OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features (2020-03-15T00:00:00.000000Z)

TL;DR

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.

Abstract

In this paper, we consider the task of one-shot object detection, which consists in detecting objects defined by a single demonstration. Differently from the standard object detection, the classes of objects used for training and testing do not overlap. We build the one-stage system that performs localization and recognition jointly. We use dense correlation matching of learned local features to find correspondences, a feed-forward geometric transformation model to align features and bilinear resampling of the correlation tensor to compute the detection score of the aligned features. All the components are differentiable, which allows end-to-end training. Experimental evaluation on several challenging domains (retail products, 3D objects, buildings and logos) shows that our method can detect unseen classes (e.g., toothpaste when trained on groceries) and outperforms several baselines by a significant margin. Our code is available online: this https URL .

Authors

A. Osokin

3 papers

Denis Sumin

1 papers

V. Lomakin

1 papers

TL;DR

Abstract

Authors

References56 items

Frustratingly Simple Few-Shot Object Detection

Incremental Few-Shot Object Detection

PyTorch: An Imperative Style, High-Performance Deep Learning Library

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

Convolutional Neural Network Architecture for Geometric Matching

Meta-Learning to Detect Rare Objects

Meta R-CNN: Towards General Solver for Instance-Level Low-Shot Learning

Few-Shot Object Detection With Attention-RPN and Multi-Relation Detector

Precise Detection in Densely Packed Scenes

Ranked List Loss for Deep Metric Learning

Few-Shot Object Detection via Feature Reweighting

One-Shot Instance Segmentation

Neighbourhood Consensus Networks

RepMet: Representative-Based Metric Learning for Classification and Few-Shot Object Detection

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

NetVLAD: CNN Architecture for Weakly Supervised Place Recognition

High Performance Visual Tracking with Siamese Region Proposal Network

Group Normalization

LSTD: A Low-Shot Transfer Detector for Object Detection

End-to-End Weakly-Supervised Semantic Alignment

Non-local Neural Networks

Fine-Tuning CNN Image Retrieval with No Human Annotation

Focal Loss for Dense Object Detection

Beyond Instance-Level Image Retrieval: Leveraging Captions to Learn a Global Visual Representation for Semantic Retrieval

Sampling Matters in Deep Embedding Learning

End-to-End Representation Learning for Correlation Filter Based Tracking

YOLO9000: Better, Faster, Stronger

Large-Scale Image Retrieval with Attentive Deep Local Features

Feature Pyramid Networks for Object Detection

Efficient Diffusion on Region Manifolds: Recovering Small Objects with Compact CNN Representations

End-to-End Learning of Deep Visual Representations for Image Retrieval

Fully-Convolutional Siamese Networks for Object Tracking

CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examples

SSD: Single Shot MultiBox Detector

Discriminative Learning of Deep Convolutional Feature Point Descriptors

NetVLAD: CNN Architecture for Weakly Supervised Place Recognition

You Only Look Once: Unified, Real-Time Object Detection

Spatial Transformer Networks

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Fast R-CNN

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

INSTRE

Recognizing Products: A Per-exemplar Multi-label Image Classification Approach

ImageNet Large Scale Visual Recognition Challenge

Microsoft COCO: Common Objects in Context

Neural Codes for Image Retrieval

OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks

Deep Neural Networks for Object Detection

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

What is an object?

Deep learning from temporal coherence in video

Distinctive Image Features from Scale-Invariant Keypoints

Object recognition from local scale-invariant features

maskrcnn-benchmark: fast, modular reference implementation of instance segmentation and object detection algorithms in PyTorch

Siamese Neural Networks for One-Shot Image Recognition

Edinburgh Research Explorer The PASCAL Visual Object Classes (VOC) Challenge

Field of Study

Venue Information

Name

Type

URL

Alternate Names