 · 871 阅读 · 1 评论 -
【论文总结】Incremental Learning of Object Detectors without Catastrophic Forgetting(附翻译)
Incremental Learning of Object Detectors without Catastrophic Forgetting论文地址:代码地址:摘要Despite their success for object detection, convolutional neural networks are ill-equipped for incremental learning, mi.e., adapting the original model trained on .原创 2021-11-15 11:23:31 · 2253 阅读 · 1 评论 -
【论文总结】DeepEMD:Few-Shot Image Classification with Differentiable Earth Mover’s Distance(附翻译)
论文地址:https://arxiv.org/abs/2003.06777代码地址:https://github.com/icoz69/DeepEMD摘要In this paper, we address the few-shot classification task from a new perspective of optimal matching between image regions. We adopt the Earth Mover’s Distance (EMD) as a me原创 2021-11-10 10:51:03 · 2732 阅读 · 1 评论 -
【论文总结】FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding(附翻译)
论文地址:https://arxiv.org/pdf/2103.05950.pdf代码地址:http://https: //github.com/MegviiDetection/FSCE摘要Emerging interests have been brought to recognize previously unseen objects given very few training examples, known as few-shot object detection (FSOD). Re原创 2021-11-05 21:27:17 · 2497 阅读 · 4 评论 -
【论文翻译】PLOP: Learning without Forgetting for Continual Semantic Segmentation
论文地址:http://https://arxiv.org/abs/2011.11390代码地址:https://github.com/arthurdouillard/CVPR2021_PLOP摘要Deep learning approaches are nowadays ubiquitously used to tackle computer vision tasks such as semantic segmentation, requiring large datasets and s翻译 2021-11-04 11:34:33 · 2602 阅读 · 5 评论 -
【论文总结】Few-shot Object Detection via Feature Reweighting(附翻译)
论文地址:https://arxiv.org/abs/1812.01866代码地址:https:// github.com/bingykang/Fewshot_Detection目录摘要1 介绍2 相关工作3 方法3.1. Feature Reweighting for Detection用于检测的特征重加权3.2. Learning Scheme4 实验4.1. Experimental Setup 实验设置4.2. Comparison with Ba...原创 2021-11-01 15:02:21 · 2859 阅读 · 0 评论 -
【论文总结】Incremental Few-Shot Object Detection(附翻译)
Incremental Few-Shot Object Detection 小样本增量目标检测论文地址:https://arxiv.org/abs/2003.04668代码暂未公开思路:文章使用方法 Opened CenterNet(ONCE)以CenterNet单阶段检测方法为基础,加入一个元学习训练的类别编码生成模型来注册新类。新类样本只需要在 meta-training 阶段以前向传播方式注册,不需要复习基类或迭代更新。Centernet:特征提取网络使用Centernet: 该..原创 2021-10-28 22:24:54 · 2378 阅读 · 2 评论 -
【论文总结】Towards Open World Object Detection(附翻译)
Towards Open World Object Detection 开放世界的目标检测摘要Humans have a natural instinct to identify unknown object instances in their environments. The intrinsic curiosity about these unknown instances aids in learning about them, when the corresponding knowledg原创 2021-04-23 13:25:30 · 6520 阅读 · 8 评论