CVAug 12, 2021

Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning

arXiv:2108.05617v175 citations
Originality Highly original
AI Analysis

This addresses a practical challenge in machine learning for scenarios with mixed data distributions, offering a novel training mechanism rather than incremental improvements.

The paper tackles the problem of open-set semi-supervised learning where out-of-distribution (OOD) data is present in unlabeled sets, proposing a method that exploits OOD data for feature learning while mitigating its negative effects, resulting in substantial performance gains over state-of-the-art approaches.

Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data. While the mainstream technique seeks to completely filter out the OOD samples for semi-supervised learning (SSL), we propose a novel training mechanism that could effectively exploit the presence of OOD data for enhanced feature learning while avoiding its adverse impact on the SSL. We achieve this goal by first introducing a warm-up training that leverages all the unlabeled data, including both the in-distribution (ID) and OOD samples. Specifically, we perform a pretext task that enforces our feature extractor to obtain a high-level semantic understanding of the training images, leading to more discriminative features that can benefit the downstream tasks. Since the OOD samples are inevitably detrimental to SSL, we propose a novel cross-modal matching strategy to detect OOD samples. Instead of directly applying binary classification, we train the network to predict whether the data sample is matched to an assigned one-hot class label. The appeal of the proposed cross-modal matching over binary classification is the ability to generate a compatible feature space that aligns with the core classification task. Extensive experiments show that our approach substantially lifts the performance on open-set SSL and outperforms the state-of-the-art by a large margin.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes