Related papers: Adaptive Patch Exiting for Scalable Single Image S…
Camera Image Signal Processing (ISP) pipelines can get appealing results in different image signal processing tasks. Nonetheless, the majority of these methods, including those employing an encoder-decoder deep architecture for the task,…
Real-time path tracing increasingly operates under extremely low sampling budgets, often below one sample per pixel, as rendering complexity, resolution, and frame-rate requirements continue to rise. While super-resolution is widely used in…
This paper proposes an efficient content adaptive screen image scaling scheme for the real-time screen applications like remote desktop and screen sharing. In the proposed screen scaling scheme, a screen content classification step is first…
Today, artificial neural networks are the state of the art for solving a variety of complex tasks, especially in image classification. Such architectures consist of a sequence of stacked layers with the aim of extracting useful information…
The popularity of Contrastive Language-Image Pre-training (CLIP) has propelled its application to diverse downstream vision tasks. To improve its capacity on downstream tasks, few-shot learning has become a widely-adopted technique.…
Recently, the performance of single image super-resolution (SR) has been significantly improved with powerful networks. However, these networks are developed for image SR with a single specific integer scale (e.g., x2;x3,x4), and cannot be…
Scaling up deep neural network capacity has been known as an effective approach to improving model quality for several different machine learning tasks. In many cases, increasing model capacity beyond the memory limit of a single…
Fixed representational capacity is a fundamental constraint in continual learning: practitioners must guess an appropriate model width before training, without knowing how many distinct concepts the data contains. We propose LACE…
Supercomputers getting ever larger and energy-efficient is at odds with the reliability of the used hardware. Thus, the time intervals between component failures are decreasing. Contrarily, the latencies for individual operations of…
In recent times, with the exception of sporadic cases, the trend in Computer Vision is to achieve minor improvements compared to considerable increases in complexity. To reverse this trend, we propose a novel method to boost image…
The primary challenge in accelerating image super-resolution lies in reducing computation while maintaining performance and adaptability. Motivated by the observation that high-frequency regions (e.g., edges and textures) are most critical…
Anomaly Detection is a relevant problem that arises in numerous real-world applications, especially when dealing with images. However, there has been little research for this task in the Continual Learning setting. In this work, we…
The edge detection task is essential in image processing aiming to extract relevant information from an image. One recurring problem in this task is the weaknesses found in some detectors, such as the difficulty in detecting loose edges and…
In this paper, we study adaptive neuron enhancement (ANE) method for solving self-adjoint second-order elliptic partial differential equations (PDEs). The ANE method is a self-adaptive method generating a two-layer spline NN and a numerical…
Evaluating rare but high-stakes events is one of the main challenges in obtaining reliable reinforcement learning policies, especially in large or infinite state/action spaces where limited scalability dictates a prohibitively large number…
While Reinforcement Learning (RL) agents can successfully learn to handle complex tasks, effectively generalizing acquired skills to unfamiliar settings remains a challenge. One of the reasons behind this is the visual encoders used are…
Decoder-only autoregressive image generation typically relies on fixed-length tokenization schemes whose token counts grow quadratically with resolution, substantially increasing the computational and memory demands of attention. We present…
Recent learning-based super-resolution (SR) methods often focus on dictionary learning or network training. In this paper, we discuss in detail a new SR method based on local patch encoding (LPE) instead of traditional dictionary learning.…
Learning light-weight yet expressive deep networks in both image synthesis and image recognition remains a challenging problem. Inspired by a more recent observation that it is the data-specificity that makes the multi-head self-attention…
Spiking neural networks (SNNs) have gained prominence for their potential in neuromorphic computing and energy-efficient artificial intelligence, yet optimizing them remains a formidable challenge for gradient-based methods due to their…