Related papers: A photosensor employing data-driven binning for ul…

Research has shown that convolutional neural networks contain significant redundancy, and high classification accuracy can be obtained even when weights and activations are reduced from floating point to binary values. In this paper, we…

Twenty-three machine learning algorithms were trained then scored to establish baseline comparison metrics and to select an image classification algorithm worthy of embedding into mission-critical satellite imaging systems. The…

Image inpainting refers to filling missing places in images using neighboring pixels. It also has many applications in different tasks of image processing. Most of these applications enhance the image quality by significant unwanted changes…

Snapshot compressed sensing (CS) refers to compressive imaging systems in which multiple frames are mapped into a single measurement frame. Each pixel in the acquired frame is a noisy linear mapping of the corresponding pixels in the frames…

Binary change detection in bi-temporal co-registered hyperspectral images is a challenging task due to a large number of spectral bands present in the data. Researchers, therefore, try to handle it by reducing dimensions. The proposed work…

Masked Image Modeling (MIM) is a self-supervised learning technique that involves masking portions of an image, such as pixels, patches, or latent representations, and training models to predict the missing information using the visible…

Time-bin encoding is a robust form of optical quantum information, especially for transmission in optical fibers. To read out the information, the separation of the time bins must be larger than the detector time resolution, typically on…

Recent vision-language models outperform vision-only models on many image classification tasks. However, because of the absence of paired text/image descriptions, it remains difficult to fine-tune these models for fine-grained image…

Fine-grained image classification remains challenging due to the large intra-class variance and small inter-class variance. Since the subtle visual differences are only in local regions of discriminative parts among subcategories, part…

Histograms are convenient non-parametric density estimators, which continue to be used ubiquitously. Summary quantities estimated from histogram-based probability density models depend on the choice of the number of bins. We introduce a…

Binary hashing is a well-known approach for fast approximate nearest-neighbor search in information retrieval. Much work has focused on affinity-based objective functions involving the hash functions or binary codes. These objective…

This paper proposes a novel semi-supervised method on object recognition. First, based on Boost Picking, a universal algorithm, Boost Picking Teaching (BPT), is proposed to train an effective binary-classifier just using a few labeled data…

Recent progress in image recognition has stimulated the deployment of vision systems at an unprecedented scale. As a result, visual data are now often consumed not only by humans but also by machines. Existing image processing methods only…

In real world scenarios, objects are often partially occluded. This requires a robustness for object recognition against these perturbations. Convolutional networks have shown good performances in classification tasks. The learned…

Random projections have proven extremely useful in many signal processing and machine learning applications. However, they often require either to store a very large random matrix, or to use a different, structured matrix to reduce the…

Semantic segmentation is a powerful method to facilitate visual scene understanding. Each pixel is assigned a label according to a pre-defined list of object classes and semantic entities. This becomes very useful as a means to summarize…

Recent deep learning-based methods for lossy image compression achieve competitive rate-distortion performance through extensive end-to-end training and advanced architectures. However, emerging applications increasingly prioritize semantic…

Creating datasets for Neuromorphic Vision is a challenging task. A lack of available recordings from Neuromorphic Vision sensors means that data must typically be recorded specifically for dataset creation rather than collecting and…

Purpose- High speed image processing is a challenging task for real-time applications such as product quality control of manufacturing lines. Smart image sensors use an array of in-pixel processors to facilitate high-speed real-time image…

Single-pixel imaging can collect images at the wavelengths outside the reach of conventional focal plane array detectors. However, the limited image quality and lengthy computational times for iterative reconstruction still impede the…