25 citations · 78 across the 25 of their papers we have counts for
28 papers
Resolving Inconsistent Semantics in Multi-Dataset Image Segmentation
Qilong Zhangli, Di Liu, Abhishek Aich +2
Leveraging multiple training datasets to scale up image segmentation models is beneficial for increasing robustness and semantic understanding. Individual datasets have well-define…
Self-Training Large Language Models for Improved Visual Program Synthesis With Visual Reinforcement
Zaid Khan, Vijay Kumar BG, Samuel Schulter +2
Visual program synthesis is a promising approach to exploit the reasoning abilities of large language models for compositional computer vision tasks. Previous work has used few-sho…
Progressive Token Length Scaling in Transformer Encoders for Efficient Universal Segmentation
Abhishek Aich, Yumin Suh, Samuel Schulter +1
A powerful architecture for universal segmentation relies on transformers that encode multi-scale image features and decode object queries into mask predictions. With efficiency be…
AIDE: An Automatic Data Engine for Object Detection in Autonomous Driving
Mingfu Liang, Jong-Chyi Su, Samuel Schulter +4
Autonomous vehicle (AV) systems rely on robust perception models as a cornerstone of safety assurance. However, objects encountered on the road exhibit a long-tailed distribution,…
Generating Enhanced Negatives for Training Language-Based Object Detectors
Shiyu Zhao, Long Zhao, Vijay Kumar B. G +4
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 annotatio…
Exploring Question Decomposition for Zero-Shot VQA
Zaid Khan, Vijay Kumar BG, Samuel Schulter +2
Visual question answering (VQA) has traditionally been treated as a single-step task where each question receives the same amount of effort, unlike natural human question-answering…
Efficient Controllable Multi-Task Architectures
Abhishek Aich, Samuel Schulter, Amit K. Roy-Chowdhury +2
We aim to train a multi-task model such that users can adjust the desired compute budget and relative importance of task performances after deployment, without retraining. This ena…
Taming Self-Training for Open-Vocabulary Object Detection
Shiyu Zhao, Samuel Schulter, Long Zhao +5
Recent studies have shown promising performance in open-vocabulary object detection (OVD) by utilizing pseudo labels (PLs) from pretrained vision and language models (VLMs). Howeve…
Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!
Zaid Khan, Vijay Kumar BG, Samuel Schulter +3
Finetuning a large vision language model (VLM) on a target dataset after large scale pretraining is a dominant paradigm in visual question answering (VQA). Datasets for specialized…
NeurOCS: Neural NOCS Supervision for Monocular 3D Object Localization
Zhixiang Min, Bingbing Zhuang, Samuel Schulter +3
Monocular 3D object localization in driving scenes is a crucial task, but challenging due to its ill-posed nature. Estimating 3D coordinates for each pixel on the object surface ho…
OmniLabel: A Challenging Benchmark for Language-Based Object Detection
Samuel Schulter, Vijay Kumar B G, Yumin Suh +4
Language-based object detection is a promising direction towards building a natural interface to describe objects in images that goes far beyond plain category names. While recent…
Exploiting Unlabeled Data with Vision and Language Models for Object Detection
Shiyu Zhao, Zhixing Zhang, Samuel Schulter +5
Building robust and generic object detection frameworks requires scaling to larger label spaces and bigger training datasets. However, it is prohibitively costly to acquire annotat…
MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation
Inkyu Shin, Yi-Hsuan Tsai, Bingbing Zhuang +5
Test-time adaptation approaches have recently emerged as a practical solution for handling domain shift without access to the source domain data. In this paper, we propose and expl…
Controllable Dynamic Multi-Task Architectures
Dripta S. Raychaudhuri, Yumin Suh, Samuel Schulter +4
Multi-task learning commonly encounters competition for resources among tasks, specifically when model capacity is limited. This challenge motivates models which allow control over…
On Generalizing Beyond Domains in Cross-Domain Continual Learning
Christian Simon, Masoud Faraki, Yi-Hsuan Tsai +5
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 knowled…
Single-Stream Multi-Level Alignment for Vision-Language Pretraining
Zaid Khan, Vijay Kumar BG, Xiang Yu +3
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 tha…
Domain Adaptation for Semantic Segmentation via Patch-Wise Contrastive Learning
Weizhe Liu, David Ferstl, Samuel Schulter +3
We introduce a novel approach to unsupervised and semi-supervised domain adaptation for semantic segmentation. Unlike many earlier methods that rely on adversarial learning for fea…
Object Detection with a Unified Label Space from Multiple Datasets
Xiangyun Zhao, Samuel Schulter, Gaurav Sharma +3
Given multiple datasets with different label spaces, the goal of this work is to train a single object detector predicting over the union of all the label spaces. The practical ben…
Domain Adaptive Semantic Segmentation Using Weak Labels
Sujoy Paul, Yi-Hsuan Tsai, Samuel Schulter +2
Learning semantic segmentation models requires a huge amount of pixel-wise labeling. However, labeled data may only be available abundantly in a domain different from the desired t…
Understanding Road Layout from Videos as a Whole
Buyu Liu, Bingbing Zhuang, Samuel Schulter +2
In this paper, we address the problem of inferring the layout of complex road scenes from video sequences. To this end, we formulate it as a top-view road attributes prediction pro…
Domain Adaptation for Structured Output via Discriminative Patch Representations
Yi-Hsuan Tsai, Kihyuk Sohn, Samuel Schulter +1
Predicting structured outputs such as semantic segmentation relies on expensive per-pixel annotations to learn supervised models like convolutional neural networks. However, models…
A Parametric Top-View Representation of Complex Road Scenes
Ziyan Wang, Buyu Liu, Samuel Schulter +1
In this paper, we address the problem of inferring the layout of complex road scenes given a single camera as input. To achieve that, we first propose a novel parameterized model o…
Learning To Simulate
Nataniel Ruiz, Samuel Schulter, Manmohan Chandraker
Simulation is a useful tool in situations where training data for machine learning models is costly to annotate or even hard to acquire. In this work, we propose a reinforcement le…
Learning to Look around Objects for Top-View Representations of Outdoor Scenes
Samuel Schulter, Menghua Zhai, Nathan Jacobs +1
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-…