IEEE

A Multi-Scale Contrast Preserving Encoder-Decoder Architecture for Local Change Detection From Thermal Video Scenes

Abstract: This article presents a new deep-learning architecture based on an encoder-decoder framework that retains contrast while performing background subtraction (BS) on thermal videos. The ...
the-decoder

Anthropic supports California's AI law - because Washington is too slow

Anthropic backs California's SB 53, a state bill that would force large developers of advanced AI to be more transparent and secure—apparently because they see Washington as too slow to act. Anthropic ...
the-decoder

Anthropic bans companies majority-controlled by China, Russia, Iran, and North Korea from Claude

Anthropic will no longer provide its services to groups that are majority-owned by Chinese entities. This marks the first time a major US AI company has made such a policy change. The new rule, which ...
IEEE

Encoder-Decoder Contrast for Unsupervised Anomaly Detection in Medical Images

Abstract: Unsupervised anomaly detection (UAD) aims to recognize anomalous images based on the training set that contains only normal images. In medical image analysis, UAD benefits from leveraging ...
GitHub

Prompt-In-the-Loop Distillation for On-Device Deployment of SAM

EdgeSAM is an accelerated variant of the Segment Anything Model (SAM), optimized for efficient execution on edge devices with minimal compromise in performance. It achieves a 40-fold speed increase ...
GitHub

SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation

We propose an encoder-decoder for open-vocabulary semantic segmentation comprising a hierarchical encoder-based cost map generation and a gradual fusion decoder. We introduce a category early ...