Related papers: Reducing Lateral Visual Biases in Displays

Gender bias in vision-language models (VLMs) can reinforce harmful stereotypes and discrimination. In this paper, we focus on mitigating gender bias towards vision-language tasks. We identify object hallucination as the essence of gender…

An acousto-optic cell was used to reduce the speckle noise that reduces the quality of Hartmann-Shack and other wave-front sensors measuring ocular aberrations. In the method presented here, a laser beam traverses an acousto-optic cell,…

Real world images frequently exhibit multiple overlapping biases, including textures, watermarks, gendered makeup, scene object pairings, etc. These biases collectively impair the performance of modern vision models, undermining both their…

While deep learning surpasses human-level performance in narrow and specific vision tasks, it is fragile and over-confident in classification. For example, minor transformations in perspective, illumination, or object deformation in the…

Standard lossy image compression algorithms aim to preserve an image's appearance, while minimizing the number of bits needed to transmit it. However, the amount of information actually needed by a user for downstream tasks -- e.g.,…

Underwater images captured by Autonomous Underwater Vehicles (AUVs) are inevitably affected by artificial light sources, which often produce halos in the foreground of the camera and seriously interfere with the quality of the image. The…

Deep learning had already demonstrated its power in medical images, including denoising, classification, segmentation, etc. All these applications are proposed to automatically analyze medical images beforehand, which brings more…

Multi-view image-based rendering consists in generating a novel view of a scene from a set of source views. In general, this works by first doing a coarse 3D reconstruction of the scene, and then using this reconstruction to establish…

Image processing techniques provide important assistance to physicians and relieve their workload in different tasks. In particular, identifying objects of interest such as lesions and anatomical structures from the image is a challenging…

A lateral shear interferometer based digital holographic microscopy has been realized to study the morphology dynamics of Human red blood cells quantitatively. Here, a lateral shear interferometer is embedded with a conventional microscope…

Vision-language (VL) understanding tasks evaluate models' comprehension of complex visual scenes through multiple-choice questions. However, we have identified two dataset biases that models can exploit as shortcuts to resolve various VL…

Chromatic dispersion, an inherent wavelength-dependent phenomenon in optical systems, has traditionally been regarded as a detrimental effect to be minimized in imaging and display. Here, we present a paradigm shift by deliberately…

Neuroscientific evidence shows that for most brain networks all pathways between cortical regions either pass through the thalamus or a transthalamic parallel route exists for any direct corticocortical connection. This paper seeks to…

Vision, as an inexpensive yet information rich sensor, is commonly used for perception on autonomous mobile robots. Unfortunately, accurate vision-based perception requires a number of assumptions about the environment to hold -- some…

A linear neural network is proposed for mamalian vision system in which backward connections from the primary visual cortex (V1) to the lateral geniculate nucleus play a key role. The backward connections control the flow of information…

As computer vision systems become more widely deployed, there is increasing concern from both the research community and the public that these systems are not only reproducing but amplifying harmful social biases. The phenomenon of bias…

There is an intricate relation between the properties of an image and how humans behave while describing the image. This behavior shows ample variation, as manifested in human signals such as eye movements and when humans start to describe…

Action recognition models rely excessively on static cues rather than dynamic human motion, which is known as static bias. This bias leads to poor performance in real-world applications and zero-shot action recognition. In this paper, we…

Multimodal representation learning, exemplified by multimodal contrastive learning (MMCL) using image-text pairs, aims to learn powerful representations by aligning cues across modalities. This approach relies on the core assumption that…

Adversarial learning can learn fairer and less biased models of language than standard methods. However, current adversarial techniques only partially mitigate model bias, added to which their training procedures are often unstable. In this…