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 1451–1500 of 2042 papers

TitleStatusHype
Memory Aware Synapses: Learning what (not) to forgetCode0
Context Augmentation for Convolutional Neural Networks—0
Glitch Classification and Clustering for LIGO with Deep Transfer Learning—0
BPGrad: Towards Global Optimality in Deep Learning via Branch and Pruning—0
ADVISE: Symbolism and External Knowledge for Decoding Advertisements—0
Robust Unsupervised Domain Adaptation for Neural Networks via Moment AlignmentCode0
Learning and Visualizing Localized Geometric Features Using 3D-CNN: An Application to Manufacturability Analysis of Drilled HolesCode0
Latent Constrained Correlation Filter—0
Analysis of Dropout in Online Learning—0
Interpreting Convolutional Neural Networks Through Compression—0
Few-Shot Adversarial Domain Adaptation—0
Procedural Text Generation from an Execution Video—0
Cascade Region Proposal and Global Context for Deep Object Detection—0
On Pre-Trained Image Features and Synthetic Images for Deep Learning—0
Object Recognition by Using Multi-level Feature Point Extraction—0
Classification and Geometry of General Perceptual Manifolds—0
Dynamic texture recognition using time-causal and time-recursive spatio-temporal receptive fields—0
Graph Convolutional Networks for Classification with a Structured Label Space—0
Eigen-Distortions of Hierarchical Representations—0
A concatenating framework of shortcut convolutional neural networks—0
Deep Scene Image Classification With the MFAFVNet—0
Understanding Low- and High-Level Contributions to Fixation Prediction—0
Deep Competitive Pathway NetworksCode0
Are we done with object recognition? The iCub robot's perspectiveCode0
A Generic Regression Framework for Pose Recognition on Color and Depth Images—0
Combinational neural network using Gabor filters for the classification of handwritten digits—0
Object Recognition from very few Training Examples for Enhancing Bicycle Maps—0
Recognizing Objects In-the-wild: Where Do We Stand?—0
Construction of Latent Descriptor Space and Inference Model of Hand-Object Interactions—0
An Adaptive Sampling Scheme to Efficiently Train Fully Convolutional Networks for Semantic Segmentation—0
Rotational Subgroup Voting and Pose Clustering for Robust 3D Object Recognition—0
Fine-grained Recognition in the Wild: A Multi-Task Domain Adaptation Approach—0
Complete End-To-End Low Cost Solution To a 3D Scanning System with Integrated Turntable—0
ShapeCodes: Self-Supervised Feature Learning by Lifting Views to Viewgrids—0
ScatterNet Hybrid Deep Learning (SHDL) Network For Object Classification—0
Automatic Dataset Augmentation—0
One-Shot Concept Learning by Simulating Evolutionary Instinct Development—0
CNN Fixations: An unraveling approach to visualize the discriminative image regionsCode0
Incorporating Copying Mechanism in Image Captioning for Learning Novel Objects—0
Knock-Knock: Acoustic Object Recognition by using Stacked Denoising Autoencoders—0
Belief Tree Search for Active Object Recognition—0
Chessboard and chess piece recognition with the support of neural networksCode0
Personalized Cinemagraphs using Semantic Understanding and Collaborative Learning—0
Temporal Dynamic Graph LSTM for Action-driven Video Object Detection—0
Fashioning with Networks: Neural Style Transfer to Design Clothes—0
Analysis and Optimization of Convolutional Neural Network ArchitecturesCode0
An Effective Training Method For Deep Convolutional Neural Network—0
Capacity limitations of visual search in deep convolutional neural networks—0
Improving Robustness of Feature Representations to Image Deformations using Powered Convolution in CNNs—0
Infinite Latent Feature Selection: A Probabilistic Latent Graph-Based Ranking Approach—0
Show:102550
← PrevPage 30 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