Search Results for author:
Found 38 papers, 20 papers with code
XNet v2: Fewer Limitations, Better Results and Greater Universality
So far, however, XNet still faces the limitations, including performance degradation when images lack high-frequency (HF) information, underutilization of raw images and insufficient fusion.
Representing Topological Self-Similarity Using Fractal Feature Maps for Accurate Segmentation of Tubular Structures
A fundamental property of such structures is their topological self-similarity, which can be quantified by fractal features such as fractal dimension (FD).
Open-TeleVision: Teleoperation with Immersive Active Visual Feedback
Teleoperation serves as a powerful method for collecting on-robot data essential for robot learning from demonstrations.
Toward Efficient Deep Spiking Neuron Networks:A Survey On Compression
With the rapid development of deep learning, Deep Spiking Neural Networks (DSNNs) have emerged as promising due to their unique spike event processing and asynchronous computation.
Blaze3DM: Marry Triplane Representation with Diffusion for 3D Medical Inverse Problem Solving
Solving 3D medical inverse problems such as image restoration and reconstruction is crucial in modern medical field.
Feature Splatting: Language-Driven Physics-Based Scene Synthesis and Editing
Scene representations using 3D Gaussian primitives have produced excellent results in modeling the appearance of static and dynamic 3D scenes.
Learning Generalizable Feature Fields for Mobile Manipulation
An open problem in mobile manipulation is how to represent objects and scenes in a unified manner, so that robots can use it both for navigating in the environment and manipulating objects.
Expressive Whole-Body Control for Humanoid Robots
Can we enable humanoid robots to generate rich, diverse, and expressive motions in the real world?
Robust Source-Free Domain Adaptation for Fundus Image Segmentation
Unsupervised Domain Adaptation (UDA) is a learning technique that transfers knowledge learned in the source domain from labelled training data to the target domain with only unlabelled data.
Compositional Sculpting of Iterative Generative Processes
A key challenge in composing iterative generative processes, such as GFlowNets and diffusion models, is that to realize the desired target distribution, all steps of the generative process need to be coordinated, and satisfy delicate balance conditions.
ADFA: Attention-augmented Differentiable top-k Feature Adaptation for Unsupervised Medical Anomaly Detection
We then apply differentiable top-k feature adaptation to train the patch descriptor, mapping the extracted feature representations to a new vector space, enabling effective detection of anomalies.
Improving Generalization of Adversarial Training via Robust Critical Fine-Tuning
The core idea of RiFT is to exploit the redundant capacity for robustness by fine-tuning the adversarially trained model on its non-robust-critical module.
Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation
Self-supervised and language-supervised image models contain rich knowledge of the world that is important for generalization.
PKU-GoodsAD: A Supermarket Goods Dataset for Unsupervised Anomaly Detection and Segmentation
It follows the unsupervised setting and only normal (defect-free) images are used for training.
Neural Volumetric Memory for Visual Locomotion Control
To solve this problem, we follow the paradigm in computer vision that explicitly models the 3D geometry of the scene and propose Neural Volumetric Memory (NVM), a geometric memory architecture that explicitly accounts for the SE(3) equivariance of the 3D world.
XNet: Wavelet-Based Low and High Frequency Fusion Networks for Fully- and Semi-Supervised Semantic Segmentation of Biomedical Images
Perturbations in consistency-based semi-supervised models are often artificially designed.
Strong Lensing Source Reconstruction Using Continuous Neural Fields
From the nature of dark matter to the rate of expansion of our Universe, observations of distant galaxies distorted through strong gravitational lensing have the potential to answer some of the major open questions in astrophysics.
Overcoming the Spectral Bias of Neural Value Approximation
Value approximation using deep neural networks is at the heart of off-policy deep reinforcement learning, and is often the primary module that provides learning signals to the rest of the algorithm.
Semi-Supervised Segmentation of Mitochondria from Electron Microscopy Images Using Spatial Continuity
Fully supervised deep learning models developed for this task achieve excellent performance but require substantial amounts of annotated data for training.
Rapid Locomotion via Reinforcement Learning
Agile maneuvers such as sprinting and high-speed turning in the wild are challenging for legged robots.
Elucidating Meta-Structures of Noisy Labels in Semantic Segmentation by Deep Neural Networks
Our understanding of the learning behavior of DNNs trained by noisy segmentation labels remains limited.
Bilinear value networks
The dominant framework for off-policy multi-goal reinforcement learning involves estimating goal conditioned Q-value function.
Invariance Through Latent Alignment
A robot's deployment environment often involves perceptual changes that differ from what it has experienced during training.
Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer
Hyperparameter (HP) tuning in deep learning is an expensive process, prohibitively so for neural networks (NNs) with billions of parameters. We show that, in the recently discovered Maximal Update Parametrization ($\mu$P), many optimal HPs remain stable even as model size changes.
Understanding the Generalization Gap in Visual Reinforcement Learning
Deep Reinforcement Learning (RL) agents have achieved superhuman performance on several video game suites.
Bi-linear Value Networks for Multi-goal Reinforcement Learning
We simultaneously learn both components.
Learning Task Informed Abstractions
Current model-based reinforcement learning methods struggle when operating from complex visual scenes due to their inability to prioritize task-relevant features.
Model-based Reinforcement Learning
reinforcement-learning
+1
Advancing biological super-resolution microscopy through deep learning: a brief review
We conclude with an outlook on how deep learning could shape the future of this new generation of light microscopy technology.
Deep Neural Networks Learn Meta-Structures from Noisy Labels in Semantic Segmentation
When trained with these noisy labels, DNNs provide largely the same segmentation performance as trained by the original ground truth.
Learning Latent Landmarks for Generalizable Planning
Planning - the ability to analyze the structure of a problem in the large and decompose it into interrelated subproblems - is a hallmark of human intelligence.
World Model as a Graph: Learning Latent Landmarks for Planning
Planning - the ability to analyze the structure of a problem in the large and decompose it into interrelated subproblems - is a hallmark of human intelligence.
Few shot domain adaptation for in situ macromolecule structural classification in cryo-electron tomograms
Motivation: Cryo-Electron Tomography (cryo-ET) visualizes structure and spatial organization of macromolecules and their interactions with other subcellular components inside single cells in the close-to-native state at sub-molecular resolution.
Plan2Vec: Unsupervised Representation Learning by Latent Plans
In this paper we introduce plan2vec, an unsupervised representation learning approach that is inspired by reinforcement learning.
Probabilistic Inference for Camera Calibration in Light Microscopy under Circular Motion
Robust and accurate camera calibration is essential for 3D reconstruction in light microscopy under circular motion.
The Importance of Sampling inMeta-Reinforcement Learning
Results are presented on a new environment we call `Krazy World': a difficult high-dimensional gridworld which is designed to highlight the importance of correctly differentiating through sampling distributions in meta-reinforcement learning.
Learning Plannable Representations with Causal InfoGAN
Finally, to generate a visual plan, we project the current and goal observations onto their respective states in the planning model, plan a trajectory, and then use the generative model to transform the trajectory to a sequence of observations.
Some Considerations on Learning to Explore via Meta-Reinforcement Learning
We consider the problem of exploration in meta reinforcement learning.
Mean Field Residual Networks: On the Edge of Chaos
Classical feedforward neural networks, such as those with tanh activations, exhibit exponential behavior on the average when propagating inputs forward or gradients backward.
