Search Results for author:
Found 31 papers, 9 papers with code
Improve Unsupervised Domain Adaptation with Mixup Training
Unsupervised domain adaptation studies the problem of utilizing a relevant source domain with abundant labels to build predictive modeling for an unannotated target domain.
Ranked #49 on
Domain Generalization
on PACS
OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion
In this paper, we propose a 360 monocular depth estimation pipeline, OmniFusion, to tackle the spherical distortion issue.
Ranked #6 on
Depth Estimation
on Stanford2D3D Panoramic
Controlling the Amount of Verbatim Copying in Abstractive Summarization
In this paper, we present a neural summarization model that, by learning from single human abstracts, can produce a broad spectrum of summaries ranging from purely extractive to highly generative ones.
Ranked #12 on
Text Summarization
on GigaWord
SeaBird: Segmentation in Bird's View with Dice Loss Improves Monocular 3D Detection of Large Objects
We argue that the cause of failure is the sensitivity of depth regression losses to noise of larger objects.
3D Object Detection
3D Object Detection From Monocular Images
+3
3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection
A major challenge in monocular 3D object detection is the limited diversity and quantity of objects in real datasets.
Interpretable and Steerable Sequence Learning via Prototypes
The prediction is obtained by comparing the inputs to a few prototypes, which are exemplar cases in the problem domain.
Visualizing Classification Structure of Large-Scale Classifiers
We propose a measure to compute class similarity in large-scale classification based on prediction scores.
A streamlined Approach to Multimodal Few-Shot Class Incremental Learning for Fine-Grained Datasets
Few-shot Class-Incremental Learning (FSCIL) poses the challenge of retaining prior knowledge while learning from limited new data streams, all without overfitting.
Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection
We argue that this contextual information should already be embedded within the known classes.
Do Convolutional Neural Networks Learn Class Hierarchy?
We present visual-analytics methods to reveal and analyze this hierarchy of similar classes in relation with CNN-internal data.
Pose-Invariant Face Alignment with a Single CNN
Face alignment has witnessed substantial progress in the last decade.
Ranked #12 on
Facial Landmark Detection
on 300W
An Incremental Dimensionality Reduction Method for Visualizing Streaming Multidimensional Data
We enhance an existing incremental PCA method in several ways to ensure its usability for visualizing streaming multidimensional data.
Disentangled Representation Learning with Sequential Residual Variational Autoencoder
Recent advancements in unsupervised disentangled representation learning focus on extending the variational autoencoder (VAE) with an augmented objective function to balance the trade-off between disentanglement and reconstruction.
VATLD: A Visual Analytics System to Assess, Understand and Improve Traffic Light Detection
In this work, we propose a visual analytics system, VATLD, equipped with a disentangled representation learning and semantic adversarial learning, to assess, understand, and improve the accuracy and robustness of traffic light detectors in autonomous driving applications.
Improving the Unsupervised Disentangled Representation Learning with VAE Ensemble
We show both theoretically and experimentally, the VAE ensemble objective encourages the linear transformations connecting the VAEs to be trivial transformations, aligning the latent representations of different models to be "alike".
Unsupervised Discriminative Learning of Sounds for Audio Event Classification
Recent progress in network-based audio event classification has shown the benefit of pre-training models on visual data such as ImageNet.
Novelty-based Generalization Evaluation for Traffic Light Detection
It is on this space we estimate the novelty of the test samples.
PanoDepth: A Two-Stage Approach for Monocular Omnidirectional Depth Estimation
In this paper, we propose a novel, model-agnostic, two-stage pipeline for omnidirectional monocular depth estimation.
Ranked #13 on
Depth Estimation
on Stanford2D3D Panoramic
Interactive Visual Pattern Search on Graph Data via Graph Representation Learning
GraphQ provides a visual query interface with a query editor and a multi-scale visualization of the results, as well as a user feedback mechanism for refining the results with additional constraints.
Self-supervised Semantic Segmentation Grounded in Visual Concepts
In this work, we propose a self-supervised pixel representation learning method for semantic segmentation by using visual concepts (i. e., groups of pixels with semantic meanings, such as parts, objects, and scenes) extracted from images.
CLIP-S$^4$: Language-Guided Self-Supervised Semantic Segmentation
To further improve the pixel embeddings and enable language-driven semantic segmentation, we design two types of consistency guided by vision-language models: 1) embedding consistency, aligning our pixel embeddings to the joint feature space of a pre-trained vision-language model, CLIP; and 2) semantic consistency, forcing our model to make the same predictions as CLIP over a set of carefully designed target classes with both known and unknown prototypes.
CLIP-S4: Language-Guided Self-Supervised Semantic Segmentation
To further improve the pixel embeddings and enable language-driven semantic segmentation, we design two types of consistency guided by vision-language models: 1) embedding consistency, aligning our pixel embeddings to the joint feature space of a pre-trained vision-language model, CLIP; and 2) semantic consistency, forcing our model to make the same predictions as CLIP over a set of carefully designed target classes with both known and unknown prototypes.
Long-Distance Gesture Recognition using Dynamic Neural Networks
We demonstrate the performance of our method on the LD-ConGR long-distance dataset where it outperforms previous state-of-the-art methods on recognition accuracy and compute efficiency.
InterVLS: Interactive Model Understanding and Improvement with Vision-Language Surrogates
Deep learning models are widely used in critical applications, highlighting the need for pre-deployment model understanding and improvement.
VLP: Vision Language Planning for Autonomous Driving
Autonomous driving is a complex and challenging task that aims at safe motion planning through scene understanding and reasoning.
AttributionScanner: A Visual Analytics System for Metadata-Free Data-Slicing Based Model Validation
Data slice-finding is an emerging technique for evaluating machine learning models.
CLIP-BEVFormer: Enhancing Multi-View Image-Based BEV Detector with Ground Truth Flow
Autonomous driving stands as a pivotal domain in computer vision, shaping the future of transportation.
UPNeRF: A Unified Framework for Monocular 3D Object Reconstruction and Pose Estimation
Monocular 3D reconstruction for categorical objects heavily relies on accurately perceiving each object's pose.
LORD: Large Models based Opposite Reward Design for Autonomous Driving
Recently, large pretrained models have gained significant attention as zero-shot reward models for tasks specified with desired linguistic goals.
TCLC-GS: Tightly Coupled LiDAR-Camera Gaussian Splatting for Surrounding Autonomous Driving Scenes
Most 3D Gaussian Splatting (3D-GS) based methods for urban scenes initialize 3D Gaussians directly with 3D LiDAR points, which not only underutilizes LiDAR data capabilities but also overlooks the potential advantages of fusing LiDAR with camera data.
Behind the Veil: Enhanced Indoor 3D Scene Reconstruction with Occluded Surfaces Completion
The 3D Inpainter with abstract representation at coarse levels is trained offline using various scenes to complete occluded surfaces.
