Related papers: Collinear features impair visual detection by rats

In this work we present point-level region contrast, a self-supervised pre-training approach for the task of object detection. This approach is motivated by the two key factors in detection: localization and recognition. While accurate…

Instance recognition is rapidly advanced along with the developments of various deep convolutional neural networks. Compared to the architectures of networks, the training process, which is also crucial to the success of detectors, has…

Face alignment is crucial for face recognition and has been widely adopted. However, current practice is too simple and under-explored. There lacks an understanding of how important face alignment is and how it should be performed, for…

Selective attention can momentarily alter visual appearance, but can such effects be learned? We tested whether training attention under sensory competition produces lasting changes in perceived contrast. Across seven days, participants…

Multispectral pedestrian detection has shown great advantages under poor illumination conditions, since the thermal modality provides complementary information for the color image. However, real multispectral data suffers from the position…

In projectors and head-mounted displays, an out-of-focus image appears blurred. Even when a display itself is in focus, computer operation may be hindered if the display is far from the user or if a user has poor visual acuity, because the…

How similar is the human mind to the sophisticated machine-learning systems that mirror its performance? Models of object categorization based on convolutional neural networks (CNNs) have achieved human-level benchmarks in assigning known…

Redundancies and correlations in the responses of sensory neurons seem to waste neural resources but can carry cues about structured stimuli and may help the brain to correct for response errors. To assess how the retina negotiates this…

Due to their powerful feature association capabilities, neural network-based computer vision models have the ability to detect and exploit unintended patterns within the data, potentially leading to correct predictions based on incorrect or…

As we move through the world, the pattern of light projected on our eyes is complex and dynamic, yet we are still able to distinguish between moving and stationary objects. We propose that humans accomplish this by exploiting constraints…

Analyzing animal behavior from video recordings is crucial for scientific research, yet manual annotation remains labor-intensive and prone to subjectivity. Efficient segmentation methods are needed to automate this process while…

Contrastive learning, which aims at minimizing the distance between positive pairs while maximizing that of negative ones, has been widely and successfully applied in unsupervised feature learning, where the design of positive and negative…

Recently, a considerable number of studies in computer vision involves deep neural architectures called vision transformers. Visual processing in these models incorporates computational models that are claimed to implement attention…

Due to their shorter operating range and large bandwidth, automotive radars can resolve many reflections from their targets of interest, mainly vehicles. This calls for the use of extended-target models in place of simpler and more…

Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved performance on tasks such as visual grounding and visual question answering. However, the reasoning processes of these models remain largely opaque;…

In recent years, driven by the need for safer and more autonomous transport systems, the automotive industry has shifted toward integrating a growing number of Advanced Driver Assistance Systems (ADAS). Among the array of sensors employed…

Many state-of-the-art trackers usually resort to the pretrained convolutional neural network (CNN) model for correlation filtering, in which deep features could usually be redundant, noisy and less discriminative for some certain instances,…

Multimodal models like CLIP have gained significant attention due to their remarkable zero-shot performance across various tasks. However, studies have revealed that CLIP can inadvertently learn spurious associations between target…

Clinical prediction models are developed widely across medical disciplines. When predictors in such models are highly collinear, unexpected or spurious predictor-outcome associations may occur, thereby potentially reducing face-validity and…

The bilateral asymmetry of flanks of animals with visual body marks that uniquely identify an individual, complicates tasks like population estimations. Automatically generated additional information on the visible side of the animal would…