SD-Pose: Semantic Decomposition for Cross-Domain 6D Object Pose Estimation

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Pulmonary nodules and masses are crucial imaging features in lung cancer screening that require careful management in clinical diagnosis. Despite the success of deep learning-based medical image segmentation, the robust performance on various sizes of lesi ...

The set of finite binary matrices of a given size is known to carry a finite type AA bicrystal structure. We first review this classical construction, explain how it yields a short proof of the equality between Kostka polynomials and one-dimensional sums t ...

The monumental progress in the development of machine learning models has led to a plethora of applications with transformative effects in engineering and science. This has also turned the attention of the research community towards the pursuit of construc ...

We present two open-source Python packages: "electron spectro-microscopy"(espm) and "electron microscopy tables"(emtables). The espm software enables the simulation of scanning transmission electron microscopy energy-dispersive X-ray spectroscopy datacubes ...

We address the problem of segmenting anomalies and unusual obstacles in road scenes for the purpose of self-driving safety. The objects in question are not present in the common training sets as it is not feasible to collect and annotate examples for every ...

Superoxide radicals (O-2(center dot-)) have been suggested as an important chain carrier in the radical chain reaction that promotes ozone (O-3) decomposition to hydroxyl radicals ((OH)-O-center dot) during ozonation. However, due to the difficulty in meas ...

We propose a method for adapting neural networks to distribution shifts at test-time. In contrast to training-time robustness mechanisms that attempt to anticipate and counter the shift, we create a closed-loop system and make use of test-time feedback sig ...

The accurate, robust and efficient transfer of the deformation gradient tensor between meshes of different resolution is crucial in cardiac electromechanics simulations. This paper presents a novel method that combines rescaled localized Radial Basis Funct ...

Most recent 6D object pose estimation methods first use object detection to obtain 2D bounding boxes before actually regressing the pose. However, the general object detection methods they use are ill-suited to handle cluttered scenes, thus producing poor ...

Along with the successful deployment of deep neural networks in several application domains, the need to unravel the black-box nature of these networks has seen a significant increase recently. Several methods have been introduced to provide insight into t ...

In this thesis, we discuss the problems of scattering and optical manipulation related to nanosystems of different complexities. The multipolar decomposition method is used to represent scattering processes in nanosystems as a series of elementary excitati ...

Explainable AI (XAI) methods aim to describe the decision process of deep neural networks. Early XAI methods produced visual explanations, whereas more recent techniques generate multimodal explanations that include textual information and visual represent ...

The successes of deep learning for semantic segmentation can in be, in part, attributed to its scale: a notion that encapsulates the largeness of these computational architectures and the labeled datasets they are trained on. These resource requirements hi ...

We consider the problem of compressing an information source when a correlated one is available as side information only at the decoder side, which is a special case of the distributed source coding problem in information theory. In particular, we consider ...

The Joint Photographic Experts Group (JPEG) AI learning-based image coding system is an ongoing joint standardization effort between International Organization for Standardization (ISO), International Electrotechnical Commission (IEC), and International Te ...

Mapping behavioural actions to neural activity is a fundamental goal of neuroscience. As our ability to record large neural and behavioural data increases, there is growing interest in modelling neural dynamics during adaptive behaviours to probe neural re ...

This paper introduces TACOSS a text-image alignment approach that allows explainable land cover semantic segmentation by directly integrating semantic concepts encoded from texts. TACOSS combines convolutional neural networks for visual feature extraction ...

SD-Pose: Semantic Decomposition for Cross-Domain 6D Object Pose Estimation

Chat with Graph Search

Scale-Aware Test-Time Click Adaptation for Pulmonary Nodule and Mass Segmentation

Duality and bicrystals on infinite binary matrices

Probabilistic methods for neural combinatorial optimization

espm: A Python library for the simulation of STEM-EDXS datasets

Detecting Anomalies and Obstacles in Road Scenes

Evaluation of the role of superoxide radical as chain carrier for the formation of hydroxyl radical during ozonation

Rapid Network Adaptation: Learning to Adapt Neural Networks Using Test-Time Feedback

Preserving the positivity of the deformation gradient determinant in intergrid interpolation by combining RBFs and SVD: Application to cardiac electromechanics

Rigidity-Aware Detection for 6D Object Pose Estimation

DARE: Towards Robust Text Explanations in Biomedical and Healthcare Applications

Frequency and time domains interactions in nanophotonics

BLACK-BOX ATTACKS ON IMAGE ACTIVITY PREDICTION AND ITS NATURAL LANGUAGE EXPLANATIONS

Confidence Matters: Applications to Semantic Segmentation

Neural Distributed Image Compression with Cross-Attention Feature Alignment

The JPEG AI Standard: Providing Efficient Human and Machine Visual Data Consumption

Learnable latent embeddings for joint behavioural and neural analysis

Text as a Richer Source of Supervision in Semantic Segmentation Tasks