SOTAVerified

Object Categorization

Object categorization identifies which label, from a given set, best corresponds to an image region defined by an input image and bounding box.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 61–70 of 80 papers

TitleStatusHype
Data augmentation instead of explicit regularizationCode0
Learning robust visual representations using data augmentation invarianceCode0
Deep Learning Human Mind for Automated Visual ClassificationCode0
Category-orthogonal object features guide information processing in recurrent neural networks trained for object categorizationCode0
OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning FrameworkCode0
Unsupervised Domain Adaptation through Inter-modal Rotation for RGB-D Object RecognitionCode0
Vocabulary-informed Zero-shot and Open-set LearningCode0
Improved object recognition using neural networks trained to mimic the brain's statistical propertiesCode0
Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representationsCode0
Systematic evaluation of CNN advances on the ImageNetCode0
Show:102550
← PrevPage 7 of 8Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Unified-IOXLCategorization (ablation)61.7—Unverified
2GPV-2Categorization (ablation)54.7—Unverified
3CLIPCategorization (ablation)48.1—Unverified
4OFA_LargeCategorization (ablation)22.6—Unverified