Attention mechanisms have been found effective for person re-identification (Re-ID). However, the learned "attentive" features are often not naturally uncorrelated or "diverse", which compromises the retrieval performance based on the Euclidean distance. We advocate the complementary powers of attention and diversity for Re-ID, by proposing an Attentive but Diverse Network (ABD-Net). ABD-Net seamlessly integrates attention modules and diversity regularizations throughout the entire network to learn features that are representative, robust, and more discriminative. Specifically, we introduce a pair of complementary attention modules, focusing on channel aggregation and position awareness, respectively. Then, we plug in a novel orthogonality constraint that efficiently enforces diversity on both hidden activations and weights. Through an extensive set of ablation study, we verify that the attentive and diverse terms each contributes to the performance boosts of ABD-Net. It consistently outperforms existing state-of-the-art methods on there popular person Re-ID benchmarks. * This also exploits attention mechanisms.• This is with a ResNet-152 backbone. This is with a DenseNet-121 backbone. ‡ Official codes are not released. We report the numbers in the original paper, which are better than our re-implementation.comes 3.40% for top-1 and 6.40% for mAP. We also considered SVDNet [13] and HA- CNN [50] which also proposed to generate diverse and uncorrelated feature embeddings. ABD-Net surpasses both with significant top-1 and mAP improvement. Overall, our observations endorse the superiority of ABD-Net by combing "attentive" and "diverse". VisualizationsAttention Pattern Visualization: We conduct a set of attention visualizations * * on the final output feature maps of the baseline (XE), baseline (XE) + PAM + CAM, and ABD-Net (XE), as shown in Fig.5. We notice that the feature maps from the baseline show little attentiveness. PAM + * * Grad-CAM visualization method [73]: https://github.com/ utkuozbulak/pytorch-cnn-visualizations; RAM visualization method [74] for testing images. More results can be found in the supplementary.

Mobile memory capacity (a) Best performance achievable Mobile memory capacity (b) Performance trained on global image Mobile memory capacity (c) Performance trained on local patchesFigure 1: Inference memory and mean intersection over union (mIoU) accuracy on the DeepGlobe dataset [1]. (a): Comparison of best achievable mIoU v.s. memory for different segmentation methods. (b): mIoU/memory with different global image sizes (downsampling rate shown in scale annotations). (c): mIoU/memory with different local patch sizes (normalized patch size shown in scale annotations). GLNet (red dots) integrates both global and local information in a compact way, contributing to a well-balanced trade-off between accuracy and memory usage. See Section 4 for experiment details. Methods studied: ICNet [2], DeepLabv3+ [3], FPN [4], FCN-8s [5], UNet [6], PSPNet [7], SegNet [8], and the proposed GLNet. AbstractSegmentation of ultra-high resolution images is increasingly demanded, yet poses significant challenges for algorithm efficiency, in particular considering the (GPU) memory limits. Current approaches either downsample an ultrahigh resolution image or crop it into small patches for separate processing. In either way, the loss of local fine details or global contextual information results in limited segmentation accuracy. We propose collaborative Global-Local Networks (GLNet) to effectively preserve both global and local information in a highly memory-efficient manner. GLNet is composed of a global branch and a local branch, taking the downsampled entire image and its cropped local patches as respective inputs. For segmentation, GLNet deeply fuses feature maps from two branches, capturing both the high-resolution fine structures from zoomed-in local patches and the contextual dependency from the downsampled input. To further resolve the potential class imbalance problem between background and foreground regions, we present a coarse-to-fine variant of GLNet, also being * The first two authors contributed equally. memory-efficient. Extensive experiments and analyses have been performed on three real-world ultra-high aerial and medical image datasets (resolution up to 30 million pixels). With only one single 1080Ti GPU and less than 2GB memory used, our GLNet yields high-quality segmentation results and achieves much more competitive accuracymemory usage trade-offs compared to state-of-the-arts.

No abstract

No abstract

The comparative losses (typically, triplet loss) are appealing choices for learning person re-identification (ReID) features. However, the triplet loss is computationally much more expensive than the (practically more popular) classification loss, limiting their wider usage in massive datasets. Moreover, the abundance of label noise and outliers in ReID datasets may also put the margin-based loss in jeopardy. This work addresses the above two shortcomings of triplet loss, extending its effectiveness to large-scale ReID datasets with potentially noisy labels. We propose a fastapproximated triplet (FAT) loss, which provably converts the point-wise triplet loss into its upper bound form, consisting of a point-to-set loss term plus cluster compactness regularization. It preserves the effectiveness of triplet loss, while leading to linear complexity to the training set size. A label distillation strategy is further designed to learn refined soft-labels in place of the potentially noisy labels, from only an identified subset of confident examples, through teacher-student networks. We conduct extensive experiments on three most popular ReID benchmarks (Market-1501, DukeMTMC-reID, and MSMT17), and demonstrate that FAT loss with distilled labels lead to ReID features with remarkable accuracy, efficiency, robustness, and direct transferability to unseen datasets.