Name
Title | ||
|---|---|---|
TC-Net for iSBIR: Triplet Classification Network for Instance-level Sketch Based Image Retrieval |
Abstract | ||
|---|---|---|
Sketch has been employed as an effective communication tool to express the abstract and intuitive meaning of object. While content-based sketch recognition has been studied for several decades, the instance-level Sketch Based Image Retrieval (iSBIR) task has attracted significant research attention recently. In many previous iSBIR works -- TripletSN, and DSSA, edge maps were employed as intermediate representations in bridging the cross-domain discrepancy between photos and sketches. However, it is nontrivial to efficiently train and effectively use the edge maps in an iSBIR system. Particularly, we find that such an edge map based iSBIR system has several major limitations. First, the system has to be pre-trained on a significant amount of edge maps, either from large-scale sketch datasets, e.g., TU-Berlin~\citeeitz2012hdhso, or converted from other large-scale image datasets, e.g., ImageNet-1K\citedeng2009imagenet dataset. Second, the performance of such an iSBIR system is very sensitive to the quality of edge maps. Third and empirically, the multi-cropping strategy is essentially very important in improving the performance of previous iSBIR systems. To address these limitations, this paper advocates an end-to-end iSBIR system without using the edge maps. Specifically, we present a Triplet Classification Network (TC-Net) for iSBIR which is composed of two major components: triplet Siamese network, and auxiliary classification loss. Our TC-Net can break the limitations existed in previous works. Extensive experiments on several datasets validate the efficacy of the proposed network and system.
|
Year | DOI | Venue |
|---|---|---|
2019 | 10.1145/3343031.3350900 | Proceedings of the 27th ACM International Conference on Multimedia |
Keywords | Field | DocType |
sbir, sketch, triplet classification network | Computer vision,Edge maps,Information retrieval,Computer science,Bridging (networking),Image retrieval,Sketch recognition,Artificial intelligence,Sketch | Conference |
ISBN | Citations | PageRank |
978-1-4503-6889-6 | 3 | 0.37 |
References | Authors | |
0 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Hangyu Lin | 1 | 9 | 2.87 |
| Yanwei Fu | 2 | 543 | 51.93 |
| Peng Lu | 3 | 126 | 17.62 |
| Shaogang Gong | 4 | 7941 | 498.04 |
| Xiangyang Xue | 5 | 2466 | 154.25 |
| Yu-Gang Jiang | 6 | 3071 | 152.58 |