Abstract | ||
---|---|---|
We present an approach that combines appearance and semantic information for 2D image-based localization (2D-VL) across large perceptual changes and time lags. Compared to appearance features, the semantic layout of a scene is generally more invariant to appearance variations. We use this intuition and propose a novel end-to-end deep attention-based framework that utilizes multimodal cues to generate robust embeddings for 2D-VL. The proposed attention module predicts a shared channel attention and modality-specific spatial attentions to guide the embeddings to focus on more reliable image regions. We evaluate our model against state-of-the-art (SOTA) methods on three challenging localization datasets. We report an average (absolute) improvement of $19\%$ over current SOTA for 2D-VL. Furthermore, we present an extensive study demonstrating the contribution of each component of our model, showing $8$--$15\%$ and $4\%$ improvement from adding semantic information and our proposed attention module. We finally show the predicted attention maps to offer useful insights into our model. |
Year | Venue | DocType |
---|---|---|
2018 | arXiv: Computer Vision and Pattern Recognition | Journal |
Volume | Citations | PageRank |
abs/1812.03402 | 1 | 0.34 |
References | Authors | |
0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zachary Seymour | 1 | 1 | 1.02 |
Karan Sikka | 2 | 1 | 1.02 |
Han-Pang Chiu | 3 | 94 | 10.83 |
Supun Samarasekera | 4 | 792 | 85.72 |
Rakesh Kumar | 5 | 1923 | 157.44 |