Oral
Guided Similarity Separation for Image Retrieval
Chundi Liu · Guangwei Yu · Maksims Volkovs · Cheng Chang · Himanshu Rai · Junwei Ma · Satya Krishna Gorti

Wed Dec 11th 03:50 -- 04:05 PM @ West Ballrooms A + B

Despite recent progress in computer vision, image retrieval remains a challenging open problem. Numerous variations such as view angle, lighting and occlusion make it difficult to design models that are both robust and efficient. Many leading methods traverse the nearest neighbor graph to exploit higher order neighbor information and uncover the highly complex underlying manifold. In this work we propose a different approach where we leverage graph convolutional networks to directly encode neighbor information into image descriptors. We further leverage ideas from clustering and manifold learning, and introduce an unsupervised loss based on pairwise separation of image similarities. Empirically, we demonstrate that our model is able to successfully learn a new descriptor space that significantly improves retrieval accuracy, while still allowing efficient inner product inference. Experiments on five public benchmarks show highly competitive performance with up to 24\% relative improvement in mAP over leading baselines. Full code for this work is available here: https://github.com/layer6ai-labs/GSS.

Author Information

Chundi Liu (Layer6 AI)
Guangwei Yu (Layer6)
Maksims Volkovs (Layer6 AI)
Cheng Chang (Layer6 AI)
Himanshu Rai (Layer6 AI)
Junwei Ma (Layer6 AI)
Satya Krishna Gorti (Layer6 AI)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors