No abstract

Lesion detection from computed tomography (CT) scans is challenging compared to natural object detection because of two major reasons: small lesion size and small inter-class variation. Firstly, the lesions usually only occupy a small region in the CT image. The feature of such small region may not be able to provide sufficient information due to its limited spatial feature resolution. Secondly, in CT scans, the lesions are often indistinguishable from the background since the lesion and non-lesion areas may have very similar appearances. To tackle both problems, we need to enrich the feature representation and improve the feature discriminativeness. Therefore, we introduce a dual-attention mechanism to the 3D contextual lesion detection framework, including the cross-slice contextual attention to selectively aggregate the information from different slices through a soft re-sampling process. Moreover, we propose intra-slice spatial attention to focus the feature learning in the most prominent regions. Our method can be easily trained end-toend without adding heavy overhead on the base detection network. We use DeepLesion dataset and train a universal lesion detector to detect all kinds of lesions such as liver tumors, lung nodules, and so on. The results show that our model can significantly boost the results of the baseline lesion detector (with 3D contextual information) but using much fewer slices.

The task of action recognition in dark videos is useful in various scenarios, e.g., night surveillance and self-driving at night. Though progress has been made in action recognition task for videos in normal illumination, few have studied action recognition in the dark, partly due to the lack of sufficient datasets for such a task. In this paper, we explored the task of action recognition in dark videos. We bridge the gap of the lack of data by collecting a new dataset: the Action Recognition in the Dark (ARID) dataset. It consists of 3,784 video clips with 11 action categories. To the best of our knowledge, it is the first dataset focused on human actions in dark videos. To gain further understanding of our ARID dataset, we analyze our dataset in detail and showed its necessity over synthetic dark videos. Additionally, we benchmark the performance of current action recognition models on our dataset and explored potential methods for increasing their performances. We show that current action recognition models and frame enhancement methods may not be effective solutions for the task of action recognition in dark videos (data available at https://xuyu0010.github.io/arid).

It is desirable to train convolutional networks (CNNs) to run more efficiently during inference. In many cases however, the computational budget that the system has for inference cannot be known beforehand during training, or the inference budget is dependent on the changing real-time resource availability. Thus, it is inadequate to train just inference-efficient CNNs, whose inference costs are not adjustable and cannot adapt to varied inference budgets. We propose a novel approach for cost-adjustable inference in CNNs -Stochastic Downsampling Point (SDPoint). During training, SDPoint applies feature map downsampling to a random point in the layer hierarchy, with a random downsampling ratio. The different stochastic downsampling configurations known as SDPoint instances (of the same model) have computational costs different from each other, while being trained to minimize the same prediction loss. Sharing network parameters across different instances provides significant regularization boost. During inference, one may handpick a SDPoint instance that best fits the inference budget. The effectiveness of SDPoint, as both a cost-adjustable inference approach and a regularizer, is validated through extensive experiments on image classification.

Domain adaptation (DA) approaches address domain shift and enable networks to be applied to different scenarios. Although various image DA approaches have been proposed in recent years, there is limited research towards video DA. This is partly due to the complexity in adapting the different modalities of features in videos, which includes the correlation features extracted as long-term dependencies of pixels across spatiotemporal dimensions. The correlation features are highly associated with action classes and proven their effectiveness in accurate video feature extraction through the supervised action recognition task. Yet correlation features of the same action would differ across domains due to domain shift. Therefore we propose a novel Adversarial Correlation Adaptation Network (ACAN) to align action videos by aligning pixel correlations. ACAN aims to minimize the distribution of correlation information, termed as Pixel Correlation Discrepancy (PCD). Additionally, video DA research is also limited by the lack of cross-domain video datasets with larger domain shifts.We, therefore, introduce a novel HMDB-ARID dataset with a larger domain shift caused by a larger statistical difference between domains. This dataset is built in an effort to leverage current datasets for dark video classification.