CVMMAug 6, 2020

Data-driven Meta-set Based Fine-Grained Visual Classification

arXiv:2008.02438v11 citations
AI Analysis

This addresses the challenge of constructing fine-grained datasets without expert annotation, which is incremental as it builds on existing noise-robust methods.

The paper tackles the problem of label noise in web-sourced fine-grained image datasets by proposing a data-driven meta-set approach, achieving superior performance over state-of-the-art noise-robust methods on three datasets.

Constructing fine-grained image datasets typically requires domain-specific expert knowledge, which is not always available for crowd-sourcing platform annotators. Accordingly, learning directly from web images becomes an alternative method for fine-grained visual recognition. However, label noise in the web training set can severely degrade the model performance. To this end, we propose a data-driven meta-set based approach to deal with noisy web images for fine-grained recognition. Specifically, guided by a small amount of clean meta-set, we train a selection net in a meta-learning manner to distinguish in- and out-of-distribution noisy images. To further boost the robustness of model, we also learn a labeling net to correct the labels of in-distribution noisy data. In this way, our proposed method can alleviate the harmful effects caused by out-of-distribution noise and properly exploit the in-distribution noisy samples for training. Extensive experiments on three commonly used fine-grained datasets demonstrate that our approach is much superior to state-of-the-art noise-robust methods.

Code Implementations1 repo
Foundations

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

Your Notes