Search Results for author:
Found 31 papers, 7 papers with code
Shuffle and Attend: Video Domain Adaptation
As the first novelty, we propose an attention mechanism which focuses on more discriminative clips and directly optimizes for video-level (cf.
Ranked #3 on
Unsupervised Domain Adaptation
on UCF-HMDB
Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement
We propose a method where we exploit existing annotations for a vision-language task to improvise a coarse reward signal for that task, treat the LLM as a policy, and apply reinforced self-training to improve the visual program synthesis ability of the LLM for that task.
AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving
This necessitates an expensive process of continuously curating and annotating data with significant human effort.
Generating Enhanced Negatives for Training Language-Based Object Detectors
The recent progress in language-based open-vocabulary object detection can be largely attributed to finding better ways of leveraging large-scale data with free-form text annotations.
Efficient Controllable Multi-Task Architectures
Further, we present a simple but effective search algorithm that translates user constraints to runtime width configurations of both the shared encoder and task decoders, for sampling the sub-architectures.
Taming Self-Training for Open-Vocabulary Object Detection
This work identifies two challenges of using self-training in OVD: noisy PLs from VLMs and frequent distribution changes of PLs.
Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!
We introduce SelTDA (Self-Taught Data Augmentation), a strategy for finetuning large VLMs on small-scale VQA datasets.
NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization
Monocular 3D object localization in driving scenes is a crucial task, but challenging due to its ill-posed nature.
OmniLabel: A Challenging Benchmark for Language-Based Object Detection
With more than 28K unique object descriptions on over 25K images, OmniLabel provides a challenging benchmark with diverse and complex object descriptions in a naturally open-vocabulary setting.
Exploiting Unlabeled Data with Vision and Language Models for Object Detection
We propose a novel method that leverages the rich semantics available in recent vision and language models to localize and classify objects in unlabeled images, effectively generating pseudo labels for object detection.
Ranked #15 on
Open Vocabulary Object Detection
on MSCOCO
(using extra training data)
MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation
In this paper, we propose and explore a new multi-modal extension of test-time adaptation for 3D semantic segmentation.
Controllable Dynamic Multi-Task Architectures
In contrast to the existing dynamic multi-task approaches that adjust only the weights within a fixed architecture, our approach affords the flexibility to dynamically control the total computational cost and match the user-preferred task importance better.
Single-Stream Multi-Level Alignment for Vision-Language Pretraining
Self-supervised vision-language pretraining from pure images and text with a contrastive loss is effective, but ignores fine-grained alignment due to a dual-stream architecture that aligns image and text representations only on a global level.
On Generalizing Beyond Domains in Cross-Domain Continual Learning
Humans have the ability to accumulate knowledge of new tasks in varying conditions, but deep neural networks often suffer from catastrophic forgetting of previously learned knowledge after learning a new task.
Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning
We introduce a novel approach to unsupervised and semi-supervised domain adaptation for semantic segmentation.
Object Detection with a Unified Label Space from Multiple Datasets
To address this challenge, we design a framework which works with such partial annotations, and we exploit a pseudo labeling approach that we adapt for our specific case.
Domain Adaptive Semantic Segmentation Using Weak Labels
In this work, we propose a novel framework for domain adaptation in semantic segmentation with image-level weak labels in the target domain.
Understanding Road Layout from Videos as a Whole
(2) Introducing the LSTM and FTM modules improves the prediction consistency in videos.
Domain Adaptation for Structured Output via Disentangled Patch Representations
To this end, we propose to learn discriminative feature representations of patches based on label histograms in the source domain, through the construction of a disentangled space.
Domain Adaptation for Structured Output via Discriminative Patch Representations
Predicting structured outputs such as semantic segmentation relies on expensive per-pixel annotations to learn supervised models like convolutional neural networks.
Ranked #22 on
Image-to-Image Translation
on SYNTHIA-to-Cityscapes
A Parametric Top-View Representation of Complex Road Scenes
In this paper, we address the problem of inferring the layout of complex road scenes given a single camera as input.
Learning To Simulate
Simulation is a useful tool in situations where training data for machine learning models is costly to annotate or even hard to acquire.
Learning to Look around Objects for Top-View Representations of Outdoor Scenes
Given a single RGB image of a complex outdoor road scene in the perspective view, we address the novel problem of estimating an occlusion-reasoned semantic scene layout in the top-view.
Memory Warps for Learning Long-Term Online Video Representations
This paper proposes a novel memory-based online video representation that is efficient, accurate and predictive.
Learning to Adapt Structured Output Space for Semantic Segmentation
In this paper, we propose an adversarial learning method for domain adaptation in the context of semantic segmentation.
Ranked #3 on
Domain Adaptation
on Synscapes-to-Cityscapes
Deep Network Flow for Multi-Object Tracking
In this work, we demonstrate that it is possible to learn features for network-flow-based data association via backpropagation, by expressing the optimum of a smoothed network flow problem as a differentiable function of the pairwise association costs.
Conditioned Regression Models for Non-Blind Single Image Super-Resolution
However, this setting is not realistic for practical applications, because the blur is typically different for each test image.
Hybrid One-Shot 3D Hand Pose Estimation by Exploiting Uncertainties
Model-based approaches to 3D hand tracking have been shown to perform well in a wide range of scenarios.
Fast and Accurate Image Upscaling With Super-Resolution Forests
The aim of single image super-resolution is to reconstruct a high-resolution image from a single low-resolution input.
Accurate Object Detection with Joint Classification-Regression Random Forests
In this way, we can simultaneously predict the object probability of a window in a sliding window approach as well as regress its aspect ratio with a single model.
Alternating Decision Forests
Contrary to Boosted Trees, in our method the loss minimization is an inherent part of the tree growing process, thus allowing to keep the benefits of common Random Forests, such as, parallel processing.
