Image Classification
3777 papers with code • 168 benchmarks • 240 datasets
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.
Libraries
Use these libraries to find Image Classification models and implementationsDatasets
Subtasks
- Out of Distribution (OOD) Detection
- Few-Shot Image Classification
- Fine-Grained Image Classification
- Semi-Supervised Image Classification
- Semi-Supervised Image Classification
- Learning with noisy labels
- Hyperspectral Image Classification
- Self-Supervised Image Classification
- Small Data Image Classification
- Multi-Label Image Classification
- Genre classification
- Sequential Image Classification
- Unsupervised Image Classification
- Efficient ViTs
- Document Image Classification
- Satellite Image Classification
- Sparse Representation-based Classification
- Photo geolocation estimation
- Image Classification with Differential Privacy
- Token Reduction
- Superpixel Image Classification
- Classification Consistency
- Gallbladder Cancer Detection
- Artistic style classification
- Artist classification
- Temporal Metadata Manipulation Detection
- Misclassification Rate - Natural Adversarial Samples
- Scale Generalisation
Latest papers
PairAug: What Can Augmented Image-Text Pairs Do for Radiology?
Acknowledging this limitation, our objective is to devise a framework capable of concurrently augmenting medical image and text data.
Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning
We propose a novel architecture and method of explainable classification with Concept Bottleneck Models (CBMs).
DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets
In DeiT-LT, we introduce an efficient and effective way of distillation from CNN via distillation DIST token by using out-of-distribution images and re-weighting the distillation loss to enhance focus on tail classes.
Guarantees of confidentiality via Hammersley-Chapman-Robbins bounds
The HCR bounds appear to be insufficient on their own to guarantee confidentiality of the inputs to inference with standard deep neural nets, "ResNet-18" and "Swin-T," pre-trained on the data set, "ImageNet-1000," which contains 1000 classes.
Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual Loss
Through extensive experiments, we demonstrate that our SR4IR achieves outstanding task performance by generating SR images useful for a specific image recognition task, including semantic segmentation, object detection, and image classification.
ImageNot: A contrast with ImageNet preserves model rankings
We introduce ImageNot, a dataset designed to match the scale of ImageNet while differing drastically in other aspects.
A Universal Knowledge Embedded Contrastive Learning Framework for Hyperspectral Image Classification
Therefore, we propose a universal knowledge embedded contrastive learning framework (KnowCL) for supervised, unsupervised, and semisupervised HSI classification, which largely closes the gap of HSI classification models between pocket models and standard vision backbones.
CAM-Based Methods Can See through Walls
CAM-based methods are widely-used post-hoc interpretability method that produce a saliency map to explain the decision of an image classification model.
Improving Visual Recognition with Hyperbolical Visual Hierarchy Mapping
Visual scenes are naturally organized in a hierarchy, where a coarse semantic is recursively comprised of several fine details.
Can Biases in ImageNet Models Explain Generalization?
The robust generalization of models to rare, in-distribution (ID) samples drawn from the long tail of the training distribution and to out-of-training-distribution (OOD) samples is one of the major challenges of current deep learning methods.