Object Recognition

Object recognition is a computer vision technique for detecting + classifying objects in images or videos. Since this is a combined task of object detection plus image classification, the state-of-the-art tables are recorded for each component task here and here.

( Image credit: Tensorflow Object Detection API )

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 191–200 of 2042 papers

Title	Date	Tasks	Status	Hype
OPFython: A Python-Inspired Optimum-Path Forest Classifier	Jan 28, 2020	DiversityGeneral Classification	CodeCode Available	1
Brain-Score: Which Artificial Neural Network for Object Recognition is most Brain-Like?	Jan 2, 2020	Object Recognition	CodeCode Available	1
Rehearsal-Free Continual Learning over Small Non-I.I.D. Batches	Jul 8, 2019	class-incremental learningClass Incremental Learning	CodeCode Available	1
Billion-scale semi-supervised learning for image classification	May 2, 2019	ClassificationGeneral Classification	CodeCode Available	1
Efficient Attention: Attention with Linear Complexities	Dec 4, 2018	Depth EstimationExtractive Text Summarization	CodeCode Available	1
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness	Nov 29, 2018	Domain GeneralizationImage Classification	CodeCode Available	1
Compact Generalized Non-local Network	Oct 31, 2018	Object DetectionObject Recognition	CodeCode Available	1
PCL: Proposal Cluster Learning for Weakly Supervised Object Detection	Jul 9, 2018	image-classificationMultiple Instance Learning	CodeCode Available	1
Task-Driven Convolutional Recurrent Models of the Visual System	Jun 20, 2018	General ClassificationObject Recognition	CodeCode Available	1
Why do deep convolutional networks generalize so poorly to small image transformations?	May 30, 2018	Data AugmentationObject Recognition	CodeCode Available	1

Show:10 25 50

← PrevPage 20 of 205Next →

All datasets shape bias CIFAR10-DVS N-Caltech 101 ObjectNet (All classes)ObjectNet (ImageNet classes)ObjectNet (ImageNet classes, trained on ImageNet)DVS128 Gesture MECCANO N-CARS

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Imagen	shape bias	98.7	—	Unverified
2	Stable Diffusion	shape bias	92.7	—	Unverified
3	Parti	shape bias	91.7	—	Unverified
4	ViT-22B-384	shape bias	86.4	—	Unverified
5	ViT-22B-560	shape bias	83.8	—	Unverified
6	CLIP (ViT-B)	shape bias	79.9	—	Unverified
7	ViT-22B-224	shape bias	78	—	Unverified
8	ResNet-50 (L2 eps 5.0 adv trained)	shape bias	69.5	—	Unverified
9	ResNet-50 (with strong augmentations)	shape bias	62.2	—	Unverified
10	SWSL (ResNeXt-101)	shape bias	49.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Spike-VGG11	Accuracy (% )	85.55	—	Unverified
2	SSNN	Accuracy (% )	78.57	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Spike-VGG11	Accuracy (% )	85.62	—	Unverified
2	SSNN	Accuracy (% )	79.25	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ObjectNet-Baseline	Top 5 Accuracy	18.75	—	Unverified
2	yun	Top 5 Accuracy	14.75	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ObjectNet-Baseline	Top 5 Accuracy	52.24	—	Unverified
2	DY	Top 5 Accuracy	0.08	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	ObjectNet-Baseline	Top 5 Accuracy	52.24	—	Unverified
2	AJ2021	Top 5 Accuracy	27.68	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SSNN	Accuracy (% )	94.91	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Faster-RCNN	mAP	30.39	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Spike-VGG11	Accuracy (% )	96	—	Unverified