Computer Vision
 
Edit

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.

Source: Metamorphic Testing for Object Detection Systems

Libraries

Use these libraries to find Image Classification models and implementations

Datasets

Subtasks

PairAug: What Can Augmented Image-Text Pairs Do for Radiology?

faceonlive/ai-research • 7 Apr 2024

Acknowledging this limitation, our objective is to devise a framework capable of concurrently augmenting medical image and text data.

144
07 Apr 2024
Paper
Code

Sparse Concept Bottleneck Models: Gumbel Tricks in Contrastive Learning

icml24/sparsecbm • • 4 Apr 2024

We propose a novel architecture and method of explainable classification with Concept Bottleneck Models (CBMs).

1
04 Apr 2024
Paper
Code

DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets

val-iisc/DeiT-LT • • 3 Apr 2024

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.

11
03 Apr 2024
Paper
Code

Guarantees of confidentiality via Hammersley-Chapman-Robbins bounds

facebookresearch/hcrbounds • • 3 Apr 2024

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.

1
03 Apr 2024
Paper
Code

Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual Loss

jaehakim97/sr4ir • • 2 Apr 2024

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.

22
02 Apr 2024
Paper
Code

ImageNot: A contrast with ImageNet preserves model rankings

olawalesalaudeen/imagenot • 2 Apr 2024

We introduce ImageNot, a dataset designed to match the scale of ImageNet while differing drastically in other aspects.

2
02 Apr 2024
Paper
Code

A Universal Knowledge Embedded Contrastive Learning Framework for Hyperspectral Image Classification

quanweiliu/knowcl • • 2 Apr 2024

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.

1
02 Apr 2024
Paper
Code

CAM-Based Methods Can See through Walls

magamedt/cam-can-see-through-walls • • 2 Apr 2024

CAM-based methods are widely-used post-hoc interpretability method that produce a saliency map to explain the decision of an image classification model.

0
02 Apr 2024
Paper
Code

Improving Visual Recognition with Hyperbolical Visual Hierarchy Mapping

kwonjunn01/hi-mapper • 1 Apr 2024

Visual scenes are naturally organized in a hierarchy, where a coarse semantic is recursively comprised of several fine details.

5
01 Apr 2024
Paper
Code

Can Biases in ImageNet Models Explain Generalization?

paulgavrikov/biases_vs_generalization • • 1 Apr 2024

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.

2
01 Apr 2024
Paper
Code
Contact us on: hello@paperswithcode.com . Papers With Code is a free resource with all data licensed under CC-BY-SA.
Terms Data policy Cookies policy