IEEE

A Novel Semi-Supervised Object Detection Approach via Scale Rebalancing and Global Proposal Contrast Consistency

Abstract: Semi-supervised Object Detection (SSOD) is a method that uses a small amount of labeled data and a large amount of unlabeled data to improve the performance of object detection. However, ...
GitHub

Images as Noisy Labels: Unleashing the Potential of the Diffusion Model for Open-Vocabulary Semantic Segmentation

This repository is the official PyTorch implementation of the ICCV 2025 (Highlight) paper: Images as Noisy Labels: Unleashing the Potential of the Diffusion Model for Open-Vocabulary Semantic ...
IEEE

GFENet: Generalization Feature Extraction Network for Few-Shot Object Detection

Abstract: Few-shot object detection achieves rapid detection of novel-class objects by training detectors with a minimal number of novel-class annotated instances. Transfer learning-based few-shot ...
FIA Formula E

FP1 REPORT: Jake Dennis tops the opening session of Formula E's 150th race

São Paulo race winner Jake Dennis continued his recent run of form, topping the timing sheets for Free Practice 1 in Mexico City. The circuit is a place with happy memories for Dennis, who won the ...