Object detection is the task of detecting instances of objects of a certain class within an image. The state-of-the-art methods can be categorized into two main types: one-stage methods and two stage-methods. One-stage methods prioritize inference speed, and example models include YOLO, SSD and RetinaNet. Two-stage methods prioritize detection accuracy, and example models include Faster R-CNN, Mask R-CNN and Cascade R-CNN.
The most popular benchmark is the MSCOCO dataset. Models are typically evaluated according to a Mean Average Precision metric.
( Image credit: Detectron )
We present a class of efficient models called MobileNets for mobile and embedded vision applications.
Ranked #166 on
Object Detection
on COCO test-dev
We achieve new state of the art results for mobile classification, detection and segmentation.
Ranked #43 on
Semantic Segmentation
on Cityscapes test
IMAGE CLASSIFICATION NEURAL ARCHITECTURE SEARCH OBJECT DETECTION SEMANTIC SEGMENTATION
In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and benchmarks as well as across a spectrum of different model sizes.
Ranked #4 on
Retinal OCT Disease Classification
on OCT2017
IMAGE CLASSIFICATION OBJECT DETECTION PERSON RE-IDENTIFICATION RETINAL OCT DISEASE CLASSIFICATION SEMANTIC SEGMENTATION
Deep residual nets are foundations of our submissions to ILSVRC & COCO 2015 competitions, where we also won the 1st places on the tasks of ImageNet detection, ImageNet localization, COCO detection, and COCO segmentation.
Ranked #2 on
Pedestrian Attribute Recognition
on UAV-Human
DOMAIN GENERALIZATION FINE-GRAINED IMAGE CLASSIFICATION IMAGE-TO-IMAGE TRANSLATION OBJECT DETECTION PEDESTRIAN ATTRIBUTE RECOGNITION PEDESTRIAN TRAJECTORY PREDICTION PERSON RE-IDENTIFICATION RETINAL OCT DISEASE CLASSIFICATION SEMANTIC SEGMENTATION
We propose SpineNet, a backbone with scale-permuted intermediate features and cross-scale connections that is learned on an object detection task by Neural Architecture Search.
Ranked #4 on
Image Classification
on iNaturalist
IMAGE CLASSIFICATION INSTANCE SEGMENTATION NEURAL ARCHITECTURE SEARCH REAL-TIME OBJECT DETECTION
In this paper we propose a method that leverages temporal context from the unlabeled frames of a novel camera to improve performance at that camera.
Model efficiency has become increasingly important in computer vision.
Ranked #1 on
Object Detection
on COCO minival
(AP50 metric)
We model an object as a single point --- the center point of its bounding box.
Ranked #13 on
Real-Time Object Detection
on COCO
(using extra training data)
Models and examples built with TensorFlow
Ranked #11 on
Video Object Detection
on ImageNet VID
OBJECT RECOGNITION REAL-TIME OBJECT DETECTION VIDEO OBJECT DETECTION
The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform.
Ranked #106 on
Object Detection
on COCO test-dev