Related papers: Base Layer Efficiency in Scalable Human-Machine Co…
Computer Vision techniques represent a class of algorithms that are highly computation and data intensive in nature. Generally, performance of these algorithms in terms of execution speed on desktop computers is far from real-time. Since…
Large Language Models (LLMs) have achieved remarkable success in source code understanding, yet as software systems grow in scale, computational efficiency has become a critical bottleneck. Currently, these models rely on a text-based…
Video Coding for Machines (VCM) aims to compress visual signals for machine analysis. However, existing methods only consider a few machines, neglecting the majority. Moreover, the machine's perceptual characteristics are not leveraged…
We describe an approach for segmenting an image into regions that correspond to surfaces in the scene that are partially surrounded by the medium. It integrates both appearance and motion statistics into a cost functional, that is seeded…
Automated surface-anomaly detection using machine learning has become an interesting and promising area of research, with a very high and direct impact on the application domain of visual inspection. Deep-learning methods have become the…
This paper offers a new perspective on the limits of machine learning: the ceiling on progress is set not by model size or algorithm choice but by the information structure of the task itself. Code generation has progressed more reliably…
Accurate 3D object detection is a critical component of autonomous driving, enabling vehicles to perceive their surroundings with precision and make informed decisions. LiDAR sensors, widely used for their ability to provide detailed 3D…
Large Language Models have shown impressive capabilities in coding tasks like code generation and code completion, as they have been trained on a large amount of code data. Also, since one of the core pretraining objectives is Next Token…
The many successes of deep neural networks (DNNs) over the past decade have largely been driven by computational scale rather than insights from biological intelligence. Here, we explore if these trends have also carried concomitant…
With advances in data-driven machine learning research, a wide variety of prediction models have been proposed to capture spatio-temporal features for the analysis of video streams. Recognising actions and detecting action transitions…
We identify an issue in multi-task learnable compression, in which a representation learned for one task does not positively contribute to the rate-distortion performance of a different task as much as expected, given the estimated amount…
Recent studies have shown that the efficiency of deep neural networks in mobile applications can be significantly improved by distributing the computational workload between the mobile device and the cloud. This paradigm, termed…
While recent deep neural networks have achieved a promising performance on object recognition, they rely implicitly on the visual contents of the whole image. In this paper, we train deep neural net- works on the foreground (object) and…
We use static object data to improve success detection for stacking objects on and nesting objects in one another. Such actions are necessary for certain robotics tasks, e.g., clearing a dining table or packing a warehouse bin. However,…
Research on human face processing using eye movements has provided evidence that we recognize face images successfully focusing our visual attention on a few inner facial regions, mainly on the eyes, nose and mouth. To understand how we…
This paper studies a layered coding framework with a relaxed hierarchical structure. Advances in wired/wireless communication and consumer electronic devices have created a requirement for serving the same content at different quality…
The goal of this paper is to present a new efficient image segmentation method based on evolutionary computation which is a model inspired from human behavior. Based on this model, a four layer process for image segmentation is proposed…
Many images and videos are primarily processed by computer vision algorithms, involving only occasional human inspection. When this content requires compression before processing, e.g., in distributed applications, coding methods must…
Scaling up self-supervised learning has driven breakthroughs in language and vision, yet comparable progress has remained elusive in reinforcement learning (RL). In this paper, we study building blocks for self-supervised RL that unlock…
We propose a new strategy to decode color codes, which is based on the projection of the error onto three surface codes. This provides a method to transform every decoding algorithm of surface codes into a decoding algorithm of color codes.…