Search Results for author:
Found 28 papers, 5 papers with code
HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts
In an era where the volume of data drives the effectiveness of self-supervised learning, the specificity and clarity of data semantics play a crucial role in model training.
Leveraging Temporal Contextualization for Video Action Recognition
We propose Temporal Contextualization (TC), a novel layer-wise temporal information infusion mechanism for video that extracts core information from each frame, interconnects relevant information across the video to summarize into context tokens, and ultimately leverages the context tokens during the feature encoding process.
Masked Image Modeling via Dynamic Token Morphing
Masked Image Modeling (MIM) arises as a promising option for Vision Transformers among various self-supervised learning (SSL) methods.
Learning with Unmasked Tokens Drives Stronger Vision Learners
MIMs such as Masked Autoencoder (MAE) learn strong representations by randomly masking input tokens for the encoder to process, with the decoder reconstructing the masked tokens to the input.
METAVerse: Meta-Learning Traversability Cost Map for Off-Road Navigation
To conduct a comprehensive evaluation, we collect driving data from various terrains and demonstrate that our method can obtain a global model that minimizes uncertainty.
Safe Navigation in Unstructured Environments by Minimizing Uncertainty in Control and Perception
We train a vehicle dynamics model that can quantify the epistemic uncertainty of the model to perform active exploration, resulting in the efficient collection of training data and effective avoidance of uncertain state-action spaces.
Masking Augmentation for Supervised Learning
In this paper, we propose a novel way to involve masking augmentations dubbed Masked Sub-model (MaskSub).
Bridging Active Exploration and Uncertainty-Aware Deployment Using Probabilistic Ensemble Neural Network Dynamics
Active exploration, in which a robot directs itself to states that yield the highest information gain, is essential for efficient data collection and minimizing human supervision.
What Do Self-Supervised Vision Transformers Learn?
We present a comparative study on how and why contrastive learning (CL) and masked image modeling (MIM) differ in their representations and in their performance of downstream tasks.
Learning Terrain-Aware Kinodynamic Model for Autonomous Off-Road Rally Driving With Model Predictive Path Integral Control
High-speed autonomous driving in off-road environments has immense potential for various applications, but it also presents challenges due to the complexity of vehicle-terrain interactions.
Panoramic Image-to-Image Translation
This task is difficult due to the geometric distortion of panoramic images and the lack of a panoramic image dataset with diverse conditions, like weather or time.
Robust Camera Pose Refinement for Multi-Resolution Hash Encoding
Multi-resolution hash encoding has recently been proposed to reduce the computational cost of neural renderings, such as NeRF.
Self-Supervised 3D Traversability Estimation with Proxy Bank Guidance
To mitigate the uncertainty, we introduce a deep metric learning-based method to incorporate unlabeled data with a few positive and negative prototypes in order to leverage the uncertainty, which jointly learns using semantic segmentation and traversability regression.
ScaTE: A Scalable Framework for Self-Supervised Traversability Estimation in Unstructured Environments
By integrating our framework with a model predictive controller, we demonstrate that estimated traversability results in effective navigation that enables distinct maneuvers based on the driving characteristics of the vehicles.
Physics Embedded Neural Network Vehicle Model and Applications in Risk-Aware Autonomous Driving Using Latent Features
Non-holonomic vehicle motion has been studied extensively using physics-based models.
Residual-Guided Learning Representation for Self-Supervised Monocular Depth Estimation
In this paper, we propose residual guidance loss that enables the depth estimation network to embed the discriminative feature by transferring the discriminability of auto-encoded features.
Multi-view Arbitrary Style Transfer
We propose a photometric consistency loss, which directly enforces the geometrically consistent style texture across the view, and a stroke consistency loss, which matches the characteristics and directions of the brushstrokes by aligning the local patches of the corresponding pixels before minimizing feature deviation.
Just a Few Points Are All You Need for Multi-View Stereo: A Novel Semi-Supervised Learning Method for Multi-View Stereo
We generate the spare ground truth of the DTU dataset for evaluation and extensive experiments verify that our SGT-MVSNet outperforms the state-of-the-art MVS methods on the sparse ground truth setting.
Meta Batch-Instance Normalization for Generalizable Person Re-Identification
To this end, we combine learnable batch-instance normalization layers with meta-learning and investigate the challenging cases caused by both batch and instance normalization layers.
Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation
Finally, the exploration scheme locally aligns features in a class-wise manner complementary to the attraction scheme by selectively aligning unlabeled target features complementary to the perturbation scheme.
Semi-supervised Domain Adaptation
Unsupervised Domain Adaptation
Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification
To implement our approach, we introduce an ID-preserving person image generation network and a hierarchical feature learning module.
CNN-based Semantic Segmentation using Level Set Loss
Note that each binary image consists of background and regions belonging to a class.
Learning to Align Multi-Camera Domains using Part-Aware Clustering for Unsupervised Video Person Re-Identification
Since the cost of labeling increases dramatically as the number of cameras increases, it is difficult to apply the re-identification algorithm to a large camera network.
RPM-Net: Robust Pixel-Level Matching Networks for Self-Supervised Video Object Segmentation
In this paper, we introduce a self-supervised approach for video object segmentation without human labeled data. Specifically, we present Robust Pixel-level Matching Net-works (RPM-Net), a novel deep architecture that matches pixels between adjacent frames, using only color information from unlabeled videos for training.
Self-Ensembling with GAN-based Data Augmentation for Domain Adaptation in Semantic Segmentation
Unsupervised domain adaptation seeks to adapt the model trained on the source domain to the target domain.
Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection
Experimental results show that our approach effectively improves the performance of the one-stage object detection in unsupervised domain adaptation setting.
Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation
To learn target discriminative representations, using pseudo-labels is a simple yet effective approach for unsupervised domain adaptation.
Diversify and Match: A Domain Adaptive Representation Learning Paradigm for Object Detection
We construct a structured domain adaptation framework for our learning paradigm and introduce a practical way of DD for implementation.
