computer-vision

One-Shot Object Detection

3260 papers • 126 benchmarks • 313 datasets

( Image credit: Siamese Mask R-CNN )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in one-shot-object-detection

Trend

Dataset

Best Model

Actions

MS COCO

PASCAL VOC 2012 val

Libraries

i

Use these libraries to find one-shot-object-detection models and implementations

Datasets

SKU110K

Subtasks

No subtasks available.

Most implemented papers

One-Shot Instance Segmentation

M. Bethge, Claudio Michaelis, Alexander S. Ecker, Ivan Ustyuzhaninov•Tue Nov 27 2018

Siamese Mask R-CNN is extended by a Siamese backbone encoding both reference image and scene, allowing it to target detection and segmentation towards the reference category.

96

Content

0

Paper Graph

Quasi-Dense Similarity Learning for Multiple Object Tracking

Trevor Darrell, F. Yu, Haofeng Chen, Jiangmiao Pang, Xia Li, Linlu Qiu, Qi Li•Wed Jun 10 2020

Quasi-Dense Similarity Learning is presented, which densely samples hundreds of region proposals on a pair of images for contrastive learning and which outperforms all existing methods on MOT, BDD100K, Waymo, and TAO tracking benchmarks.

450 0

Paper Graph

DroNet: Efficient convolutional neural network detector for real-time UAV applications

T. Theocharides, C. Kyrkou, George Plastiras, Stylianos I. Venieris, C. Bouganis•Tue Jul 17 2018

The paper presents a holistic approach for designing such systems; the data collection and training stages, the CNN architecture, and the optimizations necessary to efficiently map such a CNN on a lightweight embedded processing platform suitable for deployment on UAVs.

134 0

Paper Graph

Simple Open-Vocabulary Object Detection with Vision Transformers

N. Houlsby, Xiaohua Zhai, Alexey Dosovitskiy, Mostafa Dehghani, A. Gritsenko, Anurag Arnab, M. Minderer, Maxim Neumann, Dirk Weissenborn, Aravindh Mahendran, Thomas Kipf, Austin Stone, Xiao Wang, Zhuoran Shen•Wed May 11 2022

This paper proposes a strong recipe for transferring image-text models to open-vocabulary object detection using a standard Vision Transformer architecture with minimal modifications, contrastive image- text pre-training, and end-to-end detection fine-tuning.

372 0

Paper Graph

One-Shot Object Detection with Co-Attention and Co-Excitation

Hwann-Tzong Chen, Ting-I Hsieh, Yi-Chen Lo, Tyng-Luh Liu•Wed Nov 27 2019

A novel CoAE framework that develops a squeeze-and-co-excitation scheme that can adaptively emphasize correlated feature channels to help uncover relevant proposals and eventually the target objects, and designs a margin-based ranking loss for implicitly learning a metric to predict the similarity of a region proposal to the underlying query.

189 0

Paper Graph

OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features

A. Osokin, Denis Sumin, V. Lomakin•Sat Mar 14 2020

Experimental evaluation shows that the one-stage system that performs localization and recognition jointly can detect unseen classes and outperforms several baselines by a significant margin.

64 0

Paper Graph

One-Shot Object Detection without Fine-Tuning

Yu-Wing Tai, Chi-Keung Tang, Yau Pun Chen, Xiang Li, Lin Zhang•Thu May 07 2020

A two-stage model consisting of a first stage Matching-FCOS network and a second stage Structure-Aware Relation Module is introduced, the combination of which integrates metric learning with an anchor-free Faster R-CNN-style detection pipeline, eventually eliminating the need to fine-tune on the support images.

31 0

Paper Graph

Balanced and Hierarchical Relation Learning for One-shot Object Detection

Jianqiang Huang, Han Yang, Sijia Cai, Hualian Sheng, Bing Deng, Xiansheng Hua, Yong Tang, Yu Zhang•Tue May 31 2022

Instance-level feature matching is significantly important to the success of modern one-shot object detectors. Re-cently, the methods based on the metric-learning paradigm have achieved an impressive process. Most of these works only measure the relations between query and target objects on a single level, resulting in suboptimal performance overall. In this paper, we introduce the balanced and hierarchical learning for our detector. The contributions are two-fold: firstly, a novel Instance-level Hierarchical Relation (IHR) module is proposed to encode the contrastive-level, salient-level, and attention-level relations simultane-ously to enhance the query-relevant similarity representation. Secondly, we notice that the batch training of the IHR module is substantially hindered by the positive-negative sample imbalance in the one-shot scenario. We then in-troduce a simple but effective Ratio-Preserving Loss (RPL) to protect the learning of rare positive samples and sup-press the effects of negative samples. Our loss can adjust the weight for each sample adaptively, ensuring the desired positive-negative ratio consistency and boosting query-related IHR learning. Extensive experiments show that our method outperforms the state-of-the-art method by 1.6% and 1.3% on PASCAL VOC and MS COCO datasets for unseen classes, respectively. The code will be available at https://github.com/hero-y/BHRL.

24 0

Paper Graph

A Few Seconds Can Change Everything: Fast Decision-based Attacks against DNNs

Ningping Mou, Baolin Zheng, Yunjie Ge, Binqing Guo•Thu Jun 30 2022

This work proposes a novel and efficient decision-based attack against black-box models, dubbed FastDrop, which only requires a few queries and work well under strong defenses, and generates adversarial examples by dropping information in the frequency domain.

5 0

Paper Graph

RepMet: Representative-based metric learning for classification and one-shot object detection

Sharath Pankanti, A. Bronstein, Leonid Karlinsky, R. Feris, Sivan Harary, Eli Schwartz, R. Giryes, J. Shtok, Mattias Marder, Abhishek Kumar•Mon Jun 11 2018

This work proposes a new method for DML that simultaneously learns the backbone network parameters, the embedding space, and the multi-modal distribution of each of the training categories in that space, in a single end-to-end training process.

39 0

Paper Graph

Adding a benchmark result helps the community track progress.