• Publications
  • Influence
Going deeper with convolutions
We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual RecognitionExpand
SuperPoint: Self-Supervised Interest Point Detection and Description
This paper presents a self-supervised framework for training interest point detectors and descriptors suitable for a large number of multiple-view geometry problems in computer vision and introduces Homographic Adaptation, a multi-scale, multi-homography approach for boosting interest point detection repeatability and performing cross-domain adaptation. Expand
Training Deep Neural Networks on Noisy Labels with Bootstrapping
A generic way to handle noisy and incomplete labeling by augmenting the prediction objective with a notion of consistency is proposed, which considers a prediction consistent if the same prediction is made given similar percepts, where the notion of similarity is between deep network features computed from the input data. Expand
ParseNet: Looking Wider to See Better
This work presents a technique for adding global context to deep convolutional networks for semantic segmentation, and achieves state-of-the-art performance on SiftFlow and PASCAL-Context with small additional computational cost over baselines. Expand
GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks
A gradient normalization (GradNorm) algorithm that automatically balances training in deep multitask models by dynamically tuning gradient magnitudes is presented, showing that for various network architectures, for both regression and classification tasks, and on both synthetic and real datasets, GradNorm improves accuracy and reduces overfitting across multiple tasks. Expand
Objects in Context
This work proposes to incorporate semantic object context as a post-processing step into any off-the-shelf object categorization model using a conditional random field (CRF) framework, which maximizes object label agreement according to contextual relevance. Expand
Deep Image Homography Estimation
Two convolutional neural network architectures are presented for HomographyNet: a regression network which directly estimates the real-valued homography parameters, and a classification network which produces a distribution over quantized homographies. Expand
SuperGlue: Learning Feature Matching With Graph Neural Networks
SuperGlue is introduced, a neural network that matches two sets of local features by jointly finding correspondences and rejecting non-matchable points and introduces a flexible context aggregation mechanism based on attention, enabling SuperGlue to reason about the underlying 3D scene and feature assignments jointly. Expand
Object categorization using co-occurrence, location and appearance
This work introduces a novel approach to object categorization that incorporates two types of context-co-occurrence and relative location - with local appearance-based features and uses a conditional random field (CRF) to maximize object label agreement according to both semantic and spatial relevance. Expand
RoomNet: End-to-End Room Layout Estimation
This paper predicts the locations of the room layout keypoints using RoomNet, an end-to-end trainable encoder-decoder network and presents optional extensions to the RoomNet architecture such as including recurrent computations and memory units to refine the keypoint locations under the same parametric capacity. Expand