About

Object Localization is the task of locating an instance of a particular object category in an image, typically by specifying a tightly cropped bounding box centered on the instance. An object proposal specifies a candidate bounding box, and an object proposal is said to be a correct localization if it sufficiently overlaps a human-labeled “ground-truth” bounding box for the given object. In the literature, the “Object Localization” task is to locate one instance of an object category, whereas “object detection” focuses on locating all instances of a category in a given image.

Source: Fast On-Line Kernel Density Estimation for Active Object Localization

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Subtasks

Datasets

Greatest papers with code

Grid R-CNN

CVPR 2019 open-mmlab/mmdetection

This paper proposes a novel object detection framework named Grid R-CNN, which adopts a grid guided localization mechanism for accurate object detection.

OBJECT DETECTION OBJECT LOCALIZATION

Learning Deep Features for Discriminative Localization

CVPR 2016 tensorpack/tensorpack

In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network to have remarkable localization ability despite being trained on image-level labels.

WEAKLY-SUPERVISED OBJECT LOCALIZATION

VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detection

CVPR 2018 charlesq34/pointnet

Accurate detection of objects in 3D point clouds is a central problem in many applications, such as autonomous navigation, housekeeping robots, and augmented/virtual reality.

3D OBJECT DETECTION AUTONOMOUS NAVIGATION FEATURE ENGINEERING OBJECT LOCALIZATION REGION PROPOSAL

Eigen-CAM: Class Activation Map using Principal Components

1 Aug 2020jacobgil/pytorch-grad-cam

At the heart of this progress is convolutional neural networks (CNNs) that are capable of learning representations or features given a set of data.

WEAKLY-SUPERVISED OBJECT LOCALIZATION

Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks

30 Oct 2017jacobgil/pytorch-grad-cam

Over the last decade, Convolutional Neural Network (CNN) models have been highly successful in solving complex vision problems.

3D ACTION RECOGNITION KNOWLEDGE DISTILLATION OBJECT LOCALIZATION

Dilated Residual Networks

CVPR 2017 osmr/imgclsmob

Convolutional networks for image classification progressively reduce resolution until the image is represented by tiny feature maps in which the spatial structure of the scene is no longer discernible.

CLASSIFICATION IMAGE CLASSIFICATION OBJECT LOCALIZATION SCENE UNDERSTANDING SEMANTIC SEGMENTATION

Deep Snake for Real-Time Instance Segmentation

CVPR 2020 zju3dv/snake

Based on deep snake, we develop a two-stage pipeline for instance segmentation: initial contour proposal and contour deformation, which can handle errors in object localization.

OBJECT LOCALIZATION REAL-TIME INSTANCE SEGMENTATION SEMANTIC CONTOUR PREDICTION SEMANTIC SEGMENTATION

Kimera: from SLAM to Spatial Perception with 3D Dynamic Scene Graphs

18 Jan 2021MIT-SPARK/Kimera

This mental model captures geometric and semantic aspects of the scene, describes the environment at multiple levels of abstractions (e. g., objects, rooms, buildings), includes static and dynamic entities and their relations (e. g., a person is in a room at a given time).

3D RECONSTRUCTION OBJECT LOCALIZATION SCENE PARSING VISUAL LOCALIZATION