TY  - JOUR
AU  - Bhalaji Nagarajan
AU  - Marc Bolaños
AU  - Eduardo Aguilar
AU  - Petia Radeva
PY  - 2023//
TI  - Deep ensemble-based hard sample mining for food recognition
T2  - JVCIR
JO  - Journal of Visual Communication and Image Representation
SP  - 103905
VL  - 95
N2  - Deep neural networks represent a compelling technique to tackle complex real-world problems, but are over-parameterized and often suffer from over- or under-confident estimates. Deep ensembles have shown better parameter estimations and often provide reliable uncertainty estimates that contribute to the robustness of the results. In this work, we propose a new metric to identify samples that are hard to classify. Our metric is defined as coincidence score for deep ensembles which measures the agreement of its individual models. The main hypothesis we rely on is that deep learning algorithms learn the low-loss samples better compared to large-loss samples. In order to compensate for this, we use controlled over-sampling on the identified ”hard” samples using proper data augmentation schemes to enable the models to learn those samples better. We validate the proposed metric using two public food datasets on different backbone architectures and show the improvements compared to the conventional deep neural network training using different performance metrics.
UR  - https://www.sciencedirect.com/science/article/pii/S1047320323001554
N1  - MILAB
ID  - Bhalaji Nagarajan2023
ER  -