Search Results for author:
Found 71 papers, 50 papers with code
Feature Pyramid Networks for Object Detection
Feature pyramids are a basic component in recognition systems for detecting objects at different scales.
Ranked #3 on
Pedestrian Detection
on TJU-Ped-campus
Fashionpedia: Ontology, Segmentation, and an Attribute Localization Dataset
In this work we explore the task of instance segmentation with attribute localization, which unifies instance segmentation (detect and segment each object instance) and fine-grained visual attribute categorization (recognize one or multiple attributes).
PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows
Specifically, we learn a two-level hierarchy of distributions where the first level is the distribution of shapes and the second level is the distribution of points given a shape.
Ranked #4 on
Point Cloud Generation
on ShapeNet Car
Tracking Everything Everywhere All at Once
We present a new test-time optimization method for estimating dense and long-range motion from a video sequence.
Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving
However, in this paper we argue that it is not the quality of the data but its representation that accounts for the majority of the difference.
3D Object Detection From Stereo Images
Autonomous Driving
+2
Visual Prompt Tuning
The current modus operandi in adapting pre-trained models involves updating all the backbone parameters, ie, full fine-tuning.
Ranked #2 on
Prompt Engineering
on ImageNet-21k
Inferring and Executing Programs for Visual Reasoning
Existing methods for visual reasoning attempt to directly map inputs to outputs using black-box architectures without explicitly modeling the underlying reasoning processes.
Ranked #5 on
Visual Question Answering (VQA)
on CLEVR-Humans
Unsupervised Semantic Segmentation by Distilling Feature Correspondences
Unsupervised semantic segmentation aims to discover and localize semantically meaningful categories within image corpora without any form of annotation.
Ranked #4 on
Unsupervised Semantic Segmentation
on Potsdam-3
Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving
In this paper we provide substantial advances to the pseudo-LiDAR framework through improvements in stereo depth estimation.
3D Object Detection From Stereo Images
Autonomous Driving
+2
Emergent Correspondence from Image Diffusion
We propose a simple strategy to extract this implicit knowledge out of diffusion networks as image features, namely DIffusion FeaTures (DIFT), and use them to establish correspondences between real images.
Low-shot Visual Recognition by Shrinking and Hallucinating Features
Low-shot visual learning---the ability to recognize novel object categories from very few examples---is a hallmark of human visual intelligence.
CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
When building artificial intelligence systems that can reason and answer questions about visual data, we need diagnostic tests to analyze our progress and discover shortcomings.
Learning Features by Watching Objects Move
Given the extensive evidence that motion plays a key role in the development of the human visual system, we hope that this straightforward approach to unsupervised learning will be more effective than cleverly designed 'pretext' tasks studied in the literature.
PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering
With our novel learning objective, our framework can learn high-level semantic concepts.
Ranked #3 on
Unsupervised Semantic Segmentation
on COCO-Stuff-171
End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection
Reliable and accurate 3D object detection is a necessity for safe autonomous driving.
Geometry Processing with Neural Fields
Most existing geometry processing algorithms use meshes as the default shape representation.
Learning Gradient Fields for Shape Generation
Point cloud generation thus amounts to moving randomly sampled points to high-density areas.
Learning Feature Descriptors using Camera Pose Supervision
Recent research on learned visual descriptors has shown promising improvements in correspondence estimation, a key component of many 3D vision tasks.
Hypercolumns for Object Segmentation and Fine-grained Localization
Recognition algorithms based on convolutional networks (CNNs) typically use the output of the last layer as feature representation.
Doppelgangers: Learning to Disambiguate Images of Similar Structures
Our evaluation shows that our method can distinguish illusory matches in difficult cases, and can be integrated into SfM pipelines to produce correct, disambiguated 3D reconstructions.
Better Monocular 3D Detectors with LiDAR from the Past
Accurate 3D object detection is crucial to autonomous driving.
DeepBox: Learning Objectness with Convolutional Networks
Existing object proposal approaches use primarily bottom-up cues to rank proposals, while we believe that objectness is in fact a high level construct.
Train in Germany, Test in The USA: Making 3D Object Detectors Generalize
In the domain of autonomous driving, deep learning has substantially improved the 3D object detection accuracy for LiDAR and stereo camera data alike.
Wasserstein Distances for Stereo Disparity Estimation
Existing approaches to depth or disparity estimation output a distribution over a set of pre-defined discrete values.
Ranked #2 on
Stereo Depth Estimation
on KITTI2015
(three pixel error metric)
3D Object Detection From Stereo Images
Autonomous Driving
+5
Few-Shot Classification with Feature Map Reconstruction Networks
In this paper we reformulate few-shot classification as a reconstruction problem in latent space.
Learning to Detect Mobile Objects from LiDAR Scans Without Labels
Current 3D object detectors for autonomous driving are almost entirely trained on human-annotated data.
Low-Shot Learning from Imaginary Data
Humans can quickly learn new visual concepts, perhaps because they can easily visualize or imagine what novel objects look like from different views.
Resource Aware Person Re-identification across Multiple Resolutions
Not all people are equally easy to identify: color statistics might be enough for some cases while others might require careful reasoning about high- and low-level details.
Ranked #12 on
Person Re-Identification
on CUHK03 detected
Learning Single-View 3D Reconstruction with Limited Pose Supervision
It is expensive to label images with 3D structure or precise camera pose.
LDLS: 3-D Object Segmentation Through Label Diffusion From 2-D Images
We obtain 2-D segmentation predictions by applying Mask-RCNN to the RGB image, and then link this image to a 3-D lidar point cloud by building a graph of connections among 3-D points and 2-D pixels.
Polynomial Neural Fields for Subband Decomposition and Manipulation
We use this framework to design Fourier PNFs, which match state-of-the-art performance in signal representation tasks that use neural fields.
Low-shot learning with large-scale diffusion
This paper considers the problem of inferring image labels from images when only a few annotated examples are available at training time.
Few-Shot Learning with Localization in Realistic Settings
Traditional recognition methods typically require large, artificially-balanced training classes, while few-shot learning methods are tested on artificially small ones.
Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognition
Few-shot, fine-grained classification requires a model to learn subtle, fine-grained distinctions between different classes (e. g., birds) based on a few images alone.
Extreme Rotation Estimation using Dense Correlation Volumes
We present a technique for estimating the relative 3D rotation of an RGB image pair in an extreme setting, where the images have little or no overlap.
Self-training for Few-shot Transfer Across Extreme Task Differences
Most few-shot learning techniques are pre-trained on a large, labeled "base dataset".
Hindsight is 20/20: Leveraging Past Traversals to Aid 3D Perception
Self-driving cars must detect vehicles, pedestrians, and other traffic participants accurately to operate safely.
When Does Self-supervision Improve Few-shot Learning?
We investigate the role of self-supervised learning (SSL) in the context of few-shot learning.
Stay Positive: Non-Negative Image Synthesis for Augmented Reality
In applications such as optical see-through and projector augmented reality, producing images amounts to solving non-negative image generation, where one can only add light to an existing image.
GeoStyle: Discovering Fashion Trends and Events
Understanding fashion styles and trends is of great potential interest to retailers and consumers alike.
Accurate Differential Operators for Hybrid Neural Fields
Yet in many applications like rendering and simulation, hybrid neural fields can cause noticeable and unreasonable artifacts.
Can We Characterize Tasks Without Labels or Features?
The problem of expert model selection deals with choosing the appropriate pretrained network ("expert") to transfer to a target task.
Extending and Analyzing Self-Supervised Learning Across Domains
There has been little to no work with these methods on other smaller domains, such as satellite, textural, or biological imagery.
Unsupervised Adaptation from Repeated Traversals for Autonomous Driving
For a self-driving car to operate reliably, its perceptual system must generalize to the end-user's environment -- ideally without additional annotation efforts.
Coarsely-Labeled Data for Better Few-Shot Transfer
Few-shot learning is based on the premise that labels are expensive, especially when they are fine-grained and require expertise.
Field-Guide-Inspired Zero-Shot Learning
Annotating the full set of attributes for a novel category proves to be a tedious and expensive task in deployment.
Distilling from Similar Tasks for Transfer Learning on a Budget
To alleviate this, we propose a weighted multi-source distillation method to distill multiple source models trained on different domains weighted by their relevance for the target task into a single efficient model (named DistillWeighted).
Pre-Training LiDAR-Based 3D Object Detectors Through Colorization
Accurate 3D object detection and understanding for self-driving cars heavily relies on LiDAR point clouds, necessitating large amounts of labeled data to train.
Iterative Instance Segmentation
Existing methods for pixel-wise labelling tasks generally disregard the underlying structure of labellings, often leading to predictions that are visually implausible.
Exploring Person Context and Local Scene Context for Object Detection
In this paper we explore two ways of using context for object detection.
Simultaneous Detection and Segmentation
Unlike classical semantic segmentation, we require individual object instances.
Ranked #5 on
Object Detection
on PASCAL VOC 2012
R-CNNs for Pose Estimation and Action Detection
We present convolutional neural networks for the tasks of keypoint (pose) prediction and action classification of people in unconstrained images.
Deep Fundamental Matrix Estimation without Correspondences
Estimating fundamental matrices is a classic problem in computer vision.
A Deep-Learning-Based Fashion Attributes Detection Model
Such information analyzing process is called abstracting, which recognize similarities or differences across all the garments and collections.
Detecting Objects using Deformation Dictionaries
Several popular and effective object detectors separately model intra-class variations arising from deformations and appearance changes.
Using k-Poselets for Detecting People and Localizing Their Keypoints
A k-poselet is a deformable part model (DPM) with k parts, where each of the parts is a poselet, aligned to a specific configuration of keypoints based on ground-truth annotations.
Boosting Supervision with Self-Supervision for Few-shot Learning
We present a technique to improve the transferability of deep representations learned on small labeled datasets by introducing self-supervised tasks as auxiliary loss functions.
Few-Shot Generalization for Single-Image 3D Reconstruction via Priors
To address this problem, we present a new model architecture that reframes single-view 3D reconstruction as learnt, category agnostic refinement of a provided, category-specific prior.
On the Efficacy of Knowledge Distillation
In this paper, we present a thorough evaluation of the efficacy of knowledge distillation and its dependence on student and teacher architectures.
Augmentation-Interpolative AutoEncoders for Unsupervised Few-Shot Image Generation
We aim to build image generation models that generalize to new domains from few examples.
Exploiting Playbacks in Unsupervised Domain Adaptation for 3D Object Detection
Self-driving cars must detect other vehicles and pedestrians in 3D to plan safe routes and avoid collisions.
A theoretically grounded characterization of feature representations
We present theoretical results showing how these measurements can be used to bound the error of the downstream classifiers, and show empirically that these bounds correlate well with actual downstream performance.
Orientation-Discriminative Feature Representation for Decentralized Pedestrian Tracking
This paper focuses on the problem of decentralized pedestrian tracking using a sensor network.
Activation Regression for Continuous Domain Generalization with Applications to Crop Classification
Geographic variance in satellite imagery impacts the ability of machine learning models to generalise to new regions.
Diagnosing and Remedying Shot Sensitivity with Cosine Few-Shot Learners
Existing approaches generally assume that the shot number at test time is known in advance.
Ithaca365: Dataset and Driving Perception under Repeated and Challenging Weather Conditions
Advances in perception for self-driving cars have accelerated in recent years due to the availability of large-scale datasets, typically collected at specific locations and under nice weather conditions.
Image-to-Image Translation for Autonomous Driving from Coarsely-Aligned Image Pairs
In this paper, we investigate the idea of turning sensor inputs (i. e., images) captured in an adverse condition into a benign one (i. e., sunny), upon which the downstream tasks (e. g., semantic segmentation) can attain high accuracy.
Change-Aware Sampling and Contrastive Learning for Satellite Images
While a vast amount of spatio-temporal satellite image data is readily available, most of it remains unlabelled.
Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features
Additionally, we leverage the statistics for a novel self-training process to stabilize the training.
RealFill: Reference-Driven Generation for Authentic Image Completion
Once personalized, RealFill is able to complete a target image with visually compelling contents that are faithful to the original scene.
Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment
We introduce a method to train vision-language models for remote-sensing images without using any textual annotations.
