Search Results for author:
Found 23 papers, 13 papers with code
Radar-Guided Polynomial Fitting for Metric Depth Estimation
We propose PolyRad, a novel radar-guided depth estimation method that introduces polynomial fitting to transform scaleless depth predictions from pretrained monocular depth estimation (MDE) models into metric depth maps.
ProtoDepth: Unsupervised Continual Depth Completion with Prototypes
To extend ProtoDepth to the challenging setting where the test-time domain identity is withheld, we propose to learn domain descriptors that enable the model to select the appropriate prototype set for inference.
TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception
Labeling LiDAR point clouds is notoriously time-and-energy-consuming, which spurs recent unsupervised 3D representation learning methods to alleviate the labeling burden in LiDAR perception via pretrained weights.
UnCLe: Unsupervised Continual Learning of Depth Completion
We find that unsupervised continual learning of depth completion is an open problem, and we invite researchers to leverage UnCLe as a development platform.
RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions
Our method, RSA, takes as input a text caption describing objects present in an image and outputs the parameters of a linear transformation which can be applied globally to a relative depth map to yield metric-scaled depth predictions.
NeuroBind: Towards Unified Multimodal Representations for Neural Signals
Understanding neural activity and information representation is crucial for advancing knowledge of brain function and cognition.
All-day Depth Completion
In poorly illuminated regions where photometric intensities do not afford the inference of local shape, the coarse approximation of scene depth serves as a prior; the uncertainty map is then used with the image to guide refinement through an uncertainty-driven residual learning (URL) scheme.
WorDepth: Variational Language Prior for Monocular Depth Estimation
To test this, we focus on monocular depth estimation, the problem of predicting a dense depth map from a single image, but with an additional text caption describing the scene.
Test-Time Adaptation for Depth Completion
During test time, sparse depth features are projected using this map as a proxy for source domain features and are used as guidance to train a set of auxiliary parameters (i. e., adaptation layer) to align image and sparse depth features from the target test domain to that of the source domain.
Binding Touch to Everything: Learning Unified Multimodal Tactile Representations
We introduce UniTouch, a unified tactile model for vision-based touch sensors connected to multiple modalities, including vision, language, and sound.
AugUndo: Scaling Up Augmentations for Monocular Depth Completion and Estimation
The sparse depth modality in depth completion have seen even less use as intensity transformations alter the scale of the 3D scene, and geometric transformations may decimate the sparse points during resampling.
Divide-and-Conquer the NAS puzzle in Resource Constrained Federated Learning Systems
In this paper, we propose DC-NAS -- a divide-and-conquer approach that performs supernet-based Neural Architecture Search (NAS) in a federated system by systematically sampling the search space.
Uncovering the Representation of Spiking Neural Networks Trained with Surrogate Gradient
However, some essential questions exist pertaining to SNNs that are little studied: Do SNNs trained with surrogate gradient learn different representations from traditional Artificial Neural Networks (ANNs)?
Exploring Temporal Information Dynamics in Spiking Neural Networks
After training, we observe that information becomes highly concentrated in earlier few timesteps, a phenomenon we refer to as temporal information concentration.
Wearable-based Human Activity Recognition with Spatio-Temporal Spiking Neural Networks
SNNs allow spatio-temporal extraction of features and enjoy low-power computation with binary spikes.
Exploring Lottery Ticket Hypothesis in Spiking Neural Networks
To scale up a pruning technique towards deep SNNs, we investigate Lottery Ticket Hypothesis (LTH) which states that dense networks contain smaller subnetworks (i. e., winning tickets) that achieve comparable performance to the dense networks.
On the Viability of Monocular Depth Pre-training for Semantic Segmentation
We choose monocular depth prediction as the geometric task, and semantic segmentation as the downstream semantic task, and design a collection of empirical tests by exploring different forms of supervision, training pipelines, and data sources for both depth pre-training and semantic fine-tuning.
Addressing Client Drift in Federated Continual Learning with Adaptive Optimization
However, there is little attention towards additional challenges emerging when federated aggregation is performed in a continual learning system.
Neuromorphic Data Augmentation for Training Spiking Neural Networks
In an effort to minimize this generalization gap, we propose Neuromorphic Data Augmentation (NDA), a family of geometric augmentations specifically designed for event-based datasets with the goal of significantly stabilizing the SNN training and reducing the generalization gap between training and test performance.
Ranked #1 on
Event data classification
on CIFAR10-DVS
(using extra training data)
Rate Coding or Direct Coding: Which One is Better for Accurate, Robust, and Energy-efficient Spiking Neural Networks?
Then, we measure the robustness of the coding techniques on two adversarial attack methods.
Neural Architecture Search for Spiking Neural Networks
Interestingly, SNASNet found by our search algorithm achieves higher performance with backward connections, demonstrating the importance of designing SNN architecture for suitably using temporal information.
Robust Federated Learning with Noisy Labels
To solve these problems, we introduce a novel federated learning scheme that the server cooperates with local models to maintain consistent decision boundaries by interchanging class-wise centroids.
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.
