SOTAVerified

Image Classification

Image Classification is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike object detection, which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as image retrieval, which also involves finding similar images in a large database.

Source: Metamorphic Testing for Object Detection Systems

Papers

Showing 89518975 of 10420 papers

TitleStatusHype
Iterative Reorganization with Weak Spatial Constraints: Solving Arbitrary Jigsaw Puzzles for Unsupervised Representation LearningCode1
ProxylessNAS: Direct Neural Architecture Search on Target Task and HardwareCode2
GLoMo: Unsupervised Learning of Transferable Relational Graphs0
Modern Neural Networks Generalize on Small Data Sets0
Learning to Specialize with Knowledge Distillation for Visual Question Answering0
MetaGAN: An Adversarial Approach to Few-Shot Learning0
Symbolic Graph Reasoning Meets ConvolutionsCode0
Thwarting Adversarial Examples: An L_0-Robust Sparse Fourier Transform0
Structure-Aware Convolutional Neural NetworksCode0
Stochastic Training of Residual Networks: a Differential Equation Viewpoint0
Snapshot Distillation: Teacher-Student Optimization in One Generation0
Classifying a specific image region using convolutional nets with an ROI mask as inputCode0
Modeling natural language emergence with integral transform theory and reinforcement learningCode0
On the Computational Inefficiency of Large Batch Sizes for Stochastic Gradient Descent0
Graph-Based Global Reasoning NetworksCode0
Effective, Fast, and Memory-Efficient Compressed Multi-function Convolutional Neural Networks for More Accurate Medical Image Classification0
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnessCode1
Generalized Coarse-to-Fine Visual Recognition with Progressive Training0
TEA-DNN: the Quest for Time-Energy-Accuracy Co-optimized Deep Neural Networks0
Unsupervised Meta-Learning For Few-Shot Image Classification0
Adversarial Attacks for Optical Flow-Based Action Recognition Classifiers0
ESPNetv2: A Light-weight, Power Efficient, and General Purpose Convolutional Neural NetworkCode0
Sequentially Aggregated Convolutional NetworksCode0
Efficient non-uniform quantizer for quantized neural network targeting reconfigurable hardware0
Stochastic Gradient Push for Distributed Deep LearningCode0
Show:102550
← PrevPage 359 of 417Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94Unverified
4DaViT-GTop 1 Accuracy90.4Unverified
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
6DaViT-HTop 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10RevCol-HTop 1 Accuracy90Unverified