Robust and Label-Efficient Deep Waste Detection

TL;DR

This paper advances AI waste detection by benchmarking models, optimizing prompts, fine-tuning detectors, and proposing a semi-supervised ensemble pseudo-labeling method that improves performance on real-world datasets.

Contribution

It establishes strong baselines, introduces an ensemble pseudo-labeling framework, and generates high-quality annotations for waste detection, addressing dataset limitations and domain-specific challenges.

Findings

Transformer-based detectors achieved 51.6 mAP.

Prompt optimization significantly improves zero-shot accuracy.

Pseudo-labeling surpasses fully supervised training results.

Abstract

Effective waste sorting is critical for sustainable recycling, yet AI research in this domain continues to lag behind commercial systems due to limited datasets and reliance on legacy object detectors. In this work, we advance AI-driven waste detection by establishing strong baselines and introducing an ensemble-based semi-supervised learning framework. We first benchmark state-of-the-art Open-Vocabulary Object Detection (OVOD) models on the real-world ZeroWaste dataset, demonstrating that while class-only prompts perform poorly, LLM-optimized prompts significantly enhance zero-shot accuracy. Next, to address domain-specific limitations, we fine-tune modern transformer-based detectors, achieving a new baseline of 51.6 mAP. We then propose a soft pseudo-labeling strategy that fuses ensemble predictions using spatial and consensus-aware weighting, enabling robust semi-supervised training. Applied to the unlabeled ZeroWaste-s subset, our pseudo-annotations achieve performance gains that surpass fully supervised training, underscoring the effectiveness of scalable annotation pipelines. Our work contributes to the research community by establishing rigorous baselines, introducing a robust ensemble-based pseudo-labeling pipeline, generating high-quality annotations for the unlabeled ZeroWaste-s subset, and systematically evaluating OVOD models under real-world waste sorting conditions. Our code is available at: https://github.com/h-abid97/robust-waste-detection.