This paper introduces a novel approach that integrates graph theory into self-supervised representation learning. Traditional methods focus on intra-instance variations generated by applying augmentations. However, they often overlook important inter-instance relationships. While our method retains the intra-instance property, it further captures inter-instance relationships by constructing$k$-nearest neighbor (KNN) graphs for both teacher and student streams during pretraining. In these graphs, nodes represent samples along with their latent representations. Edges encode the similarity between instances. Following pretraining, a representation refinement phase is performed. In this phase, Graph Neural Networks (GNNs) propagate messages not only among immediate neighbors but also across multiple hops, thereby enabling broader contextual integration. Experimental results on CIFAR-10, ImageNet-100, and ImageNet-1K demonstrate accuracy improvements of 7.3%, 3.2%, and 1.0%, respectively, over state-of-the-art methods. These results highlight the effectiveness of the proposed graph-based mechanism. The code is publicly available athttps://github.com/alijavidani/SSL-GraphNNCLR.

MOTIVATION: Finding outliers in RNA-sequencing (RNA-Seq) gene expression (GE) can help in identifying genes that are aberrant and cause Mendelian disorders. Recently developed models for this task rely on modeling RNA-Seq GE data using the negative binomial distribution (NBD). However, some of those models either rely on procedures for inferring NBD's parameters in a nonbiased way that are computationally demanding and thus make confounder control challenging, while others rely on less computationally demanding but biased procedures and convoluted confounder control approaches that hinder interpretability. RESULTS: In this article, we present OutSingle (Outlier detection using Singular Value Decomposition), an almost instantaneous way of detecting outliers in RNA-Seq GE data. It uses a simple log-normal approach for count modeling. For confounder control, it uses the recently discovered optimal hard threshold (OHT) method for noise detection, which itself is based on singular value decomposition (SVD). Due to its SVD/OHT utilization, OutSingle's model is straightforward to understand and interpret. We then show that our novel method, when used on RNA-Seq GE data with real biological outliers masked by confounders, outcompetes the previous state-of-the-art model based on an ad hoc denoising autoencoder. Additionally, OutSingle can be used to inject artificial outliers masked by confounders, which is difficult to achieve with previous approaches. We describe a way of using OutSingle for outlier injection and proceed to show how OutSingle outperforms its competition on 16 out of 18 datasets that were generated from three real datasets using OutSingle's injection procedure with different outlier types and magnitudes. Our methods are applicable to other types of similar problems involving finding outliers in matrices under the presence of confounders. AVAILABILITY AND IMPLEMENTATION: The code for OutSingle is available at https://github.com/esalkovic/outsingle.

Accurately maintaining digital street maps is labor-intensive. To address this challenge, much work has studied automatically processing geospatial data sources such as GPS trajectories and satellite images to reduce the cost of maintaining digital maps. An end-to-end map update system would first process geospatial data sources to extract insights, and second leverage those insights to update and improve the map. However, prior work largely focuses on the first step of this pipeline: these map extraction methods infer road networks from scratch given geospatial data sources (in effect creating entirely new maps), but do not address the second step of leveraging this extracted information to update the existing map data. In this paper, we first explain why current map extraction techniques yield low accuracy when extended to update existing maps. We then propose a novel method that leverages the progression of satellite imagery over time to substantially improve accuracy. Our approach first compares satellite images captured at different times to identify portions of the physical road network that have visibly changed, and then updates the existing map accordingly. We show that our change-based approach reduces error rates four-fold.

Traffic accidents cost about 3% of the world’s GDP and are the leading cause of death in children and young adults. Accident risk maps are useful tools to monitor and mitigate accident risk. We present a technique to generate high-resolution (5 meters) accident risk maps. At this high resolution, accidents are sparse and risk estimation is limited by bias-variance trade-off. Prior accident risk maps either estimate low-resolution maps that are of low utility (high bias), or they use frequency-based estimation techniques that inaccurately predict where accidents actually happen (high variance). To improve this trade-off, we use an end-to-end deep architecture that can input satellite imagery, GPS trajectories, road maps and the history of accidents. Our evaluation on four metropolitan areas in the US with a total area of 7,488 km2shows that our technique outperform prior work in terms of resolution and accuracy.

Inferring road attributes such as lane count and road type from satellite imagery is challenging. Often, due to the occlusion in satellite imagery and the spatial correlation of road attributes, a road attribute at one position on a road may only be apparent when considering far-away segments of the road. Thus, to robustly infer road attributes, the model must integrate scattered information and capture the spatial correlation of features along roads. Existing solutions that rely on image classifiers fail to capture this correlation, resulting in poor accuracy. We find this failure is caused by a fundamental limitation – the limited effective receptive field of image classifiers.To overcome this limitation, we propose RoadTagger, an end-to-end architecture which combines both Convolutional Neural Networks (CNNs) and Graph Neural Networks (GNNs) to infer road attributes. Using a GNN allows information to propagate on the road network graph and eliminates the receptive field limitation of image classifiers. We evaluate RoadTagger on both a large real-world dataset covering 688 km2 area in 20 U.S. cities and a synthesized dataset. In the evaluation, RoadTagger improves inference accuracy over the CNN image classifier based approaches. In addition, RoadTagger is robust to disruptions in the satellite imagery and is able to learn complicated inductive rules for aggregating scattered information along the road network.

We present a simple yet effective learning technique that significantly improves mAP of YOLO object detectors without compromising their speed. During network training, we carefully feed in localization information. We excite certain activations in order to help the network learn to better localize (Figure 2). In the later stages of training, we gradually reduce our assisted excitation to zero. We reached a new state-of-the-art in the speed-accuracy trade-off (Figure 1). Our technique improves the mAP of YOLOv2 by 3.8% and mAP of YOLOv3 by 2.2% on MSCOCO dataset. This technique is inspired from curriculum learning. It is simple and effective and it is applicable to most single-stage object detectors.

Applying linear templates is an integral part of many object detection systems and accounts for a significant portion of computation time. We describe a method that achieves a substantial end-to-end speedup over the best current methods, without loss of accuracy. Our method is a combination of approximating scores by vector quantizing feature windows and a number of speedup techniques including cascade. Our procedure allows speed and accuracy to be traded off in two ways: by choosing the number of Vector Quantization levels, and by choosing to rescore windows or not. Our method can be directly plugged into any recognition system that relies on linear templates. We demonstrate our method to speed up the original Exemplar SVM detector [1] by an order of magnitude and Deformable Part models [2] by two orders of magnitude with no loss of accuracy.

In this paper, we introduce visual phrases, complex visual composites like "a person riding a horse." Visual phrases often display significantly reduced visual complexity compared to their component objects because the appearance of those objects can change profoundly when they participate in relations. We introduce a dataset suitable for phrasal recognition that uses familiar PASCAL object categories, and demonstrate significant experimental gains resulting from exploiting visual phrases. We show that a visual phrase detector significantly outperforms a baseline which detects component objects and reasons about relations, even though visual phrase training sets tend to be smaller than those for objects. We argue that any multiclass detection system must decode detector outputs to produce final results; this is usually done with nonmaximum suppression. We describe a novel decoding procedure that can account accurately for local context without solving difficult inference problems. We show this decoding procedure outperforms the state of the art. Finally, we show that decoding a combination of phrasal and object detectors produces real improvements in detector results.

In this paper we introduce visual phrases, complex visual composites like “a person riding a horse”. Visual phrases often display significantly reduced visual complexity compared to their component objects, because the appearance of those objects can change profoundly when they participate in relations. We introduce a dataset suitable for phrasal recognition that uses familiar PASCAL object categories, and demonstrate significant experimental gains resulting from exploiting visual phrases. We show that a visual phrase detector significantly outperforms a baseline which detects component objects and reasons about relations, even though visual phrase training sets tend to be smaller than those for objects. We argue that any multi-class detection system must decode detector outputs to produce final results; this is usually done with non-maximum suppression. We describe a novel decoding procedure that can account accurately for local context without solving difficult inference problems. We show this decoding procedure outperforms the state of the art. Finally, we show that decoding a combination of phrasal and object detectors produces real improvements in detector results.