Search Results for author:
Found 22 papers, 1 papers with code
NaturalVLM: Leveraging Fine-grained Natural Language for Affordance-Guided Visual Manipulation
To address these challenges, we introduce a comprehensive benchmark, NrVLM, comprising 15 distinct manipulation tasks, containing over 4500 episodes meticulously annotated with fine-grained language instructions.
Continual Domain Adversarial Adaptation via Double-Head Discriminators
We prove that with the introduction of a pre-trained source-only domain discriminator, the empirical estimation error of $\gH$-divergence related adversarial loss is reduced from the source domain side.
ManipLLM: Embodied Multimodal Large Language Model for Object-Centric Robotic Manipulation
By fine-tuning the injected adapters, we preserve the inherent common sense and reasoning ability of the MLLMs while equipping them with the ability for manipulation.
Learning Part Motion of Articulated Objects Using Spatially Continuous Neural Implicit Representations
More importantly, while many methods could only model a certain kind of joint motion (such as the revolution in the clockwise order), our proposed framework is generic to different kinds of joint motions in that transformation matrix can model diverse kinds of joint motions in the space.
LightSAGE: Graph Neural Networks for Large Scale Item Retrieval in Shopee's Advertisement Recommendation
Graph Neural Network (GNN) is the trending solution for item retrieval in recommendation problems.
ImageManip: Image-based Robotic Manipulation with Affordance-guided Next View Selection
This framework is designed to capture multiple perspectives of the target object and infer depth information to complement its geometry.
CLIP-Lung: Textual Knowledge-Guided Lung Nodule Malignancy Prediction
Drawing on the capability of the contrastive language-image pre-training (CLIP) model to learn generalized visual representations from text annotations, in this paper, we propose CLIP-Lung, a textual knowledge-guided framework for lung nodule malignancy prediction.
LSDM: Long-Short Diffeomorphic Motion for Weakly-Supervised Ultrasound Landmark Tracking
In this paper, we propose a long-short diffeomorphic motion network, which is a multi-task framework with a learnable deformation prior to search for the plausible deformation of landmark.
Progressive Voronoi Diagram Subdivision: Towards A Holistic Geometric Framework for Exemplar-free Class-Incremental Learning
Exemplar-free Class-incremental Learning (CIL) is a challenging problem because rehearsing data from previous phases is strictly prohibited, causing catastrophic forgetting of Deep Neural Networks (DNNs).
A Bayesian Detect to Track System for Robust Visual Object Tracking and Semi-Supervised Model Learning
Based on our particle filter inference algorithm, a semi-supervised learn-ing algorithm is utilized for learning tracking network on intermittent labeled frames by variational inference.
Learning Individual Interactions from Population Dynamics with Discrete-Event Simulation Model
Traditional machine learning approaches capture complex system dynamics either with dynamic Bayesian networks and state space models, which is hard to scale because it is non-trivial to prescribe the dynamics with a sparse graph or a system of differential equations; or a deep neural networks, where the distributed representation of the learned dynamics is hard to interpret.
Confidence Intervals of Treatment Effects in Panel Data Models with Interactive Fixed Effects
We consider the construction of confidence intervals for treatment effects estimated using panel models with interactive fixed effects.
FedMM: Saddle Point Optimization for Federated Adversarial Domain Adaptation
Federated adversary domain adaptation is a unique distributed minimax training task due to the prevalence of label imbalance among clients, with each client only seeing a subset of the classes of labels required to train a global model.
LAViTeR: Learning Aligned Visual and Textual Representations Assisted by Image and Caption Generation
Pre-training visual and textual representations from large-scale image-text pairs is becoming a standard approach for many downstream vision-language tasks.
An End-to-End learnable Flow Regularized Model for Brain Tumor Segmentation
Many segmentation tasks for biomedical images can be modeled as the minimization of an energy function and solved by a class of max-flow and min-cut optimization algorithms.
Multi-Scale Feature Pyramid Network: A Heavily Occluded Pedestrian Detection Network Based on ResNet
MFPN includes two modules, namely double feature pyramid network (FPN) integrated with ResNet (DFR) and repulsion loss of minimum (RLM).
Strongly Connected Topology Model and Confirmation-based Propagation Method for Cross-chain Interaction
Meanwhile, different from legacy networks, the propagation method is required to keep the data validity.
Distributed, Parallel, and Cluster Computing
A Stochastic Gradient Langevin Dynamics Algorithm For Noise Intrinsic Federated Learning
Our introduced SGLD oracle would lower generalization errors in local node's parameter learning and provide local node DP protections.
Scribble-based Hierarchical Weakly Supervised Learning for Brain Tumor Segmentation
In this paper, we use only two kinds of weak labels, i. e., scribbles on whole tumor and healthy brain tissue, and global labels for the presence of each substructure, to train a deep learning model to segment all the sub-regions.
A closer look at network resolution for efficient network design
We propose a framework to mutually learn from different input resolutions and network widths.
Brain Tumor Segmentation on MRI with Missing Modalities
We design a brain tumor segmentation algorithm that is robust to the absence of any modality.
Dynamic Routing on Deep Neural Network for Thoracic Disease Classification and Sensitive Area Localization
We present and evaluate a new deep neural network architecture for automatic thoracic disease detection on chest X-rays.
