Illumination Normalization by Partially Impossible Encoder-Decoder Cost Function
This work addresses illumination normalization for enhancing robustness in computer vision systems, particularly in automotive applications, but it is incremental as it builds on existing encoder-decoder frameworks with novel cost function and regularization techniques.
The paper tackles the problem of illumination and environmental variations degrading computer vision model reliability by introducing a new cost function strategy for encoder-decoder networks that averages out unimportant information to focus on salient features, achieving improved robustness as assessed on three public datasets and a released synthetic automotive dataset.
Images recorded during the lifetime of computer vision based systems undergo a wide range of illumination and environmental conditions affecting the reliability of previously trained machine learning models. Image normalization is hence a valuable preprocessing component to enhance the models' robustness. To this end, we introduce a new strategy for the cost function formulation of encoder-decoder networks to average out all the unimportant information in the input images (e.g. environmental features and illumination changes) to focus on the reconstruction of the salient features (e.g. class instances). Our method exploits the availability of identical sceneries under different illumination and environmental conditions for which we formulate a partially impossible reconstruction target: the input image will not convey enough information to reconstruct the target in its entirety. Its applicability is assessed on three publicly available datasets. We combine the triplet loss as a regularizer in the latent space representation and a nearest neighbour search to improve the generalization to unseen illuminations and class instances. The importance of the aforementioned post-processing is highlighted on an automotive application. To this end, we release a synthetic dataset of sceneries from three different passenger compartments where each scenery is rendered under ten different illumination and environmental conditions: see https://sviro.kl.dfki.de