Search Results for author:
Found 41 papers, 28 papers with code
ATT3D: Amortized Text-to-3D Object Synthesis
Text-to-3D modelling has seen exciting progress by combining generative text-to-image models with image-to-3D methods like Neural Radiance Fields.
Motion-Conditioned Diffusion Model for Controllable Video Synthesis
In response to this gap, we introduce MCDiff, a conditional diffusion model that generates a video from a starting image frame and a set of strokes, which allow users to specify the intended content and dynamics for synthesis.
Magic3D: High-Resolution Text-to-3D Content Creation
DreamFusion has recently demonstrated the utility of a pre-trained text-to-image diffusion model to optimize Neural Radiance Fields (NeRF), achieving remarkable text-to-3D synthesis results.
Optimizing Anchor-based Detectors for Autonomous Driving Scenes
This paper summarizes model improvements and inference-time optimizations for the popular anchor-based detectors in the scenes of autonomous driving.
Vision Transformer for NeRF-Based View Synthesis from a Single Input Image
Existing approaches condition on local image features to reconstruct a 3D object, but often render blurry predictions at viewpoints that are far away from the source view.
A Unified Sequence Interface for Vision Tasks
Despite that, by formulating the output of each task as a sequence of discrete tokens with a unified interface, we show that one can train a neural network with a single model architecture and loss function on all these tasks, with no task-specific customization.
NeRF-Supervision: Learning Dense Object Descriptors from Neural Radiance Fields
In particular, we demonstrate that a NeRF representation of a scene can be used to train dense object descriptors.
Scaling Open-Vocabulary Image Segmentation with Image-Level Labels
We propose OpenSeg to address the above issue while still making use of scalable image-level supervision of captions.
A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation
In this paper, we comprehensively study three architecture design choices on ViT -- spatial reduction, doubled channels, and multiscale features -- and demonstrate that a vanilla ViT architecture can fulfill this goal without handcrafting multiscale features, maintaining the original ViT design philosophy.
Multi-Task Self-Training for Learning General Representations
The results suggest self-training is a promising direction to aggregate labeled and unlabeled training data for learning general feature representations.
Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval from a Single Image
3D perception of object shapes from RGB image input is fundamental towards semantic scene understanding, grounding image-based perception in our spatially 3-dimensional real-world environments.
Learning Open-World Object Proposals without Learning to Classify
In this paper, we identify that the problem is that the binary classifiers in existing proposal methods tend to overfit to the training categories.
Ranked #2 on
Open World Object Detection
on COCO VOC to non-VOC
Learning to See before Learning to Act: Visual Pre-training for Manipulation
With just a small amount of robotic experience, we can further fine-tune the affordance model to achieve better results.
Simple Training Strategies and Model Scaling for Object Detection
We benchmark these improvements on the vanilla ResNet-FPN backbone with RetinaNet and RCNN detectors.
Ranked #53 on
Object Detection
on COCO minival
SITTA: Single Image Texture Translation for Data Augmentation
In this paper, we propose and explore the problem of image translation for data augmentation.
Open-vocabulary Object Detection via Vision and Language Knowledge Distillation
On COCO, ViLD outperforms the previous state-of-the-art by 4. 8 on novel AP and 11. 4 on overall AP.
Ranked #2 on
Open Vocabulary Object Detection
on Objects365
Revisiting ResNets: Improved Training and Scaling Strategies
Using improved training and scaling strategies, we design a family of ResNet architectures, ResNet-RS, which are 1. 7x - 2. 7x faster than EfficientNets on TPUs, while achieving similar accuracies on ImageNet.
Ranked #1 on
Document Image Classification
on AIP
Bottleneck Transformers for Visual Recognition
Finally, we present a simple adaptation of the BoTNet design for image classification, resulting in models that achieve a strong performance of 84. 7% top-1 accuracy on the ImageNet benchmark while being up to 1. 64x faster in compute time than the popular EfficientNet models on TPU-v3 hardware.
Ranked #50 on
Instance Segmentation
on COCO minival
Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation
Our baseline model outperforms the LVIS 2020 Challenge winning entry by +3. 6 mask AP on rare categories.
Ranked #1 on
Object Detection
on PASCAL VOC 2007
(using extra training data)
INeRF: Inverting Neural Radiance Fields for Pose Estimation
We then show that for complex real-world scenes from the LLFF dataset, iNeRF can improve NeRF by estimating the camera poses of novel images and using these images as additional training data for NeRF.
Efficient Scale-Permuted Backbone with Learned Resource Distribution
Furthermore, SpineNet is built with a uniform resource distribution over operations.
SoDA: Multi-Object Tracking with Soft Data Association
Robust multi-object tracking (MOT) is a prerequisite fora safe deployment of self-driving cars.
Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve
We propose to leverage existing large-scale datasets of 3D models to understand the underlying 3D structure of objects seen in an image by constructing a CAD-based representation of the objects and their poses.
Rethinking Pre-training and Self-training
For example, on the COCO object detection dataset, pre-training benefits when we use one fifth of the labeled data, and hurts accuracy when we use all labeled data.
Ranked #1 on
Semantic Segmentation
on PASCAL VOC 2012 val
Improving Semantic Segmentation through Spatio-Temporal Consistency Learned from Videos
We leverage unsupervised learning of depth, egomotion, and camera intrinsics to improve the performance of single-image semantic segmentation, by enforcing 3D-geometric and temporal consistency of segmentation masks across video frames.
SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
We propose SpineNet, a backbone with scale-permuted intermediate features and cross-scale connections that is learned on an object detection task by Neural Architecture Search.
Ranked #9 on
Image Classification
on iNaturalist
MnasFPN: Learning Latency-aware Pyramid Architecture for Object Detection on Mobile Devices
We propose MnasFPN, a mobile-friendly search space for the detection head, and combine it with latency-aware architecture search to produce efficient object detection models.
Ranked #234 on
Object Detection
on COCO test-dev
Learning Data Augmentation Strategies for Object Detection
Importantly, the best policy found on COCO may be transferred unchanged to other detection datasets and models to improve predictive accuracy.
Ranked #83 on
Object Detection
on COCO test-dev
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection
Here we aim to learn a better architecture of feature pyramid network for object detection.
ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors
However, it is difficult and costly to segment objects in novel categories because a large number of mask annotations is required.
Class-Balanced Loss Based on Effective Number of Samples
We design a re-weighting scheme that uses the effective number of samples for each class to re-balance the loss, thereby yielding a class-balanced loss.
Ranked #2 on
Long-tail Learning
on EGTEA
DropBlock: A regularization method for convolutional networks
This lack of success of dropout for convolutional layers is perhaps due to the fact that activation units in convolutional layers are spatially correlated so information can still flow through convolutional networks despite dropout.
Ranked #729 on
Image Classification
on ImageNet
Focal Loss for Dense Object Detection
Our novel Focal Loss focuses training on a sparse set of hard examples and prevents the vast number of easy negatives from overwhelming the detector during training.
Ranked #3 on
Long-tail Learning
on EGTEA
Collaborative Metric Learning
Metric learning algorithms produce distance metrics that capture the important relationships among data.
Ranked #1 on
Recommendation Systems
on MovieLens 20M
(Recall@100 metric)
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-traffic
A MultiPath Network for Object Detection
To address these challenges, we test three modifications to the standard Fast R-CNN object detector: (1) skip connections that give the detector access to features at multiple network layers, (2) a foveal structure to exploit object context at multiple object resolutions, and (3) an integral loss function and corresponding network adjustment that improve localization.
Ranked #102 on
Instance Segmentation
on COCO test-dev
Learning to Refine Object Segments
In this work we propose to augment feedforward nets for object segmentation with a novel top-down refinement approach.
Ranked #4 on
Region Proposal
on COCO test-dev
Learning Deep Representations for Ground-to-Aerial Geolocalization
Most approaches predict the location of a query image by matching to ground-level images with known locations (e. g., street-view data).
Microsoft COCO Captions: Data Collection and Evaluation Server
In this paper we describe the Microsoft COCO Caption dataset and evaluation server.
Microsoft COCO: Common Objects in Context
We present a new dataset with the goal of advancing the state-of-the-art in object recognition by placing the question of object recognition in the context of the broader question of scene understanding.
Cross-View Image Geolocalization
On the other hand, there is no shortage of visual and geographic data that densely covers the Earth we examine overhead imagery and land cover survey data but the relationship between this data and ground level query photographs is complex.
