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

Showing 18011850 of 2042 papers

TitleStatusHype
SVM and ELM: Who Wins? Object Recognition with Deep Convolutional Features from ImageNet0
Monocular SLAM Supported Object Recognition0
Exploiting an Oracle that Reports AUC Scores in Machine Learning Contests0
Hyper-Class Augmented and Regularized Deep Learning for Fine-Grained Image Classification0
Regularizing Max-Margin Exemplars by Reconstruction and Generative Models0
Recurrent Convolutional Neural Network for Object Recognition0
Zero-Shot Object Recognition by Semantic Manifold Distance0
Automatically Discovering Local Visual Material Attributes0
Beyond Spatial Pooling: Fine-Grained Representation Learning in Multiple Domains0
A Novel Locally Linear KNN Model for Visual Recognition0
On the Relationship Between Visual Attributes and Convolutional Networks0
Semi-Supervised Domain Adaptation With Subspace Learning for Visual Recognition0
Data-Driven 3D Voxel Patterns for Object Category Recognition0
A Dynamic Programming Approach for Fast and Robust Object Pose Recognition From Range Images0
Is Object Localization for Free? - Weakly-Supervised Learning With Convolutional Neural Networks0
DeepContour: A Deep Convolutional Feature Learned by Positive-Sharing Loss for Contour Detection0
Understanding Tools: Task-Oriented Object Modeling, Learning and Recognition0
CURL: Co-trained Unsupervised Representation Learning for Image Classification0
Texture Synthesis Using Convolutional Neural NetworksCode0
The Best of Both Worlds: Combining Data-independent and Data-driven Approaches for Action Recognition0
Robust Visual Knowledge Transfer via EDA0
Dense Semantic Correspondence where Every Pixel is a Classifier0
PISA: Pixelwise Image Saliency by Aggregating Complementary Appearance Contrast Measures with Edge-Preserving Coherence0
Sparse 3D convolutional neural networksCode0
Improving neural networks with bunches of neurons modeled by Kumaraswamy units: Preliminary study0
Learning to See by Moving0
ReNet: A Recurrent Neural Network Based Alternative to Convolutional NetworksCode0
Deep Learning and Continuous Representations for Natural Language Processing0
Exploit Bounding Box Annotations for Multi-label Object Recognition0
Bio-inspired Unsupervised Learning of Visual Features Leads to Robust Invariant Object Recognition0
Real-world Object Recognition with Off-the-shelf Deep Conv Nets: How Many Objects can iCub Learn?0
Real-time Monocular Object SLAM0
Kernel Manifold AlignmentCode0
A Probabilistic Theory of Deep LearningCode0
The Semantics of Image Annotation0
Generalized K-fan Multimodal Deep Model with Shared Representations0
Factorization of View-Object Manifolds for Joint Object Recognition and Pose Estimation0
Lifting Object Detection Datasets into 3D0
Do We Need More Training Data?0
Modelling Local Deep Convolutional Neural Network Features to Improve Fine-Grained Image Classification0
Learning Descriptors for Object Recognition and 3D Pose Estimation0
Scalable Bayesian Optimization Using Deep Neural NetworksCode0
Unsupervised Network Pretraining via Encoding Human Design0
Measuring and Understanding Sensory Representations within Deep Networks Using a Numerical Optimization Framework0
Incorporating Structural Alternatives and Sharing into Hierarchy for Multiclass Object Recognition and Detection0
DeepID3: Face Recognition with Very Deep Neural NetworksCode0
Hyper-parameter optimization of Deep Convolutional Networks for object recognition0
Deep Learning with Nonparametric ClusteringCode0
A Survey on Recent Advances of Computer Vision Algorithms for Egocentric Video0
From Visual Attributes to Adjectives through Decompositional Distributional Semantics0
Show:102550
← PrevPage 37 of 41Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Imagenshape bias98.7Unverified
2Stable Diffusionshape bias92.7Unverified
3Partishape bias91.7Unverified
4ViT-22B-384shape bias86.4Unverified
5ViT-22B-560shape bias83.8Unverified
6CLIP (ViT-B)shape bias79.9Unverified
7ViT-22B-224shape bias78Unverified
8ResNet-50 (L2 eps 5.0 adv trained)shape bias69.5Unverified
9ResNet-50 (with strong augmentations)shape bias62.2Unverified
10SWSL (ResNeXt-101)shape bias49.8Unverified
#ModelMetricClaimedVerifiedStatus
1Spike-VGG11Accuracy (% )85.55Unverified
2SSNNAccuracy (% )78.57Unverified
#ModelMetricClaimedVerifiedStatus
1Spike-VGG11Accuracy (% )85.62Unverified
2SSNNAccuracy (% )79.25Unverified
#ModelMetricClaimedVerifiedStatus
1ObjectNet-BaselineTop 5 Accuracy18.75Unverified
2yunTop 5 Accuracy14.75Unverified
#ModelMetricClaimedVerifiedStatus
1ObjectNet-BaselineTop 5 Accuracy52.24Unverified
2DYTop 5 Accuracy0.08Unverified
#ModelMetricClaimedVerifiedStatus
1ObjectNet-BaselineTop 5 Accuracy52.24Unverified
2AJ2021Top 5 Accuracy27.68Unverified
#ModelMetricClaimedVerifiedStatus
1SSNNAccuracy (% )94.91Unverified
#ModelMetricClaimedVerifiedStatus
1Faster-RCNNmAP30.39Unverified
#ModelMetricClaimedVerifiedStatus
1Spike-VGG11Accuracy (% )96Unverified