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 1020110225 of 10420 papers

TitleStatusHype
Self-Supervised Learning Through Efference CopiesCode0
Task agnostic continual learning with Pairwise layer architectureCode0
Some like it tough: Improving model generalization via progressively increasing the training difficultyCode0
Task2Box: Box Embeddings for Modeling Asymmetric Task RelationshipsCode0
Tactics to Directly Map CNN graphs on Embedded FPGAsCode0
Transformer Meets Twicing: Harnessing Unattended Residual InformationCode0
Tackling Distribution Shifts in Task-Oriented Communication with Information BottleneckCode0
WSAM: Visual Explanations from Style Augmentation as Adversarial Attacker and Their Influence in Image ClassificationCode0
WSEBP: A Novel Width-depth Synchronous Extension-based Basis Pursuit Algorithm for Multi-Layer Convolutional Sparse CodingCode0
Synthetic-Powered Predictive InferenceCode0
Synthetic Medical Images from Dual Generative Adversarial NetworksCode0
SynCo: Synthetic Hard Negatives in Contrastive Learning for Better Unsupervised Visual RepresentationsCode0
Symmetric Cross Entropy for Robust Learning with Noisy LabelsCode0
Wukong: A 100 Million Large-scale Chinese Cross-modal Pre-training BenchmarkCode0
Weakly Supervised Complementary Parts Models for Fine-Grained Image Classification from the Bottom UpCode0
Transformers: State-of-the-Art Natural Language ProcessingCode0
Symbolic Graph Reasoning Meets ConvolutionsCode0
Scaling Federated Learning Solutions with Kubernetes for Synthesizing Histopathology ImagesCode0
Weakly Supervised Domain Adaptation for Built-up Region Segmentation in Aerial and Satellite ImageryCode0
Transforming task representations to perform novel tasksCode0
Symbolic Discovery of Optimization AlgorithmsCode0
Solar Power Plant Detection on Multi-Spectral Satellite Imagery using Weakly-Supervised CNN with Feedback Features and m-PCNN FusionCode0
TransformNet: Self-supervised representation learning through predicting geometric transformationsCode0
Variational Saccading: Efficient Inference for Large Resolution ImagesCode0
Transfusion: Understanding Transfer Learning for Medical ImagingCode0
Show:102550
← PrevPage 409 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