Related papers: Hadamax Encoding: Elevating Performance in Model-F…
Motivated by the success of encoding multi-scale contextual information for image analysis, we propose our PointAtrousGraph (PAG) - a deep permutation-invariant hierarchical encoder-decoder for efficiently exploiting multi-scale edge…
Transformer is a state-of-the-art model in the field of natural language processing (NLP). Current NLP models primarily increase the number of transformers to improve processing performance. However, this technique requires a lot of…
Continual learning is a desirable feature in many modern machine learning applications, which allows in-field adaptation and updating, ranging from accommodating distribution shift, to fine-tuning, and to learning new tasks. For…
As acquiring pixel-wise annotations of real-world images for semantic segmentation is a costly process, a model can instead be trained with more accessible synthetic data and adapted to real images without requiring their annotations. This…
This paper presents a set of full-resolution lossy image compression methods based on neural networks. Each of the architectures we describe can provide variable compression rates during deployment without requiring retraining of the…
Machine Learning has become the bedrock of recent advances in text, image, video, and audio processing and generation. Most production systems deal with several models during deployment and training, each with a variety of tuned…
Reconstruction of high-definition maps is a crucial task in perceiving the autonomous driving environment, as its accuracy directly impacts the reliability of prediction and planning capabilities in downstream modules. Current vectorized…
Many modern video processing pipelines rely on edge-aware (EA) filtering methods. However, recent high-quality methods are challenging to run in real-time on embedded hardware due to their computational load. To this end, we propose an…
AdaNet is a lightweight TensorFlow-based (Abadi et al., 2015) framework for automatically learning high-quality ensembles with minimal expert intervention. Our framework is inspired by the AdaNet algorithm (Cortes et al., 2017) which learns…
The variable and unpredictable load demands in hybrid agricultural tractors make it difficult to design optimal rule-based energy management strategies, motivating the use of adaptive, learning-based control. However, existing approaches…
Generative Adversarial Networks (GANs) have achieved state-of-the-art performance for several image generation and manipulation tasks. Different works have improved the limited understanding of the latent space of GANs by embedding images…
The future of artificial intelligence (AI) acceleration demands a paradigm shift beyond the limitations of purely electronic or photonic architectures. Photonic analog computing delivers unmatched speed and parallelism but struggles with…
To utilize pre-trained neural networks on edge and mobile devices, we often require efficient adaptation to user-specific runtime data distributions while operating under limited compute and memory resources. On-device retraining with a…
We investigate deep neural network performance in the textindependent speaker recognition task. We demonstrate that using angular softmax activation at the last classification layer of a classification neural network instead of a simple…
Denoising diffusion models have emerged as state-of-the-art in generative tasks across image, audio, and video domains, producing high-quality, diverse, and contextually relevant data. However, their broader adoption is limited by high…
Nowadays, IEEE 802.11, i.e., Wi-Fi has emerged as a prevailing technology for broadband wireless networking. To meet the tremendous rise of demand for future generation wireless LANs, a robust and efficient MAC protocol is required for the…
Diffusion Models (DMs) have exhibited superior performance in generating high-quality and diverse images. However, this exceptional performance comes at the cost of expensive architectural design, particularly due to the attention module…
Transformer models have achieved remarkable success in various machine learning tasks but suffer from high computational complexity and resource requirements. The quadratic complexity of the self-attention mechanism further exacerbates…
From a young age humans learn to use grammatical principles to hierarchically combine words into sentences. Action grammars is the parallel idea, that there is an underlying set of rules (a "grammar") that govern how we hierarchically…
Orthogonal frequency division multiplexing (OFDM) is a modulation technique susceptible to source, channel and amplifier nonlinearities because of its high peak-to-average ratio (PAPR). The distortion gets worse by increasing the average…