5.2k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- SupélecFR485 papers
- University of Applied Sciences and Arts of Southern SwitzerlandCH485 papers
- New York UniversityUS52 papers
- Google (United States)US16 papers
- Princeton UniversityUS15 papers
- Courant Institute of Mathematical SciencesUS13 papers
- Meta (Israel)IL11 papers
- Massachusetts Institute of TechnologyUS10 papers
- Stanford UniversityUS8 papers
- University of California, BerkeleyUS8 papers
- Cornell UniversityUS7 papers
- Carnegie Mellon UniversityUS6 papers
38 papers · 1 filter
A Dataset-Dispersion Perspective on Reconstruction Versus Recognition in Single-View 3D Reconstruction Networks
Yefan Zhou, Yiru Shen, Yujun Yan +2
Neural networks (NN) for single-view 3D reconstruction (SVR) have gained in popularity. Recent work points out that for SVR, most cutting-edge NNs have limited performance on recon…
Active Learning at the ImageNet Scale
Zeyad Ali Sami Emam, Hong-Min Chu, Ping-Yeh Chiang +4
Active learning (AL) algorithms aim to identify an optimal subset of data for annotation, such that deep neural networks (DNN) can achieve better performance when trained on this l…
Adversarial Token Attacks on Vision Transformers
Ameya Joshi, Gauri Jagatap, Chinmay Hegde
Vision transformers rely on a patch token based self attention mechanism, in contrast to convolutional networks. We investigate fundamental differences between these two families o…
3D Meta-Segmentation Neural Network
Yu Hao, Yi Fang
Though deep learning methods have shown great success in 3D point cloud part segmentation, they generally rely on a large volume of labeled training data, which makes the model suf…
Meta-Learning 3D Shape Segmentation Functions
Yu Hao, Hao Huang, Shuaihang Yuan +1
Learning robust 3D shape segmentation functions with deep neural networks has emerged as a powerful paradigm, offering promising performance in producing a consistent part segmenta…
ContinuityLearner: Geometric Continuity Feature Learning for Lane Segmentation
Haoyu Fang, Jing Zhu, Yi Fang
Lane segmentation is a challenging issue in autonomous driving system designing because lane marks show weak textural consistency due to occlusion or extreme illumination but stron…
Understanding Gender and Racial Disparities in Image Recognition Models
Rohan Mahadev, Anindya Chakravarti
Large scale image classification models trained on top of popular datasets such as Imagenet have shown to have a distributional skew which leads to disparities in prediction accura…
Multi-Label Generalized Zero Shot Learning for the Classification of Disease in Chest Radiographs
Nasir Hayat, Hazem Lashen, Farah E. Shamout
Despite the success of deep neural networks in chest X-ray (CXR) diagnosis, supervised learning only allows the prediction of disease classes that were seen during training. At inf…
Learn to Learn Metric Space for Few-Shot Segmentation of 3D Shapes
Xiang Li, Lingjing Wang, Yi Fang
Recent research has seen numerous supervised learning-based methods for 3D shape segmentation and remarkable performance has been achieved on various benchmark datasets. These supe…
G-VAE, a Geometric Convolutional VAE for ProteinStructure Generation
Hao Huang, Boulbaba Ben Amor, Xichan Lin +2
Analyzing the structure of proteins is a key part of understanding their functions and thus their role in biology at the molecular level. In addition, design new proteins in a meth…
Residual Networks as Flows of Velocity Fields for Diffeomorphic Time Series Alignment
Hao Huang, Boulbaba Ben Amor, Xichan Lin +2
Non-linear (large) time warping is a challenging source of nuisance in time-series analysis. In this paper, we propose a novel diffeomorphic temporal transformer network for both p…
Flexible Compositional Learning of Structured Visual Concepts
Yanli Zhou, Brenden M. Lake
Humans are highly efficient learners, with the ability to grasp the meaning of a new concept from just a few examples. Unlike popular computer vision systems, humans can flexibly l…
Point-supervised Segmentation of Microscopy Images and Volumes via Objectness Regularization
Shijie Li, Neel Dey, Katharina Bermond +4
Annotation is a major hurdle in the semantic segmentation of microscopy images and volumes due to its prerequisite expertise and effort. This work enables the training of semantic…
Hard-Attention for Scalable Image Classification
Athanasios Papadopoulos, Paweł Korus, Nasir Memon
Can we leverage high-resolution information without the unsustainable quadratic complexity to input scale? We propose Traversal Network (TNet), a novel multi-scale hard-attention a…
Re Learning Memory Guided Normality for Anomaly Detection
Kevin Stephen, Varun Menon
The authors have introduced a novel method for unsupervised anomaly detection that utilises a newly introduced Memory Module in their paper. We validate the authors claim that this…
NAPA: Neural Art Human Pose Amplifier
Qingfu Wan, Oliver Lu
This is the project report for CSCI-GA.2271-001. We target human pose estimation in artistic images. For this goal, we design an end-to-end system that uses neural style transfer f…
Learned Equivariant Rendering without Transformation Supervision
Cinjon Resnick, Or Litany, Hugo Larochelle +2
We propose a self-supervised framework to learn scene representations from video that are automatically delineated into objects and background. Our method relies on moving objects…
Fine-Grained Re-Identification
Priyank Pathak
Research into the task of re-identification (ReID) is picking up momentum in computer vision for its many use cases and zero-shot learning nature. This paper proposes a computation…
Investigating and Simplifying Masking-based Saliency Methods for Model Interpretability
Jason Phang, Jungkyu Park, Krzysztof J. Geras
Saliency maps that identify the most informative regions of an image for a classifier are valuable for model interpretability. A common approach to creating saliency maps involves…
Mind the Pad -- CNNs can Develop Blind Spots
Bilal Alsallakh, Narine Kokhlikyan, Vivek Miglani +2
We show how feature maps in convolutional networks are susceptible to spatial bias. Due to a combination of architectural choices, the activation at certain locations is systematic…
Encoding Robustness to Image Style via Adversarial Feature Perturbations
Manli Shu, Zuxuan Wu, Micah Goldblum +1
Adversarial training is the industry standard for producing models that are robust to small adversarial perturbations. However, machine learning practitioners need models that are…
ImagiFilter: A resource to enable the semi-automatic mining of images at scale
Houda Alberts, Iacer Calixto
Datasets (semi-)automatically collected from the web can easily scale to millions of entries, but a dataset's usefulness is directly related to how clean and high-quality its examp…
Robust Image Matching By Dynamic Feature Selection
Hao Huang, Jianchun Chen, Xiang Li +2
Estimating dense correspondences between images is a long-standing image under-standing task. Recent works introduce convolutional neural networks (CNNs) to extract high-level feat…
Using Human Psychophysics to Evaluate Generalization in Scene Text Recognition Models
Sahar Siddiqui, Elena Sizikova, Gemma Roig +2
Scene text recognition models have advanced greatly in recent years. Inspired by human reading we characterize two important scene text recognition models by measuring their domain…