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 with code

A Generic Visualization Approach for Convolutional Neural Networks

19 Jul 2020ahmdtaha/constrained_attention_filter

Compared to classification networks, attention visualization for retrieval networks is hardly studied.

WEAKLY-SUPERVISED OBJECT LOCALIZATION

21
19 Jul 2020

RepPoints V2: Verification Meets Regression for Object Detection

16 Jul 2020Scalsol/RepPointsV2

Though RepPoints provides high performance, we find that its heavy reliance on regression for object localization leaves room for improvement.

INSTANCE SEGMENTATION OBJECT DETECTION OBJECT LOCALIZATION SEMANTIC SEGMENTATION

156
16 Jul 2020

Cross-Modal Weighting Network for RGB-D Salient Object Detection

9 Jul 2020MathLee/CMWNet

In this paper, we propose a novel Cross-Modal Weighting (CMW) strategy to encourage comprehensive interactions between RGB and depth channels for RGB-D SOD.

OBJECT LOCALIZATION SALIENT OBJECT DETECTION

12
09 Jul 2020

Evaluation for Weakly Supervised Object Localization: Protocol, Metrics, and Datasets

8 Jul 2020clovaai/wsolevaluation

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

158
08 Jul 2020

Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation

3 Jul 2020GuoleiSun/MCIS_wsss

Moreover, our approach ranked 1st place in the Weakly-Supervised Semantic Segmentation Track of CVPR2020 Learning from Imperfect Data Challenge.

OBJECT LOCALIZATION WEAKLY-SUPERVISED SEMANTIC SEGMENTATION

49
03 Jul 2020

Weakly Supervised Segmentation with Multi-scale Adversarial Attention Gates

2 Jul 2020gvalvano/multiscale-adversarial-attention-gates

With unpaired segmentation masks, we train a multi-scale GAN to generate realistic segmentation masks at multiple resolutions, while we use scribbles to learn the correct position in the image.

MULTI-TASK LEARNING OBJECT LOCALIZATION SEMANTIC SEGMENTATION

1
02 Jul 2020

Distilling Knowledge from Refinement in Multiple Instance Detection Networks

23 Apr 2020luiszeni/Boosted-OICR

Then, we present an adaptive supervision aggregation function that dynamically changes the aggregation criteria for selecting boxes related to one of the ground-truth classes, background, or even ignored during the generation of each refinement module supervision.

MULTIPLE INSTANCE LEARNING WEAKLY SUPERVISED OBJECT DETECTION WEAKLY-SUPERVISED OBJECT LOCALIZATION

15
23 Apr 2020

Dual-attention Guided Dropblock Module for Weakly Supervised Object Localization

9 Mar 2020cpuimage/DualAttentionGuidedDropout

This module contains two key components, the channel attention guided dropout (CAGD) and the spatial attention guided dropblock (SAGD).

WEAKLY-SUPERVISED OBJECT LOCALIZATION

2
09 Mar 2020

Evaluating Weakly Supervised Object Localization Methods Right

CVPR 2020 clovaai/wsolevaluation

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

158
21 Jan 2020

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

663
06 Jan 2020