The Food Recognition Benchmark: Using Deep Learning to Recognize Food in Images.

The automatic recognition of food on images has numerous interesting applications, including nutritional tracking in medical cohorts. The problem has received significant research attention, but an ongoing public benchmark on non-biased (i.e., not scraped from web) data to develop open and reproducible algorithms has been missing. Here, we report on the setup of such a benchmark using publicly available food images sourced through the mobile MyFoodRepo app used in research cohorts. Through four rounds, the benchmark released the MyFoodRepo-273 dataset constituting 24,119 images and a total of 39,325 segmented polygons categorized in 273 different classes. Models were evaluated on private tests sets from the same platform with 5,000 images and 7,865 annotations in the final round. Top-performing models on the 273 food categories reached a mean average precision of 0.568 (round 4) and a mean average recall of 0.885 (round 3), and were deployed in production use of the MyFoodRepo app. We present experimental validation of round 4 results, and discuss implications of the benchmark setup designed to increase the size and diversity of the dataset for future rounds.

Using 2D video-based pose estimation for automated prediction of autism spectrum disorders in young children.

Clinical research in autism has recently witnessed promising digital phenotyping results, mainly focused on single feature extraction, such as gaze, head turn on name-calling or visual tracking of the moving object. The main drawback of these studies is the focus on relatively isolated behaviors elicited by largely controlled prompts. We recognize that while the diagnosis process understands the indexing of the specific behaviors, ASD also comes with broad impairments that often transcend single behavioral acts. For instance, the atypical nonverbal behaviors manifest through global patterns of atypical postures and movements, fewer gestures used and often decoupled from visual contact, facial affect, speech. Here, we tested the hypothesis that a deep neural network trained on the non-verbal aspects of social interaction can effectively differentiate between children with ASD and their typically developing peers. Our model achieves an accuracy of 80.9% (F1 score: 0.818; precision: 0.784; recall: 0.854) with the prediction probability positively correlated to the overall level of symptoms of autism in social affect and repetitive and restricted behaviors domain. Provided the non-invasive and affordable nature of computer vision, our approach carries reasonable promises that a reliable machine-learning-based ASD screening may become a reality not too far in the future.

Deep Learning for Understanding Satellite Imagery: An Experimental Survey.

Translating satellite imagery into maps requires intensive effort and time, especially leading to inaccurate maps of the affected regions during disaster and conflict. The combination of availability of recent datasets and advances in computer vision made through deep learning paved the way toward automated satellite image translation. To facilitate research in this direction, we introduce the Satellite Imagery Competition using a modified SpaceNet dataset. Participants had to come up with different segmentation models to detect positions of buildings on satellite images. In this work, we present five approaches based on improvements of U-Net and Mask R-Convolutional Neuronal Networks models, coupled with unique training adaptations using boosting algorithms, morphological filter, Conditional Random Fields and custom losses. The good results-as high as A P = 0.937 and A R = 0.959 -from these models demonstrate the feasibility of Deep Learning in automated satellite image annotation.