Scanning 100 Million Hubble Images in 3 Days: ESA’s AnomalyMatch Finds Over 1,000 Rare Objects

ESA’s ESAC team introduced AnomalyMatch, a semi‑supervised active‑learning framework that, with fewer than ten labeled anomalies, processed roughly 100 million Hubble cutouts in just 2–3 days, uncovering 1,339 distinct anomalous astrophysical objects such as merging galaxies, gravitational lenses, and jellyfish galaxies.

AnomalyMatchEfficientNetHubble Legacy Archive

0 likes · 16 min read

Scanning 100 Million Hubble Images in 3 Days: ESA’s AnomalyMatch Finds Over 1,000 Rare Objects

Code DAO

May 28, 2022 · Artificial Intelligence

How to Build an Image Duplicate Detection System

This article explains how to construct an image duplicate and near‑duplicate detection system, compares five similarity methods (Euclidean distance, SSIM, image hashing, cosine similarity, and CNN‑based feature similarity), provides Python implementations, evaluates them on two datasets, and discusses speed, accuracy, and robustness results.

CNNEfficientNetPython

0 likes · 18 min read

How to Build an Image Duplicate Detection System

Code DAO

May 5, 2022 · Artificial Intelligence

Optimizing Machine Learning Models for Edge Devices with TensorFlow Lite

This article explains how to convert a TensorFlow image‑classification model to TensorFlow Lite, apply different quantization techniques, benchmark the resulting models on a Raspberry Pi 4, and compare latency, size, and accuracy to demonstrate the trade‑offs of edge AI deployment.

EfficientNetModel QuantizationPython

0 likes · 16 min read

Optimizing Machine Learning Models for Edge Devices with TensorFlow Lite

Amap Tech

Jan 22, 2021 · Artificial Intelligence

Dynamic Road Condition Analysis Using EfficientNet and ConvLSTM: Solution to the AMAP‑TECH Algorithm Competition

The winning solution for the AMAP‑TECH competition combines EfficientNet spatial features with ConvLSTM temporal modeling, adds a mask‑prediction branch for closed‑road obstacles, and mitigates severe class imbalance through a two‑stage decoupled training pipeline, achieving first place on leaderboard A and top‑5 on leaderboard B without ensembling.

AI competitionConvLSTMEfficientNet

0 likes · 7 min read

Dynamic Road Condition Analysis Using EfficientNet and ConvLSTM: Solution to the AMAP‑TECH Algorithm Competition

Youku Technology

Apr 16, 2020 · Artificial Intelligence

Multimodal Video Classification: Image Feature Improvements and System Insights

The talk presents Alibaba’s hierarchical video‑category system and a multimodal classification pipeline—leveraging EfficientNet, NeXtVLAD fusion, attention‑dropping augmentation, and MoCo contrastive learning—that together boost cold‑start recall by 43%, improve program classification over 20%, and set the stage for larger models and advanced unsupervised methods.

AIEfficientNetMultimodal

0 likes · 17 min read

Multimodal Video Classification: Image Feature Improvements and System Insights

Scanning 100 Million Hubble Images in 3 Days: ESA’s AnomalyMatch Finds Over 1,000 Rare Objects

How to Build an Image Duplicate Detection System

Optimizing Machine Learning Models for Edge Devices with TensorFlow Lite

Dynamic Road Condition Analysis Using EfficientNet and ConvLSTM: Solution to the AMAP‑TECH Algorithm Competition

Multimodal Video Classification: Image Feature Improvements and System Insights

Scanning 100 Million Hubble Images in 3 Days: ESA’s AnomalyMatch Finds Over 1,000 Rare Objects