Shape-Texture Debiased Neural Network Training
international conference on learning representations, 2020.
Training CNNs to acquire a debiased shape-texture representation improves image recognition.
Shape and texture are two prominent and complementary cues for recognizing objects. Nonetheless, Convolutional Neural Networks are often biased towards either texture or shape, depending on the training dataset. Our ablation shows that such bias degenerates model performance. Motivated by this observation, we develop a simple algorithm ...More
PPT (Upload PPT)