692 citations · 1.7k across the 18 of their papers we have counts for
20 papers
MedFMC: A Real-world Dataset and Benchmark For Foundation Model Adaptation in Medical Image Classification
Dequan Wang, Xiaosong Wang, Lilong Wang +12
Foundation models, often pre-trained with large-scale data, have achieved paramount success in jump-starting various vision and language applications. Recent advances further enabl…
MAROAM: Map-based Radar SLAM through Two-step Feature Selection
Dequan Wang, Yifan Duan, Xiaoran Fan +3
In this letter, we propose MAROAM, a millimeter wave radar-based SLAM framework, which employs a two-step feature selection process to build the global consistent map. Specifically…
Decentralized Vehicle Coordination: The Berkeley DeepDrive Drone Dataset and Consensus-Based Models
Fangyu Wu, Dequan Wang, Minjune Hwang +6
A significant portion of roads, particularly in densely populated developing countries, lacks explicitly defined right-of-way rules. These understructured roads pose substantial ch…
GACT: Activation Compressed Training for Generic Network Architectures
Xiaoxuan Liu, Lianmin Zheng, Dequan Wang +9
Training large neural network (NN) models requires extensive memory resources, and Activation Compressed Training (ACT) is a promising approach to reduce training memory footprint.…
BEV-Seg: Bird's Eye View Semantic Segmentation Using Geometry and Semantic Point Cloud
Mong H. Ng, Kaahan Radia, Jianfei Chen +3
Bird's-eye-view (BEV) is a powerful and widely adopted representation for road scenes that captures surrounding objects and their spatial locations, along with overall context in t…
Tent: Fully Test-time Adaptation by Entropy Minimization
Dequan Wang, Evan Shelhamer, Shaoteng Liu +2
A model must adapt itself to generalize to new and different data during testing. In this setting of fully test-time adaptation the model has only the test data and its own paramet…
CoDeNet: Efficient Deployment of Input-Adaptive Object Detection on Embedded FPGAs
Zhen Dong, Dequan Wang, Qijing Huang +6
Deploying deep learning models on embedded systems has been challenging due to limited computing resources. The majority of existing work focuses on accelerating image classificati…
Algorithm-hardware Co-design for Deformable Convolution
Qijing Huang, Dequan Wang, Yizhao Gao +5
FPGAs provide a flexible and efficient platform to accelerate rapidly-changing algorithms for computer vision. The majority of existing work focuses on accelerating image classific…
Dynamic Scale Inference by Entropy Minimization
Dequan Wang, Evan Shelhamer, Bruno Olshausen +1
Given the variety of the visual world there is not one true scale for recognition: objects may appear at drastically different sizes across the visual field. Rather than enumerate…
Monocular Plan View Networks for Autonomous Driving
Dequan Wang, Coline Devin, Qi-Zhi Cai +2
Convolutions on monocular dash cam videos capture spatial invariances in the image plane but do not explicitly reason about distances and depth. We propose a simple transformation…
Blurring the Line Between Structure and Learning to Optimize and Adapt Receptive Fields
Evan Shelhamer, Dequan Wang, Trevor Darrell
The visual world is vast and varied, but its variations divide into structured and unstructured factors. We compose free-form filters and structured Gaussian filters, optimized end…
Objects as Points
Xingyi Zhou, Dequan Wang, Philipp Krähenbühl
Detection identifies objects as axis-aligned boxes in an image. Most successful object detectors enumerate a nearly exhaustive list of potential object locations and classify each.…
Convolutional Neural Networks on non-uniform geometrical signals using Euclidean spectral transformation
Chiyu "Max" Jiang, Dequan Wang, Jingwei Huang +2
Convolutional Neural Networks (CNN) have been successful in processing data signals that are uniformly sampled in the spatial domain (e.g., images). However, most data signals do n…
Joint Monocular 3D Vehicle Detection and Tracking
Hou-Ning Hu, Qi-Zhi Cai, Dequan Wang +5
Vehicle 3D extents and trajectories are critical cues for predicting the future location of vehicles and planning future agent ego-motion based on those predictions. In this paper,…
Deep Object-Centric Policies for Autonomous Driving
Dequan Wang, Coline Devin, Qi-Zhi Cai +2
While learning visuomotor skills in an end-to-end manner is appealing, deep neural networks are often uninterpretable and fail in surprising ways. For robotics tasks, such as auton…
VisDA: The Visual Domain Adaptation Challenge
Xingchao Peng, Ben Usman, Neela Kaushik +3
We present the 2017 Visual Domain Adaptation (VisDA) dataset and challenge, a large-scale testbed for unsupervised domain adaptation across visual domains. Unsupervised domain adap…
Deep Layer Aggregation
Fisher Yu, Dequan Wang, Evan Shelhamer +1
Visual recognition requires rich representations that span levels from low to high, scales from small to large, and resolutions from fine to coarse. Even with the depth of features…
Iterative Object and Part Transfer for Fine-Grained Recognition
Zhiqiang Shen, Yu-Gang Jiang, Dequan Wang +1
The aim of fine-grained recognition is to identify sub-ordinate categories in images like different species of birds. Existing works have confirmed that, in order to capture the su…
FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
Judy Hoffman, Dequan Wang, Fisher Yu +1
Fully convolutional models for dense prediction have proven successful for a wide range of visual tasks. Such models perform well in a supervised setting, but performance can be su…
Learning to Point and Count
Jie Shao, Dequan Wang, Xiangyang Xue +1
This paper proposes the problem of point-and-count as a test case to break the what-and-where deadlock. Different from the traditional detection problem, the goal is to discover ke…