Search Results for author:
Found 96 papers, 66 papers with code
Efficient Video Object Segmentation via Modulated Cross-Attention Memory
Recently, transformer-based approaches have shown promising results for semi-supervised video object segmentation.
Analyzing Local Representations of Self-supervised Vision Transformers
In this paper, we present a comparative analysis of various self-supervised Vision Transformers (ViTs), focusing on their local representative power.
Diffusion-Based Particle-DETR for BEV Perception
For the enhanced safety of AVs, modeling perception uncertainty in BEV is crucial.
Gaussian Grouping: Segment and Edit Anything in 3D Scenes
To address this issue, we propose Gaussian Grouping, which extends Gaussian Splatting to jointly reconstruct and segment anything in open-world 3D scenes.
Probabilistic Sampling of Balanced K-Means using Adiabatic Quantum Computing
Adiabatic quantum computing (AQC) is a promising quantum computing approach for discrete and often NP-hard optimization problems.
R3D3: Dense 3D Reconstruction of Dynamic Scenes from Multiple Cameras
We propose R3D3, a multi-camera system for dense 3D reconstruction and ego-motion estimation.
MolGrapher: Graph-based Visual Recognition of Chemical Structures
In addition, we introduce a large-scale benchmark of annotated real molecule images, USPTO-30K, to spur research on this critical topic.
Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects
On the prey side, we propose an adversarial training framework, Camouflageator, which introduces an auxiliary generator to generate more camouflaged objects that are harder for a COD method to detect.
Cascade-DETR: Delving into High-Quality Universal Object Detection
While dominating on the COCO benchmark, recent Transformer-based detection methods are not competitive in diverse domains.
Prompting Diffusion Representations for Cross-Domain Semantic Segmentation
Intrigued by this result, we set out to explore how well diffusion-pretrained representations generalize to new domains, a crucial ability for any representation.
Segment Anything Meets Point Tracking
The Segment Anything Model (SAM) has established itself as a powerful zero-shot image segmentation model, enabled by efficient point-centric annotation and prompt-based models.
Segment Anything in High Quality
HQ-SAM is only trained on the introduced detaset of 44k masks, which takes only 4 hours on 8 GPUs.
Ranked #1 on
Zero-Shot Instance Segmentation
on LVIS v1.0 val
StyleGenes: Discrete and Efficient Latent Distributions for GANs
Thus, by independently sampling a variant for each gene and combining them into the final latent vector, our approach can represent a vast number of unique latent samples from a compact set of learnable parameters.
OVTrack: Open-Vocabulary Multiple Object Tracking
This leaves contemporary MOT methods limited to a small set of pre-defined object categories.
Mask-Free Video Instance Segmentation
A consistency loss is then enforced on the found matches.
NeRF-GAN Distillation for Efficient 3D-Aware Generation with Convolutions
Pose-conditioned convolutional generative models struggle with high-quality 3D-consistent image generation from single-view datasets, due to their lack of sufficient 3D priors.
How Reliable is Your Regression Model's Uncertainty Under Real-World Distribution Shifts?
We then employ our benchmark to evaluate many of the most common uncertainty estimation methods, as well as two state-of-the-art uncertainty scores from the task of out-of-distribution detection.
Continuous Pseudo-Label Rectified Domain Adaptive Semantic Segmentation With Implicit Neural Representations
Unsupervised domain adaptation (UDA) for semantic segmentation aims at improving the model performance on the unlabeled target domain by leveraging a labeled source domain.
Fast Hierarchical Learning for Few-Shot Object Detection
These approaches however suffer from ``catastrophic forgetting'' issue due to finetuning of base detector, leading to sub-optimal performance on the base classes.
ManiFlow: Implicitly Representing Manifolds with Normalizing Flows
In contrast to prior work, we approach this problem by generating samples from the original data distribution given full knowledge about the perturbed distribution and the noise model.
AVisT: A Benchmark for Visual Object Tracking in Adverse Visibility
While being greatly benefiting to the tracking research, existing benchmarks do not pose the same difficulty as before with recent trackers achieving higher performance mainly due to (i) the introduction of more sophisticated transformers-based methods and (ii) the lack of diverse scenarios with adverse visibility such as, severe weather conditions, camouflage and imaging effects.
Video Mask Transfiner for High-Quality Video Instance Segmentation
While Video Instance Segmentation (VIS) has seen rapid progress, current approaches struggle to predict high-quality masks with accurate boundary details.
Ranked #1 on
Video Instance Segmentation
on HQ-YTVIS
Tracking Every Thing in the Wild
Our experiments show that TETA evaluates trackers more comprehensively, and TETer achieves significant improvements on the challenging large-scale datasets BDD100K and TAO compared to the state-of-the-art.
Ranked #4 on
Multi-Object Tracking
on TAO
Arbitrary-Scale Image Synthesis
Positional encodings have enabled recent works to train a single adversarial network that can generate images of different scales.
Robust Visual Tracking by Segmentation
We infer a bounding box from the segmentation mask, validate our tracker on challenging tracking datasets and achieve the new state of the art on LaSOT with a success AUC score of 69. 7%.
Transforming Model Prediction for Tracking
Optimization based tracking methods have been widely successful by integrating a target model prediction module, providing effective global reasoning by minimizing an objective function.
Ranked #20 on
Visual Object Tracking
on LaSOT
(Precision metric)
Transform your Smartphone into a DSLR Camera: Learning the ISP in the Wild
We propose a trainable Image Signal Processing (ISP) framework that produces DSLR quality images given RAW images captured by a smartphone.
Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences
We propose Probabilistic Warp Consistency, a weakly-supervised learning objective for semantic matching.
Adiabatic Quantum Computing for Multi Object Tracking
Multi-Object Tracking (MOT) is most often approached in the tracking-by-detection paradigm, where object detections are associated through time.
Fast Online Video Super-Resolution with Deformable Attention Pyramid
Our DAP aligns and integrates information from the recurrent state into the current frame prediction.
RePaint: Inpainting using Denoising Diffusion Probabilistic Models
In this work, we propose RePaint: A Denoising Diffusion Probabilistic Model (DDPM) based inpainting approach that is applicable to even extreme masks.
Collapse by Conditioning: Training Class-conditional GANs with Limited Data
On the contrary, we observe that class-conditioning causes mode collapse in limited data settings, where unconditional learning leads to satisfactory generative ability.
Efficient Visual Tracking with Exemplar Transformers
E. T. Track, our visual tracker that incorporates Exemplar Transformer modules, runs at 47 FPS on a CPU.
Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook
Accurate and robust visual object tracking is one of the most challenging and fundamental computer vision problems.
Mask Transfiner for High-Quality Instance Segmentation
Instead of operating on regular dense tensors, our Mask Transfiner decomposes and represents the image regions as a quadtree.
Ranked #1 on
Instance Segmentation
on BDD100K val
Normalizing Flow as a Flexible Fidelity Objective for Photo-Realistic Super-resolution
Super-resolution is an ill-posed problem, where a ground-truth high-resolution image represents only one possibility in the space of plausible solutions.
Learning Proposals for Practical Energy-Based Regression
Energy-based models (EBMs) have experienced a resurgence within machine learning in recent years, including as a promising alternative for probabilistic regression.
Dense Gaussian Processes for Few-Shot Segmentation
Given the support set, our dense GP learns the mapping from local deep image features to mask values, capable of capturing complex appearance distributions.
Ranked #1 on
Few-Shot Semantic Segmentation
on COCO-20i (10-shot)
PDC-Net+: Enhanced Probabilistic Dense Correspondence Network
In order to apply dense methods to real-world applications, such as pose estimation, image manipulation, or 3D reconstruction, it is therefore crucial to estimate the confidence of the predicted matches.
TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentation
In many real-world settings, the target domain task requires a different taxonomy than the one imposed by the source domain.
Deep Reparametrization of Multi-Frame Super-Resolution and Denoising
The deep reparametrization allows us to directly model the image formation process in the latent space, and to integrate learned image priors into the prediction.
Ranked #4 on
Burst Image Super-Resolution
on BurstSR
Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling
More specifically, HCFlow learns a bijective mapping between HR and LR image pairs by modelling the distribution of the LR image and the rest high-frequency component simultaneously.
Prototypical Cross-Attention Networks for Multiple Object Tracking and Segmentation
We propose Prototypical Cross-Attention Network (PCAN), capable of leveraging rich spatio-temporal information for online multiple object tracking and segmentation.
Ranked #1 on
Video Instance Segmentation
on BDD100K val
Multi-Object Tracking and Segmentation
Multiple Object Track and Segmentation
+3
NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results
This paper reviews the NTIRE2021 challenge on burst super-resolution.
Learnable Online Graph Representations for 3D Multi-Object Tracking
Tracking of objects in 3D is a fundamental task in computer vision that finds use in a wide range of applications such as autonomous driving, robotics or augmented reality.
Warp Consistency for Unsupervised Learning of Dense Correspondences
From our observations and empirical results, we design a general unsupervised objective employing two of the derived constraints.
Deep Gaussian Processes for Few-Shot Segmentation
Through the expressivity of the GP, our approach is capable of modeling complex appearance distributions in the deep feature space.
Learning Target Candidate Association to Keep Track of What Not to Track
To tackle the problem of lacking ground-truth correspondences between distractor objects in visual tracking, we propose a training strategy that combines partial annotations with self-supervision.
Ranked #4 on
Visual Object Tracking
on OTB-2015
Deep Burst Super-Resolution
We propose a novel architecture for the burst super-resolution task.
Ranked #6 on
Burst Image Super-Resolution
on SyntheticBurst
Burst Image Super-Resolution
Multi-Frame Super-Resolution
+1
DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows
We propose DeFlow, a method for learning stochastic image degradations from unpaired data.
Generating Masks from Boxes by Mining Spatio-Temporal Consistencies in Videos
This effectively limits the performance and generalization capabilities of existing video segmentation methods.
Local Memory Attention for Fast Video Semantic Segmentation
Our approach aggregates a rich representation of the semantic information in past frames into a memory module.
Learning Accurate Dense Correspondences and When to Trust Them
Establishing dense correspondences between a pair of images is an important and general problem.
Scaling Semantic Segmentation Beyond 1K Classes on a Single GPU
In this paper, we propose a novel training methodology to train and scale the existing semantic segmentation models for a large number of semantic classes without increasing the memory overhead.
Accurate 3D Object Detection using Energy-Based Models
On the KITTI dataset, our proposed approach consistently outperforms the SA-SSD baseline across all 3DOD metrics, demonstrating the potential of EBM-based regression for highly accurate 3DOD.
Ranked #1 on
3D Object Detection
on KITTI Cars Easy val
Learning Video Instance Segmentation with Recurrent Graph Neural Networks
Most existing approaches to video instance segmentation comprise multiple modules that are heuristically combined to produce the final output.
Fast Few-Shot Classification by Few-Iteration Meta-Learning
By employing an efficient initialization module and a Steepest Descent based optimization algorithm, our base learner predicts a powerful classifier within only a few iterations.
GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network
We propose GOCor, a fully differentiable dense matching module, acting as a direct replacement to the feature correlation layer.
Dense Pixel Correspondence Estimation
Feature Correlation
+2
AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results
This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results.
DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation
Scalable Vector Graphics (SVG) are ubiquitous in modern 2D interfaces due to their ability to scale to different resolutions.
Ranked #1 on
Vector Graphics Animation
on SVG-Icons8
Video Object Segmentation with Episodic Graph Memory Networks
How to make a segmentation model efficiently adapt to a specific video and to online target appearance variations are fundamentally crucial issues in the field of video object segmentation.
The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures
Based on that, we articulate the heterogeneity hypothesis: with the same training protocol, there exists a layer-wise differentiated network architecture (LW-DNA) that can outperform the original network with regular channel configurations but with a lower level of model complexity.
SRFlow: Learning the Super-Resolution Space with Normalizing Flow
SRFlow therefore directly accounts for the ill-posed nature of the problem, and learns to predict diverse photo-realistic high-resolution images.
Ranked #6 on
Image Super-Resolution
on DIV2K val - 4x upscaling
(using extra training data)
NTIRE 2020 Challenge on Video Quality Mapping: Methods and Results
For track 2, some existing methods are evaluated, showing promising solutions to the weakly-supervised video quality mapping problem.
NTIRE 2020 Challenge on Real-World Image Super-Resolution: Methods and Results
This paper reviews the NTIRE 2020 challenge on real world super-resolution.
How to Train Your Energy-Based Model for Regression
While they are commonly employed for generative image modeling, recent work has applied EBMs also for regression tasks, achieving state-of-the-art performance on object detection and visual tracking.
Ranked #1 on
Visual Object Tracking
on OTB-100
Learning Human-Object Interaction Detection using Interaction Points
Human-object interaction (HOI) detection strives to localize both the human and an object as well as the identification of complex interactions between them.
Probabilistic Regression for Visual Tracking
In this work, we therefore propose a probabilistic regression formulation and apply it to tracking.
Ranked #4 on
Object Tracking
on FE108
Learning What to Learn for Video Object Segmentation
This allows us to achieve a rich internal representation of the target in the current frame, significantly increasing the segmentation accuracy of our approach.
Know Your Surroundings: Exploiting Scene Information for Object Tracking
Such approaches are however prone to fail in case of e. g. fast appearance changes or presence of distractor objects, where a target appearance model alone is insufficient for robust tracking.
Ranked #8 on
Object Tracking
on FE108
Learning Fast and Robust Target Models for Video Object Segmentation
The target appearance model consists of a light-weight module, which is learned during the inference stage using fast optimization techniques to predict a coarse but robust target segmentation.
GLU-Net: Global-Local Universal Network for Dense Flow and Correspondences
Establishing dense correspondences between a pair of images is an important and general problem, covering geometric matching, optical flow and semantic correspondences.
AIM 2019 Challenge on Real-World Image Super-Resolution: Methods and Results
For training, only one set of source input images is therefore provided in the challenge.
Energy-Based Models for Deep Probabilistic Regression
In our proposed approach, we create an energy-based model of the conditional target density p(y|x), using a deep neural network to predict the un-normalized density from (x, y).
Ranked #1 on
Object Detection
on COCO test-dev
(Hardware Burden metric)
Unsupervised Learning for Real-World Super-Resolution
Instead of directly addressing this problem, most works employ the popular bicubic downsampling strategy to artificially generate a corresponding low resolution image.
Multi-Modal Fusion for End-to-End RGB-T Tracking
Our tracker is trained in an end-to-end manner, enabling the components to learn how to fuse the information from both modalities.
Ranked #7 on
Rgb-T Tracking
on RGBT210
Learning the Model Update for Siamese Trackers
In general, this template is linearly combined with the accumulated template from the previous frame, resulting in an exponential decay of information over time.
Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Vision
We therefore accept this task and propose a comprehensive evaluation framework for scalable epistemic uncertainty estimation methods in deep learning.
Discriminative Online Learning for Fast Video Object Segmentation
We propose a novel approach, based on a dedicated target appearance model that is exclusively learned online to discriminate between the target and background image regions.
Learning Discriminative Model Prediction for Tracking
The current strive towards end-to-end trainable computer vision systems imposes major challenges for the task of visual tracking.
Ranked #5 on
Object Tracking
on FE108
A Generative Appearance Model for End-to-end Video Object Segmentation
One of the fundamental challenges in video object segmentation is to find an effective representation of the target and background appearance.
ATOM: Accurate Tracking by Overlap Maximization
We argue that this approach is fundamentally limited since target estimation is a complex task, requiring high-level knowledge about the object.
Ranked #7 on
Object Tracking
on FE108
Synthetic data generation for end-to-end thermal infrared tracking
These methods provide us with a large labeled dataset of synthetic TIR sequences, on which we can train end-to-end optimal features for tracking.
Unveiling the Power of Deep Tracking
In the field of generic object tracking numerous attempts have been made to exploit deep features.
Density Adaptive Point Set Registration
Contrary to previous works, we model the underlying structure of the scene as a latent probability distribution, and thereby induce invariance to point set density changes.
DCCO: Towards Deformable Continuous Convolution Operators
Generally, DCF based trackers learn a rigid appearance model of the target.
Deep Projective 3D Semantic Segmentation
Recent attempts, based on 3D deep learning approaches (3D-CNNs), have achieved below-expected results.
Ranked #15 on
Semantic Segmentation
on Semantic3D
Deep Motion Features for Visual Tracking
To the best of our knowledge, we are the first to propose fusing appearance information with deep motion features for visual tracking.
ECO: Efficient Convolution Operators for Tracking
Moreover, our fast variant, using hand-crafted features, operates at 60 Hz on a single CPU, while obtaining 65. 0% AUC on OTB-2015.
Ranked #13 on
Visual Object Tracking
on VOT2017/18
Discriminative Scale Space Tracking
Compared to the standard exhaustive scale search, our approach achieves a gain of 2. 5% in average overlap precision on the OTB dataset.
Adaptive Decontamination of the Training Set: A Unified Formulation for Discriminative Visual Tracking
We propose a novel generic approach for alleviating the problem of corrupted training samples in tracking-by-detection frameworks.
Learning Spatially Regularized Correlation Filters for Visual Tracking
These methods utilize a periodic assumption of the training samples to efficiently learn a classifier on all patches in the target neighborhood.
Beyond Correlation Filters: Learning Continuous Convolution Operators for Visual Tracking
We also demonstrate the effectiveness of our learning formulation in extensive feature point tracking experiments.
A Probabilistic Framework for Color-Based Point Set Registration
On the Stanford Lounge dataset, our approach achieves a relative reduction of the failure rate by 78% compared to the baseline.
Adaptive Color Attributes for Real-Time Visual Tracking
This paper investigates the contribution of color in a tracking-by-detection framework.
