Search Results for author:
Found 36 papers, 15 papers with code
PointPWC-Net: Cost Volume on Point Clouds for (Self-)Supervised Scene Flow Estimation
We propose a novel end-to-end deep scene flow model, called PointPWC-Net, that directly processes 3D point cloud scenes with large motions in a coarse-to-fine fashion.
Where do Large Vision-Language Models Look at when Answering Questions?
Large Vision-Language Models (LVLMs) have shown promising performance in vision-language understanding and reasoning tasks.
PointRecon: Online Point-based 3D Reconstruction via Ray-based 2D-3D Matching
Our model maintains a global point cloud representation of the scene, continuously updating the features and 3D locations of points as new images are observed.
Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats
Unlike previous feed-forward models that are limited to processing 1~4 input images and can only reconstruct a small portion of a large scene, Long-LRM reconstructs the entire scene in a single feed-forward step.
Long-Term 3D Point Tracking By Cost Volume Fusion
Long-term point tracking is essential to understand non-rigid motion in the physical world better.
CVAE-SM: A Conditional Variational Autoencoder with Style Modulation for Efficient Uncertainty Quantification
Deep learning has brought transformative advancements to object segmentation, especially in marine robotics contexts such as waste management and subaquatic infrastructure oversight.
Point Cloud Models Improve Visual Robustness in Robotic Learners
In this work, we examine robustness to a suite of these types of visual changes for RGB-D and point cloud based visual control policies.
Object Dynamics Modeling with Hierarchical Point Cloud-based Representations
Modeling object dynamics with a neural network is an important problem with numerous applications.
Taming the Tail in Class-Conditional GANs: Knowledge Sharing via Unconditional Training at Lower Resolutions
In the presence of imbalanced multi-class training data, GANs tend to favor classes with more samples, leading to the generation of low-quality and less diverse samples in tail classes.
Out of Sight, Still in Mind: Reasoning and Planning about Unobserved Objects with Video Tracking Enabled Memory Models
Robots need to have a memory of previously observed, but currently occluded objects to work reliably in realistic environments.
AutoFocusFormer: Image Segmentation off the Grid
To achieve this, we propose AutoFocusFormer (AFF), a local-attention transformer image recognition backbone, which performs adaptive downsampling by learning to retain the most important pixels for the task.
Ranked #3 on
Instance Segmentation
on Cityscapes val
Maximal Cliques on Multi-Frame Proposal Graph for Unsupervised Video Object Segmentation
On the related problem of video instance segmentation, our method shows competitive performance with the previous best algorithm that requires joint training with the VOS algorithm.
Comparing the Decision-Making Mechanisms by Transformers and CNNs via Explanation Methods
In order to gain insights about the decision-making of different visual recognition backbones, we propose two methodologies, sub-explanation counting and cross-testing, that systematically applies deep explanation algorithms on a dataset-wide basis, and compares the statistics generated from the amount and nature of the explanations.
PointConvFormer: Revenge of the Point-based Convolution
Hence, we preserved the invariances from point convolution, whereas attention helps to select relevant points in the neighborhood for convolution.
BATMAN: Bilateral Attention Transformer in Motion-Appearance Neighboring Space for Video Object Segmentation
It captures object motion in the video via a novel optical flow calibration module that fuses the segmentation mask with optical flow estimation to improve within-object optical flow smoothness and reduce noise at object boundaries.
Ranked #1 on
Video Object Segmentation
on DAVIS 2017 (test-dev)
(using extra training data)
Cycle-Consistent Counterfactuals by Latent Transformations
CounterFactual (CF) visual explanations try to find images similar to the query image that change the decision of a vision system to a specified outcome.
From Heatmaps to Structural Explanations of Image Classifiers
This paper summarizes our endeavors in the past few years in terms of explaining image classifiers, with the aim of including negative results and insights we have gained.
Deep Convolution for Irregularly Sampled Temporal Point Clouds
We consider the problem of modeling the dynamics of continuous spatial-temporal processes represented by irregular samples through both space and time.
Stochastic Block-ADMM for Training Deep Networks
We prove the convergence of our proposed method and justify its capabilities through experiments in supervised and weakly-supervised settings.
Topology-Aware Segmentation Using Discrete Morse Theory
In the segmentation of fine-scale structures from natural and biomedical images, per-pixel accuracy is not the only metric of concern.
Generative Particle Variational Inference via Estimation of Functional Gradients
Recently, particle-based variational inference (ParVI) methods have gained interest because they can avoid arbitrary parametric assumptions that are common in variational inference.
Discriminative Appearance Modeling with Multi-track Pooling for Real-time Multi-object Tracking
Many approaches model each target in isolation and lack the ability to use all the targets in the scene to jointly update the memory.
The Devils in the Point Clouds: Studying the Robustness of Point Cloud Convolutions
This paper investigates different variants of PointConv, a convolution network on point clouds, to examine their robustness to input scale and rotation changes.
One Explanation is Not Enough: Structured Attention Graphs for Image Classification
Attention maps are a popular way of explaining the decisions of convolutional networks for image classification.
Deep Variational Instance Segmentation
Specifically, we propose a variational relaxation of instance segmentation as minimizing an optimization functional for a piecewise-constant segmentation problem, which can be used to train an FCN end-to-end.
Efficient Riemannian Optimization on the Stiefel Manifold via the Cayley Transform
We specify two new optimization algorithms: Cayley SGD with momentum, and Cayley ADAM on the Stiefel manifold.
PointPWC-Net: A Coarse-to-Fine Network for Supervised and Self-Supervised Scene Flow Estimation on 3D Point Clouds
We propose a novel end-to-end deep scene flow model, called PointPWC-Net, on 3D point clouds in a coarse-to-fine fashion.
Visualizing Point Cloud Classifiers by Curvature Smoothing
In this paper, we propose a novel approach to visualize features important to the point cloud classifiers.
Implicit Generative Modeling for Efficient Exploration
Each random draw from our generative model is a neural network that instantiates the dynamic function, hence multiple draws would approximate the posterior, and the variance in the future prediction based on this posterior is used as an intrinsic reward for exploration.
Counterfactual Regularization for Model-Based Reinforcement Learning
In sequential tasks, planning-based agents have a number of advantages over model-free agents, including sample efficiency and interpretability.
Topology-Preserving Deep Image Segmentation
Segmentation algorithms are prone to make topological errors on fine-scale structures, e. g., broken connections.
Visualizing Deep Networks by Optimizing with Integrated Gradients
Understanding and interpreting the decisions made by deep learning models is valuable in many domains.
Adaptive Wing Loss for Robust Face Alignment via Heatmap Regression
Then we propose a novel loss function, named Adaptive Wing loss, that is able to adapt its shape to different types of ground truth heatmap pixels.
Ranked #8 on
Face Alignment
on WFW (Extra Data)
HyperGAN: A Generative Model for Diverse, Performant Neural Networks
We introduce HyperGAN, a new generative model for learning a distribution of neural network parameters.
PointConv: Deep Convolutional Networks on 3D Point Clouds
Besides, our experiments converting CIFAR-10 into a point cloud showed that networks built on PointConv can match the performance of convolutional networks in 2D images of a similar structure.
Ranked #2 on
3D Part Segmentation
on IntrA
Unifying Bilateral Filtering and Adversarial Training for Robust Neural Networks
To evaluate against an adversary with complete knowledge of our defense, we adapt the bilateral filter as a trainable layer in a neural network and show that adding this layer makes ImageNet images significantly more robust to attacks.
