GenKL: An Iterative Framework for Resolving Label Ambiguity and Label Non-conformity in Web Images Via a New Generalized KL Divergence
Authors:
- Xia HuangXHXia Huang
- Kai Fong Ernest ChongKCKai Fong Ernest Chong
Preprint
Abstract
Web image datasets curated online inherently contain ambiguous in-distribution (ID) instances and out-of-distribution (OOD) instances, which we collectively call non-conforming (NC) instances. In many recent approaches for mitigating the negative effects of NC instances, the core implicit assumption is that the NC instances can be found via entropy maximization. For "entropy" to be well-defined, we are interpreting the output prediction vector of an instance as the parameter vector of a multinomial random variable, with respect to some trained model with a softmax output layer. Hence, entropy maximization is based on the idealized assumption that NC instances have predictions that are "almost" uniformly distributed. However, in real-world web image datasets, there are numerous NC instances whose predictions are far from being uniformly distributed. To tackle the limitation of entropy maximization, we propose $(α, β)$-generalized KL divergence, $\mathcal{D}_{\text{KL}}^{α, β}(p\|q)$, which can be used to identify significantly more NC instances. Theoretical properties of $\mathcal{D}_{\text{KL}}^{α, β}(p\|q)$ are proven, and we also show empirically that a simple use of $\mathcal{D}_{\text{KL}}^{α, β}(p\|q)$ outperforms all baselines on the NC instance identification task. Building upon $(α,β)$-generalized KL divergence, we also introduce a new iterative training framework, GenKL, that identifies and relabels NC instances. When evaluated on three web image datasets, Clothing1M, Food101/Food101N, and mini WebVision 1.0, we achieved new state-of-the-art classification accuracies: $81.34\%$, $85.73\%$ and $78.99\%$/$92.54\%$ (top-1/top-5), respectively.
Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Entropic Out-of-Distribution Detection2021
- Multi-Sentence Auxiliary Adversarial Networks for Fine-Grained Text-to-Image SynthesisIEEE Transactions on Image Processing, 2021
- Deep Learning for Generic Object Detection: A SurveyInternational Journal of Computer Vision, 2019
- Deep Learning From Noisy Image Labels With Quality EmbeddingIEEE Transactions on Image Processing, 2018
- Delta Divergence: A Novel Decision Cognizant Measure of Classifier IncongruenceIEEE Transactions on Cybernetics, 2018
- A decision cognizant Kullback–Leibler divergencePattern Recognition, 2017
- Food-101 – Mining Discriminative Components with Random Forests2014
- The kappa statistic as a function of sensitivity and specificityInternational Journal of Mathematical Education in Science and Technology, 2005
- Some interlacing properties of the Schur complement of a Hermitian matrixLinear Algebra and its Applications, 1992
- Divergence measures based on the Shannon entropyIEEE Transactions on Information Theory, 1991