SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1251–1300 of 2042 papers

TitleStatusHype
OrthographicNet: A Deep Transfer Learning Approach for 3D Object Recognition in Open-Ended DomainsCode0
Minimal Images in Deep Neural Networks: Fragile Object Recognition in Natural Images—0
Software-Defined FPGA Accelerator Design for Mobile Deep Learning Applications—0
Lift-the-flap: what, where and when for context reasoning—0
Semantic Redundancies in Image-Classification Datasets: The 10% You Don't Need—0
Bridging the Gap Between Computational Photography and Visual Recognition—0
State-Regularized Recurrent Neural Networks—0
Imaging-free object recognition enabled by optical coherence—0
Overfitting Mechanism and Avoidance in Deep Neural Networks—0
Multisource Region Attention Network for Fine-Grained Object Recognition in Remote Sensing Imagery—0
Machine learning with neural networksCode0
Characterizing and evaluating adversarial examples for Offline Handwritten Signature VerificationCode0
Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Vision—0
Volumetric Convolution: Automatic Representation Learning in Unit Ball—0
Pixel personality for dense object tracking in a 2D honeybee hive—0
DCI: Discriminative and Contrast Invertible Descriptor—0
Fine-tuning Convolutional Neural Networks for fine art classification—0
Artistic Object Recognition by Unsupervised Style Adaptation—0
Deep Metric Transfer for Label Propagation with Limited Annotated DataCode0
Robust Graph Learning from Noisy DataCode0
Pre-Trained Convolutional Neural Network Features for Facial Expression Recognition—0
Using Motion and Internal Supervision in Object Recognition—0
Grounded Human-Object Interaction Hotspots from VideoCode0
Deep RBFNet: Point Cloud Feature Learning using Radial Basis Functions—0
Spectral Illumination Correction: Achieving Relative Color Constancy Under the Spectral DomainCode0
Efficient Attention: Attention with Linear ComplexitiesCode1
Global Second-order Pooling Convolutional NetworksCode0
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnessCode1
A randomized gradient-free attack on ReLU networks—0
A Convolutional Neural Network based Live Object Recognition System as Blind Aid—0
Task-generalizable Adversarial Attack based on Perceptual MetricCode0
Artificial Color Constancy via GoogLeNet with Angular Loss FunctionCode0
Sequence-based Person Attribute Recognition with Joint CTC-Attention Model—0
CIFAR10 to Compare Visual Recognition Performance between Deep Neural Networks and Humans—0
PydMobileNet: Improved Version of MobileNets with Pyramid Depthwise Separable ConvolutionCode0
Application of Faster R-CNN model on Human Running Pattern Recognition—0
A Framework of Transfer Learning in Object Detection for Embedded SystemsCode0
Breast Cancer Classification from Histopathological Images with Inception Recurrent Residual Convolutional Neural NetworkCode0
Multi-label Object Attribute Classification using a Convolutional Neural Network—0
The Effect of Learning Strategy versus Inherent Architecture Properties on the Ability of Convolutional Neural Networks to Develop Transformation Invariance—0
Analyzing biological and artificial neural networks: challenges with opportunities for synergy?—0
Compact Generalized Non-local NetworkCode1
Object Detection based on LIDAR Temporal Pulses using Spiking Neural Networks—0
UAVid: A Semantic Segmentation Dataset for UAV ImageryCode0
Improving Annotation for 3D Pose Dataset of Fine-Grained Object CategoriesCode0
CURE-OR: Challenging Unreal and Real Environments for Object RecognitionCode0
The Newton Scheme for Deep Learning—0
Point Cloud GANCode0
Efficient architecture for deep neural networks with heterogeneous sensitivity—0
Seeing Beyond Appearance - Mapping Real Images into Geometrical Domains for Unsupervised CAD-based Recognition—0
Show:102550
← PrevPage 26 of 41Next →
All datasetsshape biasCIFAR10-DVSN-Caltech 101ObjectNet (All classes)ObjectNet (ImageNet classes)ObjectNet (ImageNet classes, trained on ImageNet)DVS128 GestureMECCANON-CARS

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Imagenshape bias98.7—Unverified
2Stable Diffusionshape bias92.7—Unverified
3Partishape bias91.7—Unverified
4ViT-22B-384shape bias86.4—Unverified
5ViT-22B-560shape bias83.8—Unverified
6CLIP (ViT-B)shape bias79.9—Unverified
7ViT-22B-224shape bias78—Unverified
8ResNet-50 (L2 eps 5.0 adv trained)shape bias69.5—Unverified
9ResNet-50 (with strong augmentations)shape bias62.2—Unverified
10SWSL (ResNeXt-101)shape bias49.8—Unverified
#ModelMetricClaimedVerifiedStatus
1Spike-VGG11Accuracy (% )85.55—Unverified
2SSNNAccuracy (% )78.57—Unverified
#ModelMetricClaimedVerifiedStatus
1Spike-VGG11Accuracy (% )85.62—Unverified
2SSNNAccuracy (% )79.25—Unverified
#ModelMetricClaimedVerifiedStatus
1ObjectNet-BaselineTop 5 Accuracy18.75—Unverified
2yunTop 5 Accuracy14.75—Unverified
#ModelMetricClaimedVerifiedStatus
1ObjectNet-BaselineTop 5 Accuracy52.24—Unverified
2DYTop 5 Accuracy0.08—Unverified
#ModelMetricClaimedVerifiedStatus
1ObjectNet-BaselineTop 5 Accuracy52.24—Unverified
2AJ2021Top 5 Accuracy27.68—Unverified
#ModelMetricClaimedVerifiedStatus
1SSNNAccuracy (% )94.91—Unverified
#ModelMetricClaimedVerifiedStatus
1Faster-RCNNmAP30.39—Unverified
#ModelMetricClaimedVerifiedStatus
1Spike-VGG11Accuracy (% )96—Unverified