Towards Machines that Perceive and Communicate
Explore cutting-edge research in visual scene understanding and grounded language processing, covering semantic segmentation, object detection, and image captioning advancements.
Deep Generative Models for Speech and Images
Explore deep learning's power in generating sounds and images, focusing on unsupervised learning and multiple levels of abstraction for advanced AI applications.
OpenAI's CLIP for Zero Shot Image Classification
Explore OpenAI's CLIP model for flexible computer vision classification without retraining, enabling generalization to new classes and images beyond initial training data.
OpenAI CLIP Explained - Multi-modal ML
Explore OpenAI's CLIP model, bridging text and image understanding. Learn about multi-modal AI, CLIP's functionality, and its applications in encoding, classification, and object detection.
Bag of Visual Words for Image Classification and Retrieval
Learn to build image embeddings using the Bag of Visual Words technique for image retrieval, object detection, and classification in computer vision applications.
Face Recognition and Privacy: Balancing Technology and Personal Rights - 2019
Exploring face recognition technology, its applications, privacy implications, and global legislation. Dispels myths and discusses potential for privacy-preserving implementations of this identification method.
Adversarial Examples in Machine Learning - Crafting and Defending Against Attacks
Explore machine learning vulnerabilities, adversarial examples, and their impact on system security. Learn crafting techniques and defenses through practical tutorials and real-world applications.
Machine Learning with TensorFlow Object Detection Running on Docker
Explore TensorFlow Object Detection API implementation using Docker, covering image creation, dependencies, and practical analysis of object detection in pictures.
Self-Training With Noisy Student Improves ImageNet Classification - Paper Explained
Explore a novel semi-supervised learning approach for image classification using unlabeled data, improving model performance and robustness through iterative self-training and noise injection techniques.
Context R-CNN- Long Term Temporal Context for Per-Camera Object Detection
Explores Context R-CNN, an object detection model leveraging long-term temporal context from static cameras. Improves performance in wildlife and traffic monitoring by incorporating data from multiple frames.
Rethinking the Truly Unsupervised Image-to-Image Translation - Paper Explained
Explore TUNIT, a groundbreaking approach to unsupervised image-to-image translation. Learn about its innovative architecture, loss functions, and experimental results for transforming images across domains.
Learning to Classify Images Without Labels - Paper Explained
Explore innovative techniques for unsupervised image classification, combining representation learning, clustering, and self-labeling to group visually similar images without predefined labels.
How to Use Facebook's DETR Object Detection Algorithm in Python - Full Tutorial
Hands-on tutorial implementing Facebook's DETR object detection algorithm in Python, covering model loading, image processing, output handling, and visualization with various test cases.
Group Normalization - Paper Explained
Explore Group Normalization as an alternative to Batch Normalization, addressing batch size limitations and improving performance in various deep learning tasks.
Supervised Contrastive Learning
Explore a novel supervised learning approach that outperforms cross-entropy loss, improving image classification models' performance and robustness across various architectures and data augmentations.
Feature Visualization and the OpenAI Microscope
Explore neural network visualizations using OpenAI Microscope, understanding feature extraction in ImageNet classifiers and techniques for visualizing internal model workings.
Blockwise Parallel Decoding for Deep Autoregressive Models
Explores a novel blockwise parallel decoding method for deep autoregressive models, enabling faster generation in tasks like machine translation and image super-resolution without sacrificing quality.
Deep Image Reconstruction from Human Brain Activity
Explores innovative technique for reconstructing visual imagery from brain activity using fMRI and deep neural networks, demonstrating potential for "mind-reading" technology and insights into neural representations.
Weight Standardization
Explores Weight Standardization technique for neural networks, improving performance in micro-batch training and outperforming other normalization methods when combined with Group Normalization.
SinGAN - Learning a Generative Model from a Single Natural Image
Unconditional generative model learns from a single image to create diverse, high-quality variations. Uses pyramid of GANs to capture patch distribution at multiple scales, enabling flexible image generation and manipulation.
Processing Megapixel Images with Deep Attention-Sampling Models
Explore a novel deep learning approach for efficiently processing high-resolution images by selectively focusing on informative regions, reducing computational costs while maintaining accuracy.