CVJan 20, 2016

Factors in Finetuning Deep Model for object detection

arXiv:1601.05150v2209 citations
Originality Incremental advance
AI Analysis

This work addresses performance optimization in object detection for computer vision applications, representing an incremental improvement.

The paper tackles the problem of improving object detection performance by analyzing factors in finetuning deep models, such as addressing class imbalance and leveraging class individuality through hierarchical feature learning, resulting in a 4.7% absolute mAP improvement on the ImageNet dataset.

Finetuning from a pretrained deep model is found to yield state-of-the-art performance for many vision tasks. This paper investigates many factors that influence the performance in finetuning for object detection. There is a long-tailed distribution of sample numbers for classes in object detection. Our analysis and empirical results show that classes with more samples have higher impact on the feature learning. And it is better to make the sample number more uniform across classes. Generic object detection can be considered as multiple equally important tasks. Detection of each class is a task. These classes/tasks have their individuality in discriminative visual appearance representation. Taking this individuality into account, we cluster objects into visually similar class groups and learn deep representations for these groups separately. A hierarchical feature learning scheme is proposed. In this scheme, the knowledge from the group with large number of classes is transferred for learning features in its sub-groups. Finetuned on the GoogLeNet model, experimental results show 4.7% absolute mAP improvement of our approach on the ImageNet object detection dataset without increasing much computational cost at the testing stage.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes