Related papers: ImageHD: Energy-Efficient On-Device Continual Lear…
The emerging Learned Compression (LC) replaces the traditional codec modules with Deep Neural Networks (DNN), which are trained end-to-end for rate-distortion performance. This approach is considered as the future of image/video…
Online continual learning aims to learn from a non-IID stream of data from a number of different tasks, where the learner is only allowed to consider data once. Methods are typically allowed to use a limited buffer to store some of the…
Incremental learning that learns new classes over time after the model's deployment is becoming increasingly crucial, particularly for industrial edge systems, where it is difficult to communicate with a remote server to conduct…
Image Understanding is becoming a vital feature in ever more applications ranging from medical diagnostics to autonomous vehicles. Many applications demand for embedded solutions that integrate into existing systems with tight real-time and…
Existing deep convolutional neural networks (CNNs) have shown their great success on image classification. CNNs mainly consist of convolutional and pooling layers, both of which are performed on local image areas without considering the…
Intrinsic image decomposition is the process of recovering the image formation components (reflectance and shading) from an image. Previous methods employ either explicit priors to constrain the problem or implicit constraints as formulated…
Recently deep learning-based methods have been applied in image compression and achieved many promising results. In this paper, we propose an improved hybrid layered image compression framework by combining deep learning and the traditional…
We present a novel algorithm to reduce tensor compute required by a conditional image generation autoencoder without sacrificing quality of photo-realistic image generation. Our method is device agnostic, and can optimize an autoencoder for…
With the goal of recovering high-quality image content from its degraded version, image restoration enjoys numerous applications, such as in surveillance, computational photography, medical imaging, and remote sensing. Recently,…
Large-scale multi-modal contrastive learning frameworks like CLIP typically require a large amount of image-text samples for training. However, these samples are always collected continuously in real scenarios. This paper discusses the…
The increasing demand for on-device intelligence in Edge AI and TinyML applications requires the efficient execution of modern Convolutional Neural Networks (CNNs). While lightweight architectures like MobileNetV2 employ Depthwise Separable…
Developing deep learning models to analyze histology images has been computationally challenging, as the massive size of the images causes excessive strain on all parts of the computing pipeline. This paper proposes a novel deep…
Embodied vision-based real-world systems, such as mobile robots, require a careful balance between energy consumption, compute latency, and safety constraints to optimize operation across dynamic tasks and contexts. As local computation…
Recent works on learned image compression perform encoding and decoding processes in a full-resolution manner, resulting in two problems when deployed for practical applications. First, parallel acceleration of the autoregressive entropy…
Convolutional neural networks rely on image texture and structure to serve as discriminative features to classify the image content. Image enhancement techniques can be used as preprocessing steps to help improve the overall image quality…
Hepatocellular carcinoma (HCC) is a common type of liver cancer whose early-stage diagnosis is a common challenge, mainly due to the manual assessment of hematoxylin and eosin-stained whole slide images, which is a time-consuming process…
In recent years, Convolutional Neural Networks (CNNs) have enabled ubiquitous image processing applications. As such, CNNs require fast runtime (forward propagation) to process high-resolution visual streams in real time. This is still a…
Hyperdimensional Computing (HDC) is a bio-inspired computing framework that has gained increasing attention, especially as a more efficient approach to machine learning (ML). This work introduces the \name{} compiler, the first open-source…
Traditional spectral imaging methods are constrained by the time-consuming scanning process, limiting the application in dynamic scenarios. One-shot spectral imaging based on reconstruction has been a hot research topic recently and the…
Inspired by the way human brain works, the emerging hyperdimensional computing (HDC) is getting more and more attention. HDC is an emerging computing scheme based on the working mechanism of brain that computes with deep and abstract…