Classifying and segmenting patterns from a limited number of examples is a significant challenge in remote sensing and earth observation due to the difficulty in acquiring accurately labeled data in large quantities. Previous studies have shown that meta-learning, which involves episodic training on query and support sets, is a promising approach. However, there has been little attention paid to direct fine-tuning techniques. This paper repurposes contrastive learning as a pre-training method for few-shot learning for classification and semantic segmentation tasks. Specifically, we introduce a generator-based contrastive learning framework (GenCo) that pre-trains backbones and simultaneously explores variants of feature samples. In fine-tuning, the auxiliary generator can be used to enrich limited labeled data samples in feature space. We demonstrate the effectiveness of our method in improving few-shot learning performance on two key remote sensing datasets: Agriculture-Vision and EuroSAT. Empirically, our approach outperforms purely supervised training on the nearly 95,000 images in Agriculture-Vision for both classification and semantic segmentation tasks. Similarly, the proposed few-shot method achieves better results on the land-cover classification task on EuroSAT compared to the results obtained from fully supervised model training on the dataset.

Contrastive learning models based on Siamese structure have demonstrated remarkable performance in self-supervised learning. Such a success of contrastive learning relies on two conditions, a sufficient number of positive pairs and adequate variations between them. If the conditions are not met, these frameworks will lack semantic contrast and be fragile on overfitting. To address these two issues, we propose Hallucinator that could efficiently generate additional positive samples for further contrast. The Hallucinator is differentiable and creates new data in the feature space. Thus, it is optimized directly with the pre-training task and introduces nearly negligible computation. Moreover, we reduce the mutual information of hallucinated pairs and smooth them through non-linear operations. This process helps avoid over-confident contrastive learning models during the training and achieves more transformation-invariant feature embeddings. Remarkably, we empirically prove that the proposed Hallucinator generalizes well to various contrastive learning models, including MoCoV1&V2, SimCLR and SimSiam. Under the linear classification protocol, a stable accuracy gain is achieved, ranging from 0.3% to 3.0% on CIFAR10&100, Tiny ImageNet, STL-10 and ImageNet. The improvement is also observed in transferring pre-train encoders to the downstream tasks, including object detection and segmentation.

Early, precise detection of nutrient deficiency stress (NDS) has key economic as well as environmental impact; precision application of chemicals in place of blanket application reduces operational costs for the growers while reducing the amount of chemicals which may enter the environment unnecessarily. Furthermore, earlier treatment reduces the amount of loss and therefore boosts crop production during a given season. With this in mind, we collect sequences of high-resolution aerial imagery and construct semantic segmentation models to detect and predict NDS across the field. Our work sits at the intersection of agriculture, remote sensing, and modern computer vision and deep learning. First, we establish a baseline for full-field detection of NDS and quantify the impact of pretraining, backbone architecture, input representation, and sampling strategy. We then quantify the amount of information available at different points in the season by building a single-timestamp model based on a UNet. Next, we construct our proposed spatiotemporal architecture, which combines a UNet with a convolutional LSTM layer, to accurately detect regions of the field showing NDS; this approach has an impressive IOU score of 0.53. Finally, we show that this architecture can be trained to predict regions of the field which are expected to show NDS in a later flight -- potentially more than three weeks in the future -- maintaining an IOU score of 0.47-0.51 depending on how far in advance the prediction is made. We will also release a dataset which we believe will benefit the computer vision, remote sensing, as well as agriculture fields. This work contributes to the recent developments in deep learning for remote sensing and agriculture, while addressing a key social challenge with implications for economics and sustainability.

The increasing number of vision-based tracking systems deployed in production have necessitated fast, robust camera calibration. In the domain of sport, the majority of current work focuses on sports where lines and intersections are easy to extract, and appearance is relatively consistent across venues. However, for more challenging sports like basketball, those techniques are not sufficient. In this paper, we propose an end-to-end approach for single moving camera calibration across challenging scenarios in sports. Our method contains three key modules: 1) area-based court segmentation, 2) camera pose estimation with embedded templates, 3) homography prediction via a spatial transform network (STN). All three modules are connected, enabling end-to-end training. We evaluate our method on a new college basketball dataset and demonstrate state of the art performance in variable and dynamic environments. We also validate our method on the World Cup 2014 dataset to show its competitive performance against the state-of-the-art methods. Lastly, we show that our method is two orders of magnitude faster than the previous state of the art on both datasets.

Analytics in professional sports has experienced a dramatic growth in the last decade due to the wide deployment of player and ball tracking systems in team sports, such as basketball and soccer. With the massive amount of fine-grained data being generated, new data-points are being generated, which can shed light on player and team performance. However, due to the complexity of plays in continuous sports, these data-points often lack the specificity and context to enable meaningful retrieval and analytics. In this article, we present an intelligent human--computer interface that utilizes trajectories instead of words, which enables specific play retrieval in sports. Various techniques of alignment, templating, and hashing were utilized by our system and they are tailored to multi-agent scenario so that interactive speeds can be achieved. We conduct a user study to compare our method to the conventional keywords-based system and the results show that our method significantly improves the retrieval quality. We also show how our interface can be utilized for broadcast purposes, where a user can draw and interact with trajectories on a broadcast view using computer vision techniques. Additionally, we show that our method can also be used for interactive analytics of player performance, which enables the users to move players around and see how performance changes as a function of position and proximity to other players.

We study the problem of modeling spatiotemporal trajectories over long time horizons using expert demonstrations. For instance, in sports, agents often choose action sequences with long-term goals in mind, such as achieving a certain strategic position. Conventional policy learning approaches, such as those based on Markov decision processes, generally fail at learning cohesive long-term behavior in such high-dimensional state spaces, and are only effective when fairly myopic decision-making yields the desired behavior. The key difficulty is that conventional models are ``single-scale'' and only learn a single state-action policy. We instead propose a hierarchical policy class that automatically reasons about both long-term and short-term goals, which we instantiate as a hierarchical neural network. We showcase our approach in a case study on learning to imitate demonstrated basketball trajectories, and show that it generates significantly more realistic trajectories compared to non-hierarchical baselines as judged by professional sports analysts.

During natural exploration, rats exhibit two particularly conspicuous vibrissal-mediated behaviors: they follow along walls, and "dab" their snouts on the ground at frequencies related to the whisking cycle. In general, the walls and ground may be located at any distance from, and at any orientation relative to, the rat's head, which raises the question of how the rat might determine the position and orientation of these surfaces. Previous studies have compellingly demonstrated that rats can accurately determine the horizontal angle at which a vibrissa first touches an object, and we therefore asked whether this parameter could provide the rat with information about the pitch, distance, and yaw of a surface relative to its head. We used a three-dimensional model of the whisker array to construct mappings between the horizontal angle of contact of each vibrissa and every possible (pitch, distance, and yaw) configuration of the head relative to a flat surface. The mappings revealed striking differences in the patterns of contact for vibrissae in different regions of the array. The exterior (A, D, E) rows provide information about the relative pitch of the surface regardless of distance. The interior (B, C) rows provide distance cues regardless of head pitch. Yaw is linearly correlated with the difference between the number of right and left whiskers touching the surface. Compared to the long reaches that whiskers can make to the side and below the rat, the reachable distance in front of the rat's nose is relatively small. We confirmed key predictions of these functional groupings in a behavioral experiment that monitored the contact patterns that the vibrissae made with a flat vertical surface. These results suggest that vibrissae in different regions of the array are not interchangeable sensors, but rather functionally grouped to acquire particular types of information about the environment.