Browse SoTA > Computer Vision > Object Localization

Object Localization

63 papers with code · Computer Vision

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

Latest papers without code

Entropy Guided Adversarial Model for Weakly Supervised Object Localization

4 Aug 2020

Unfortunately, the network activates only the features that discriminate the object and does not activate the whole object.

WEAKLY-SUPERVISED OBJECT LOCALIZATION

Eigen-CAM: Class Activation Map using Principal Components

1 Aug 2020

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

Object-Aware Centroid Voting for Monocular 3D Object Detection

20 Jul 2020

Monocular 3D object detection aims to detect objects in a 3D physical world from a single camera.

DEPTH ESTIMATION MONOCULAR 3D OBJECT DETECTION OBJECT LOCALIZATION

Geometry Constrained Weakly Supervised Object Localization

19 Jul 2020

The detector predicts the object location defined by a set of coefficients describing a geometric shape (i. e. ellipse or rectangle), which is geometrically constrained by the mask produced by the generator.

WEAKLY-SUPERVISED OBJECT LOCALIZATION

Training Interpretable Convolutional Neural Networks by Differentiating Class-specific Filters

16 Jul 2020

Most existing works attempt post-hoc interpretation on a pre-trained model, while neglecting to reduce the entanglement underlying the model.

OBJECT LOCALIZATION

MoNet3D: Towards Accurate Monocular 3D Object Localization in Real Time

29 Jun 2020

Monocular multi-object detection and localization in 3D space has been proven to be a challenging task.

MONOCULAR 3D OBJECT LOCALIZATION OBJECT DETECTION

Boundary Regularized Building Footprint Extraction From Satellite Images Using Deep Neural Network

23 Jun 2020

The proposed deep learning method consists of a two-stage object detection network to produce region of interest (RoI) features and a building boundary extraction network using graph models to learn geometric information of the polygon shapes.

OBJECT DETECTION OBJECT LOCALIZATION

Rethinking Localization Map: Towards Accurate Object Perception with Self-Enhancement Maps

9 Jun 2020

To fulfill the direct evaluation, we annotate pixel-level object masks on the ILSVRC validation set.

WEAKLY-SUPERVISED OBJECT LOCALIZATION

Evaluating Weakly Supervised Object Localization Methods Right

CVPR 2020

In this paper, we argue that WSOL task is ill-posed with only image-level labels, and propose a new evaluation protocol where full supervision is limited to only a small held-out set not overlapping with the test set.

FEW-SHOT LEARNING MODEL SELECTION WEAKLY-SUPERVISED OBJECT LOCALIZATION

Sub-Frame Appearance and 6D Pose Estimation of Fast Moving Objects

CVPR 2020

We propose a novel method that tracks fast moving objects, mainly non-uniform spherical, in full 6 degrees of freedom, estimating simultaneously their 3D motion trajectory, 3D pose and object appearance changes with a time step that is a fraction of the video frame exposure time.

6D POSE ESTIMATION DEBLURRING OBJECT LOCALIZATION SUPER-RESOLUTION