The resulting model significantly outperforms state-of-the-art models with similar accuracy in terms of mCE and inference throughput.
Beyond classification, we further validate the saliency of the learnt representations via their attribute concentration and hierarchy recovery properties, achieving 10-25% relative gains on the softmax classifier and 25-50% on triplet loss in these tasks.
Inspired by the fact that successive CNN layers represent the image with increasing levels of abstraction, we compressed our deep ranking model to a single CNN by coupling activations from multiple intermediate layers along with the last layer.
#2 best model for Image Retrieval on street2shop - topwear
In this paper, we propose a deep convolutional neural network for learning the embeddings of images in order to capture the notion of visual similarity.
Computer vision based fine-grained recognition has received great attention in recent years.