Related papers: Building Vision Models upon Heat Conduction
Recent vision architectures and self-supervised training methods enable vision models that are extremely accurate and general, but come with massive parameter and computational costs. In practical settings, such as camera traps, users have…
Learning representations in the joint domain of vision and touch can improve manipulation dexterity, robustness, and sample-complexity by exploiting mutual information and complementary cues. Here, we present Visuo-Tactile Transformers…
Vehicle-to-Vehicle technologies have enabled autonomous vehicles to share information to see through occlusions, greatly enhancing perception performance. Nevertheless, existing works all focused on homogeneous traffic where vehicles are…
Behavior prediction in dynamic, multi-agent systems is an important problem in the context of self-driving cars, due to the complex representations and interactions of road components, including moving agents (e.g. pedestrians and vehicles)…
We investigate methods to reduce inference time and memory footprint in stable diffusion models by introducing lightweight decoders for both image and video synthesis. Traditional latent diffusion pipelines rely on large Variational…
Salient object detection models often demand a considerable amount of computation cost to make precise prediction for each pixel, making them hardly applicable on low-power devices. In this paper, we aim to relieve the contradiction between…
This paper investigates how working of Convolutional Neural Network (CNN) can be explained through visualization in the context of machine perception of autonomous vehicles. We visualize what type of features are extracted in different…
We study the problem of concept induction in visual reasoning, i.e., identifying concepts and their hierarchical relationships from question-answer pairs associated with images; and achieve an interpretable model via working on the induced…
We develop a physics-based model for classical computation based on autonomous quantum thermal machines. These machines consist of few interacting quantum bits (qubits) connected to several environments at different temperatures. Heat flows…
This report details the design and optimisation of a water-cooled forced convection heat dissipation system for use in high-temperature applications (ranges between 700 degrees - 1000 degrees K). A hollow cuboid vapour chamber model was…
We present Neural Memory Object (NeMO), a novel object-centric representation that can be used to detect, segment and estimate the 6DoF pose of objects unseen during training using RGB images. Our method consists of an encoder that requires…
Split computing ($\neq$ split learning) is a promising approach to deep learning models for resource-constrained edge computing systems, where weak sensor (mobile) devices are wirelessly connected to stronger edge servers through channels…
Recent work has shown that learned image compression strategies can outperform standard hand-crafted compression algorithms that have been developed over decades of intensive research on the rate-distortion trade-off. With growing…
Global Climate Models (GCMs) are critical for simulating large-scale climate dynamics, but their coarse spatial resolution limits their applicability in regional studies. Regional Climate Models (RCMs) address this limitation through…
We propose a hybrid architecture for systematically computing robust visual explanation(s) encompassing hypothesis formation, belief revision, and default reasoning with video data. The architecture consists of two tightly integrated…
Understanding how people allocate visual attention is central to Human-Computer Interaction (HCI), yet existing computational models of attention are often either descriptive, task-specific, or difficult to interpret. My dissertation…
The speed and fidelity of detector simulations in particle physics pose compelling questions about LHC analysis and future colliders. The sparse high-dimensional data, combined with the required precision, provide a challenging task for…
An image based prediction of the effective heat conductivity for highly heterogeneous microstructured materials is presented. The synthetic materials under consideration show different inclusion morphology, orientation, volume fraction and…
Transformer-based methods have shown impressive performance in low-level vision tasks, such as image super-resolution. However, we find that these networks can only utilize a limited spatial range of input information through attribution…
Self-supervised representation learning has shown significant improvement in Natural Language Processing and 2D Computer Vision. However, existing methods face difficulties in representing 3D data because of its unordered and uneven…