Evaluating Visual Properties via Robust HodgeRank

TL;DR

This paper introduces a robust HodgeRank-based framework for evaluating visual properties from crowdsourced ranking data, effectively handling noise, incompleteness, and imbalanced annotations in large datasets.

Contribution

It develops a novel outlier detection model using Hodge decomposition and Huber's LASSO, with scalable algorithms and proven statistical consistency.

Findings

Effective outlier detection in noisy ranking data

Scalable algorithms with statistical guarantees

Validated on simulated and real-world datasets

Abstract

Nowadays, how to effectively evaluate visual properties has become a popular topic for fine-grained visual comprehension. In this paper we study the problem of how to estimate such visual properties from a ranking perspective with the help of the annotators from online crowdsourcing platforms. The main challenges of our task are two-fold. On one hand, the annotations often contain contaminated information, where a small fraction of label flips might ruin the global ranking of the whole dataset. On the other hand, considering the large data capacity, the annotations are often far from being complete. What is worse, there might even exist imbalanced annotations where a small subset of samples are frequently annotated. Facing such challenges, we propose a robust ranking framework based on the principle of Hodge decomposition of imbalanced and incomplete ranking data. According to the HodgeRank theory, we find that the major source of the contamination comes from the cyclic ranking component of the Hodge decomposition. This leads us to an outlier detection formulation as sparse approximations of the cyclic ranking projection. Taking a step further, it facilitates a novel outlier detection model as Huber's LASSO in robust statistics. Moreover, simple yet scalable algorithms are developed based on Linearized Bregman Iteration to achieve an even less biased estimator. Statistical consistency of outlier detection is established in both cases under nearly the same conditions. Our studies are supported by experiments with both simulated examples and real-world data. The proposed framework provides us a promising tool for robust ranking with large scale crowdsourcing data arising from computer vision.