Computer Vision
- Original Link : https://keras.io/examples/vision/
- Last Checked at : 2024-11-21
Image classification
Image segmentation
| Starter | Keras Version | Title | Date Created | Last Modified |
|---|---|---|---|---|
| ★ | V3 | Image segmentation with a U-Net-like architecture | 2019/03/20 | 2020/04/20 |
| V3 | Multiclass semantic segmentation using DeepLabV3+ | 2021/08/31 | 2024/01/05 | |
| V2 | Highly accurate boundaries segmentation using BASNet | 2023/05/30 | 2023/07/13 | |
| V3 | Image Segmentation using Composable Fully-Convolutional Networks | 2023/06/16 | 2023/12/25 |
| Starter | Keras Version | Title | Date Created | Last Modified ▼ |
|---|---|---|---|---|
| V3 | Multiclass semantic segmentation using DeepLabV3+ | 2021/08/31 | 2024/01/05 | |
| V3 | Image Segmentation using Composable Fully-Convolutional Networks | 2023/06/16 | 2023/12/25 | |
| V2 | Highly accurate boundaries segmentation using BASNet | 2023/05/30 | 2023/07/13 | |
| ★ | V3 | Image segmentation with a U-Net-like architecture | 2019/03/20 | 2020/04/20 |
Object detection
| Starter | Keras Version | Title | Date Created | Last Modified |
|---|---|---|---|---|
| V2 | Object Detection with RetinaNet | 2020/05/17 | 2023/07/10 | |
| V3 | Keypoint Detection with Transfer Learning | 2021/05/02 | 2023/07/19 | |
| V3 | Object detection with Vision Transformers | 2022/03/27 | 2023/11/20 |
| Starter | Keras Version | Title | Date Created | Last Modified ▼ |
|---|---|---|---|---|
| V3 | Object detection with Vision Transformers | 2022/03/27 | 2023/11/20 | |
| V3 | Keypoint Detection with Transfer Learning | 2021/05/02 | 2023/07/19 | |
| V2 | Object Detection with RetinaNet | 2020/05/17 | 2023/07/10 |
3D
| Starter | Keras Version | Title | Date Created | Last Modified |
|---|---|---|---|---|
| V3 | 3D image classification from CT scans | 2020/09/23 | 2024/01/11 | |
| V3 | Monocular depth estimation | 2021/08/30 | 2024/08/13 | |
| ★ | V3 | 3D volumetric rendering with NeRF | 2021/08/09 | 2023/11/13 |
| V3 | Point cloud segmentation with PointNet | 2020/10/23 | 2020/10/24 | |
| V3 | Point cloud classification with PointNet | 2020/05/25 | 2024/01/09 |
| Starter | Keras Version | Title | Date Created | Last Modified ▼ |
|---|---|---|---|---|
| V3 | Monocular depth estimation | 2021/08/30 | 2024/08/13 | |
| V3 | 3D image classification from CT scans | 2020/09/23 | 2024/01/11 | |
| V3 | Point cloud classification with PointNet | 2020/05/25 | 2024/01/09 | |
| ★ | V3 | 3D volumetric rendering with NeRF | 2021/08/09 | 2023/11/13 |
| V3 | Point cloud segmentation with PointNet | 2020/10/23 | 2020/10/24 |
OCR
| Starter | Keras Version | Title | Date Created | Last Modified |
|---|---|---|---|---|
| V3 | OCR model for reading Captchas | 2020/06/14 | 2024/03/13 | |
| V3 | Handwriting recognition | 2021/08/16 | 2024/09/01 |
| Starter | Keras Version | Title | Date Created | Last Modified ▼ |
|---|---|---|---|---|
| V3 | Handwriting recognition | 2021/08/16 | 2024/09/01 | |
| V3 | OCR model for reading Captchas | 2020/06/14 | 2024/03/13 |
Image enhancement
| Starter | Keras Version | Title | Date Created | Last Modified |
|---|---|---|---|---|
| V3 | Convolutional autoencoder for image denoising | 2021/03/01 | 2021/03/01 | |
| V3 | Low-light image enhancement using MIRNet | 2021/09/11 | 2023/07/15 | |
| V3 | Image Super-Resolution using an Efficient Sub-Pixel CNN | 2020/07/28 | 2020/08/27 | |
| V3 | Enhanced Deep Residual Networks for single-image super-resolution | 2022/04/07 | 2024/08/27 | |
| V3 | Zero-DCE for low-light image enhancement | 2021/09/18 | 2023/07/15 |
| Starter | Keras Version | Title | Date Created | Last Modified ▼ |
|---|---|---|---|---|
| V3 | Enhanced Deep Residual Networks for single-image super-resolution | 2022/04/07 | 2024/08/27 | |
| V3 | Low-light image enhancement using MIRNet | 2021/09/11 | 2023/07/15 | |
| V3 | Zero-DCE for low-light image enhancement | 2021/09/18 | 2023/07/15 | |
| V3 | Convolutional autoencoder for image denoising | 2021/03/01 | 2021/03/01 | |
| V3 | Image Super-Resolution using an Efficient Sub-Pixel CNN | 2020/07/28 | 2020/08/27 |
Data augmentation
| Starter | Keras Version | Title | Date Created | Last Modified |
|---|---|---|---|---|
| V3 | CutMix data augmentation for image classification | 2021/06/08 | 2023/11/14 | |
| V3 | MixUp augmentation for image classification | 2021/03/06 | 2023/07/24 | |
| V3 | RandAugment for Image Classification for Improved Robustness | 2021/03/13 | 2023/12/12 |
| Starter | Keras Version | Title | Date Created | Last Modified ▼ |
|---|---|---|---|---|
| V3 | RandAugment for Image Classification for Improved Robustness | 2021/03/13 | 2023/12/12 | |
| V3 | CutMix data augmentation for image classification | 2021/06/08 | 2023/11/14 | |
| V3 | MixUp augmentation for image classification | 2021/03/06 | 2023/07/24 |
Image & Text
| Starter | Keras Version | Title | Date Created | Last Modified |
|---|---|---|---|---|
| ★ | V3 | Image Captioning | 2021/05/29 | 2021/10/31 |
| V2 | Natural language image search with a Dual Encoder | 2021/01/30 | 2021/01/30 |
| Starter | Keras Version | Title | Date Created | Last Modified ▼ |
|---|---|---|---|---|
| ★ | V3 | Image Captioning | 2021/05/29 | 2021/10/31 |
| V2 | Natural language image search with a Dual Encoder | 2021/01/30 | 2021/01/30 |
Vision models interpretability
| Starter | Keras Version | Title | Date Created | Last Modified |
|---|---|---|---|---|
| V3 | Visualizing what convnets learn | 2020/05/29 | 2020/05/29 | |
| V3 | Model interpretability with Integrated Gradients | 2020/06/02 | 2020/06/02 | |
| V3 | Investigating Vision Transformer representations | 2022/04/12 | 2023/11/20 | |
| V3 | Grad-CAM class activation visualization | 2020/04/26 | 2021/03/07 |
| Starter | Keras Version | Title | Date Created | Last Modified ▼ |
|---|---|---|---|---|
| V3 | Investigating Vision Transformer representations | 2022/04/12 | 2023/11/20 | |
| V3 | Grad-CAM class activation visualization | 2020/04/26 | 2021/03/07 | |
| V3 | Model interpretability with Integrated Gradients | 2020/06/02 | 2020/06/02 | |
| V3 | Visualizing what convnets learn | 2020/05/29 | 2020/05/29 |
Image similarity search
| Starter | Keras Version | Title | Date Created | Last Modified |
|---|---|---|---|---|
| V2 | Near-duplicate image search | 2021/09/10 | 2023/08/30 | |
| V3 | Semantic Image Clustering | 2021/02/28 | 2021/02/28 | |
| V3 | Image similarity estimation using a Siamese Network with a contrastive loss | 2021/05/06 | 2022/09/10 | |
| V3 | Image similarity estimation using a Siamese Network with a triplet loss | 2021/03/25 | 2021/03/25 | |
| V3 | Metric learning for image similarity search | 2020/06/05 | 2020/06/09 | |
| V2 | Metric learning for image similarity search using TensorFlow Similarity | 2021/09/30 | 2022/02/29 | |
| V3 | Self-supervised contrastive learning with NNCLR | 2021/09/13 | 2024/01/22 |
| Starter | Keras Version | Title | Date Created | Last Modified ▼ |
|---|---|---|---|---|
| V3 | Self-supervised contrastive learning with NNCLR | 2021/09/13 | 2024/01/22 | |
| V2 | Near-duplicate image search | 2021/09/10 | 2023/08/30 | |
| V3 | Image similarity estimation using a Siamese Network with a contrastive loss | 2021/05/06 | 2022/09/10 | |
| V2 | Metric learning for image similarity search using TensorFlow Similarity | 2021/09/30 | 2022/02/29 | |
| V3 | Image similarity estimation using a Siamese Network with a triplet loss | 2021/03/25 | 2021/03/25 | |
| V3 | Semantic Image Clustering | 2021/02/28 | 2021/02/28 | |
| V3 | Metric learning for image similarity search | 2020/06/05 | 2020/06/09 |
Video
| Starter | Keras Version | Title | Date Created | Last Modified |
|---|---|---|---|---|
| V3 | Video Classification with a CNN-RNN Architecture | 2021/05/28 | 2023/12/08 | |
| V3 | Next-Frame Video Prediction with Convolutional LSTMs | 2021/06/02 | 2023/11/10 | |
| V3 | Video Classification with Transformers | 2021/08/06 | 2023/07/22 | |
| V3 | Video Vision Transformer | 2022/01/12 | 2024/01/15 |
| Starter | Keras Version | Title | Date Created | Last Modified ▼ |
|---|---|---|---|---|
| V3 | Video Vision Transformer | 2022/01/12 | 2024/01/15 | |
| V3 | Video Classification with a CNN-RNN Architecture | 2021/05/28 | 2023/12/08 | |
| V3 | Next-Frame Video Prediction with Convolutional LSTMs | 2021/06/02 | 2023/11/10 | |
| V3 | Video Classification with Transformers | 2021/08/06 | 2023/07/22 |
Performance recipes
| Starter | Keras Version | Title | Date Created | Last Modified |
|---|---|---|---|---|
| V3 | Gradient Centralization for Better Training Performance | 2021/06/18 | 2023/07/25 | |
| V3 | Learning to tokenize in Vision Transformers | 2021/12/10 | 2023/08/14 | |
| V3 | Knowledge Distillation | 2020/09/01 | 2020/09/01 | |
| V3 | FixRes: Fixing train-test resolution discrepancy | 2021/10/08 | 2021/10/10 | |
| V3 | Class Attention Image Transformers with LayerScale | 2022/09/19 | 2022/11/21 | |
| V3 | Augmenting convnets with aggregated attention | 2022/01/22 | 2022/01/22 | |
| V3 | Learning to Resize in Computer Vision | 2021/04/30 | 2023/12/18 |
| Starter | Keras Version | Title | Date Created | Last Modified ▼ |
|---|---|---|---|---|
| V3 | Learning to Resize in Computer Vision | 2021/04/30 | 2023/12/18 | |
| V3 | Learning to tokenize in Vision Transformers | 2021/12/10 | 2023/08/14 | |
| V3 | Gradient Centralization for Better Training Performance | 2021/06/18 | 2023/07/25 | |
| V3 | Class Attention Image Transformers with LayerScale | 2022/09/19 | 2022/11/21 | |
| V3 | Augmenting convnets with aggregated attention | 2022/01/22 | 2022/01/22 | |
| V3 | FixRes: Fixing train-test resolution discrepancy | 2021/10/08 | 2021/10/10 | |
| V3 | Knowledge Distillation | 2020/09/01 | 2020/09/01 |
Other
| Starter | Keras Version | Title | Date Created | Last Modified |
|---|---|---|---|---|
| V2 | Semi-supervision and domain adaptation with AdaMatch | 2021/06/19 | 2021/06/19 | |
| V2 | Barlow Twins for Contrastive SSL | 2021/11/04 | 2021/12/20 | |
| V2 | Consistency training with supervision | 2021/04/13 | 2021/04/19 | |
| V2 | Distilling Vision Transformers | 2022/04/05 | 2022/04/08 | |
| V2 | Focal Modulation: A replacement for Self-Attention | 2023/01/25 | 2023/02/15 | |
| V2 | Using the Forward-Forward Algorithm for Image Classification | 2023/01/08 | 2024/09/17 | |
| V2 | Masked image modeling with Autoencoders | 2021/12/20 | 2021/12/21 | |
| V2 | Segment Anything Model with 🤗Transformers | 2023/07/11 | 2023/07/11 | |
| V2 | Semantic segmentation with SegFormer and Hugging Face Transformers | 2023/01/25 | 2023/01/29 | |
| V2 | Self-supervised contrastive learning with SimSiam | 2021/03/19 | 2023/12/29 | |
| V2 | Supervised Contrastive Learning | 2020/11/30 | 2020/11/30 | |
| V2 | When Recurrence meets Transformers | 2023/03/12 | 2024/11/12 | |
| V2 | Efficient Object Detection with YOLOV8 and KerasCV | 2023/06/26 | 2023/06/26 |
| Starter | Keras Version | Title | Date Created | Last Modified ▼ |
|---|---|---|---|---|
| V2 | When Recurrence meets Transformers | 2023/03/12 | 2024/11/12 | |
| V2 | Using the Forward-Forward Algorithm for Image Classification | 2023/01/08 | 2024/09/17 | |
| V2 | Self-supervised contrastive learning with SimSiam | 2021/03/19 | 2023/12/29 | |
| V2 | Segment Anything Model with 🤗Transformers | 2023/07/11 | 2023/07/11 | |
| V2 | Efficient Object Detection with YOLOV8 and KerasCV | 2023/06/26 | 2023/06/26 | |
| V2 | Focal Modulation: A replacement for Self-Attention | 2023/01/25 | 2023/02/15 | |
| V2 | Semantic segmentation with SegFormer and Hugging Face Transformers | 2023/01/25 | 2023/01/29 | |
| V2 | Distilling Vision Transformers | 2022/04/05 | 2022/04/08 | |
| V2 | Masked image modeling with Autoencoders | 2021/12/20 | 2021/12/21 | |
| V2 | Barlow Twins for Contrastive SSL | 2021/11/04 | 2021/12/20 | |
| V2 | Semi-supervision and domain adaptation with AdaMatch | 2021/06/19 | 2021/06/19 | |
| V2 | Consistency training with supervision | 2021/04/13 | 2021/04/19 | |
| V2 | Supervised Contrastive Learning | 2020/11/30 | 2020/11/30 |