Search Results for author:
Found 52 papers, 22 papers with code
High Resolution and Fast Face Completion via Progressively Attentive GANs
Face completion is a challenging task with the difficulty level increasing significantly with respect to high resolution, the complexity of "holes" and the controllable attributes of filled-in fragments.
Continual Learning via Explicit Structure Learning
During structure learning, the model optimizes for the best structure for the current task.
CGBA: Curvature-aware Geometric Black-box Attack
While the proposed CGBA attack can work effectively for an arbitrary decision boundary, it is particularly efficient in exploiting the low curvature to craft high-quality adversarial examples, which is widely seen and experimentally verified in commonly used classifiers under non-targeted attacks.
Volumetric Wireframe Parsing from Neural Attraction Fields
Benefitting from our explicit modeling of 3D junctions, we finally compute the primal sketch of 3D wireframes by attracting the queried 3D line segments to the 3D junctions, significantly simplifying the computation paradigm of 3D wireframe parsing.
Implicit Bayes Adaptation: A Collaborative Transport Approach
We integrate a metric correction term as well as a prior cluster structure in the source data of the OT-driven adaptation.
Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver
Motivated by a new and strong observation that this challenge can be remedied by a 3D-space local-grid search scheme in an ideal case, we propose a stage-wise approach, which combines the information flow from 2D-to-3D (3D bounding box proposal generation with a single 2D image) and 3D-to-2D (proposal verification by denoising with 3D-to-2D contexts) in a top-down manner.
Learning to Grow Artificial Hippocampi in Vision Transformers for Resilient Lifelong Learning
This paper presents a method of learning to grow ArtiHippo in Vision Transformers (ViTs) for resilient lifelong learning.
NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction
This paper studies the challenging two-view 3D reconstruction in a rigorous sparse-view configuration, which is suffering from insufficient correspondences in the input image pairs for camera pose estimation.
Level-S$^2$fM: Structure from Motion on Neural Level Set of Implicit Surfaces
This paper presents a neural incremental Structure-from-Motion (SfM) approach, Level-S$^2$fM, which estimates the camera poses and scene geometry from a set of uncalibrated images by learning coordinate MLPs for the implicit surfaces and the radiance fields from the established keypoint correspondences.
Holistically-Attracted Wireframe Parsing: From Supervised to Self-Supervised Learning
This article presents Holistically-Attracted Wireframe Parsing (HAWP), a method for geometric analysis of 2D images containing wireframes formed by line segments and junctions.
HoW-3D: Holistic 3D Wireframe Perception from a Single Image
This paper studies the problem of holistic 3D wireframe perception (HoW-3D), a new task of perceiving both the visible 3D wireframes and the invisible ones from single-view 2D images.
PaCa-ViT: Learning Patch-to-Cluster Attention in Vision Transformers
The proposed PaCa module is used in designing efficient and interpretable ViT backbones and semantic segmentation head networks.
Refining Self-Supervised Learning in Imaging: Beyond Linear Metric
We introduce in this paper a new statistical perspective, exploiting the Jaccard similarity metric, as a measure-based metric to effectively invoke non-linear features in the loss of self-supervised contrastive learning.
Learning Spatially-Adaptive Squeeze-Excitation Networks for Image Synthesis and Image Recognition
For image recognition tasks, the proposed SASE is used as a drop-in replacement for convolution layers in ResNets and achieves much better accuracy than the vanilla ResNets, and slightly better than the MHSA counterparts such as the Swin-Transformer and Pyramid-Transformer in the ImageNet-1000 dataset, with significantly smaller models.
Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection
It presents the MonoCon method which learns Monocular Contexts, as auxiliary tasks in training, to help monocular 3D object detection.
Ranked #2 on
Monocular 3D Object Detection
on KITTI Cars Moderate
Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimation
This paper studies the problem of multi-person pose estimation in a bottom-up fashion.
Towards Adversarially Robust and Domain Generalizable Stereo Matching by Rethinking DNN Feature Backbones
Although it has been well-known that DNNs often suffer from adversarial vulnerability with a catastrophic drop in performance, the situation is even worse in stereo matching.
PlaneTR: Structure-Guided Transformers for 3D Plane Recovery
This paper presents a neural network built upon Transformers, namely PlaneTR, to simultaneously detect and reconstruct planes from a single image.
Deep Consensus Learning
For the real image corresponding to the input layout, its mask also is computed by the inference network, and then used by the generator to reconstruct the real image.
Local Clustering with Mean Teacher for Semi-supervised Learning
In MT, each data point is considered independent of other points during training; however, data points are likely to be close to each other in feature space if they share similar features.
Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis
This paper focuses on a recent emerged task, layout-to-image, to learn generative models that are capable of synthesizing photo-realistic images from spatial layout (i. e., object bounding boxes configured in an image lattice) and style (i. e., structural and appearance variations encoded by latent vectors).
Ranked #2 on
Layout-to-Image Generation
on COCO-Stuff 128x128
Holistically-Attracted Wireframe Parsing
For computing line segment proposals, a novel exact dual representation is proposed which exploits a parsimonious geometric reparameterization for line segments and forms a holistic 4-dimensional attraction field map for an input image.
Ranked #1 on
Line Segment Detection
on wireframe dataset
(FH metric)
Stochastic-Sign SGD for Federated Learning with Theoretical Guarantees
We present Stochastic-Sign SGD which utilizes novel stochastic-sign based gradient compressors enabling the aforementioned properties in a unified framework.
Learning Regional Attraction for Line Segment Detection
Given a line segment map, the proposed regional attraction first establishes the relationship between line segments and regions in the image lattice.
Towards Interpretable Object Detection by Unfolding Latent Structures
The proposed method focuses on weakly-supervised extractive rationale generation, that is learning to unfold latent discriminative part configurations of object instances automatically and simultaneously in detection without using any supervision for part configurations.
Towards Controllable and Interpretable Face Completion via Structure-Aware and Frequency-Oriented Attentive GANs
The proposed frequency-oriented attentive module (FOAM) encourages GANs to attend to only finer details in the coarse-to-fine progressive training, thus enabling progressive attention to face structures.
Inducing Hierarchical Compositional Model by Sparsifying Generator Network
To realize this AND-OR hierarchy in image synthesis, we learn a generator network that consists of the following two components: (i) Each layer of the hierarchy is represented by an over-complete set of convolutional basis functions.
Image Synthesis From Reconfigurable Layout and Style
Despite remarkable recent progress on both unconditional and conditional image synthesis, it remains a long-standing problem to learn generative models that are capable of synthesizing realistic and sharp images from reconfigurable spatial layout (i. e., bounding boxes + class labels in an image lattice) and style (i. e., structural and appearance variations encoded by latent vectors), especially at high resolution.
Ranked #2 on
Layout-to-Image Generation
on COCO-Stuff 64x64
Attentive Normalization
In state-of-the-art deep neural networks, both feature normalization and feature attention have become ubiquitous.
Ranked #71 on
Instance Segmentation
on COCO minival
Pose Guided Fashion Image Synthesis Using Deep Generative Model
In order to formulate the framework, we employ one generator and two discriminators for image synthesis.
Adversarial Distillation for Ordered Top-k Attacks
One scheme of learning attacks is to design a proper adversarial objective function that leads to the imperceptible perturbation for any test image (e. g., the Carlini-Wagner (C&W) method).
Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting
Addressing catastrophic forgetting is one of the key challenges in continual learning where machine learning systems are trained with sequential or streaming tasks.
Learning Spatial Pyramid Attentive Pooling in Image Synthesis and Image-to-Image Translation
In experiments, the proposed SPAP is tested in GANs on the Celeba-HQ-128 dataset~\cite{karras2017progressive}, and tested in CycleGANs on the Image-to-Image translation datasets including the Cityscape dataset~\cite{cordts2016cityscapes}, Facade and Aerial Maps dataset~\cite{zhu2017unpaired}, both obtaining better performance.
Neural Abstract Style Transfer for Chinese Traditional Painting
In experiments, the proposed method shows more appealing stylized results in transferring the style of Chinese traditional painting than state-of-the-art neural style transfer methods.
Learning Attraction Field Representation for Robust Line Segment Detection
In experiments, our method is tested on the WireFrame dataset and the YorkUrban dataset with state-of-the-art performance obtained.
Relational Long Short-Term Memory for Video Action Recognition
By doing this, our Relational LSTM is capable of capturing long and short-range spatio-temporal relations between objects in videos in a principled way.
ARCHER: Aggressive Rewards to Counter bias in Hindsight Experience Replay
Experience replay is an important technique for addressing sample-inefficiency in deep reinforcement learning (RL), but faces difficulty in learning from binary and sparse rewards due to disproportionately few successful experiences in the replay buffer.
Auto-Context R-CNN
Although surrounding context is well-known for its importance in object detection, it has yet been integrated in R-CNNs in a flexible and effective way.
High Resolution Face Completion with Multiple Controllable Attributes via Fully End-to-End Progressive Generative Adversarial Networks
It is a challenging task with the difficulty level increasing significantly with respect to high resolution, the complexity of "holes" and the controllable attributes of filled-in fragments.
AOGNets: Compositional Grammatical Architectures for Deep Learning
This paper presents deep compositional grammatical architectures which harness the best of two worlds: grammar models and DNNs.
Towards Interpretable R-CNN by Unfolding Latent Structures
We focus on weakly-supervised extractive rationale generation, that is learning to unfold latent discriminative part configurations of object instances automatically and simultaneously in detection without using any supervision for part configurations.
Scene-centric Joint Parsing of Cross-view Videos
The proposed joint parsing framework represents such correlations and constraints explicitly and generates semantic scene-centric parse graphs.
An Attention-Driven Approach of No-Reference Image Quality Assessment
The model learning is implemented by a reinforcement strategy, in which the rewards of both tasks guide the learning of the optimal sampling policy to acquire the "task-informative" image regions so that the predictions can be made accurately and efficiently (in terms of the sampling steps).
Multi-Task Learning
No-Reference Image Quality Assessment
+1
Zero-Shot Learning posed as a Missing Data Problem
This paper presents a method of zero-shot learning (ZSL) which poses ZSL as the missing data problem, rather than the missing label problem.
Object Detection via Aspect Ratio and Context Aware Region-based Convolutional Networks
This paper presents a method of integrating a mixture of object models and region-based convolutional networks for accurate object detection.
Face Detection with End-to-End Integration of a ConvNet and a 3D Model
The proposed method addresses two issues in adapting state- of-the-art generic object detection ConvNets (e. g., faster R-CNN) for face detection: (i) One is to eliminate the heuristic design of prede- fined anchor boxes in the region proposals network (RPN) by exploit- ing a 3D mean face model.
Ranked #7 on
Face Detection
on Annotated Faces in the Wild
Recognizing Car Fluents from Video
Since there are no publicly related dataset, we collect and annotate a car fluent dataset consisting of car videos with diverse fluents.
A Restricted Visual Turing Test for Deep Scene and Event Understanding
and a sequence of story-line based queries, the task is to provide answers either simply in binary form "true/false" (to a polar query) or in an accurate natural language description (to a non-polar query).
Online Object Tracking, Learning and Parsing with And-Or Graphs
In the former, our AOGTracker outperforms state-of-the-art tracking algorithms including two trackers based on deep convolutional network.
Learning And-Or Models to Represent Context and Occlusion for Car Detection and Viewpoint Estimation
Firstly, the structure of the And-Or model is learned with three components: (a) mining multi-car contextual patterns based on layouts of annotated single car bounding boxes, (b) mining occlusion configurations between single cars, and (c) learning different combinations of part visibility based on car 3D CAD simulation.
Discriminatively Trained And-Or Tree Models for Object Detection
This paper presents a method of learning reconfigurable And-Or Tree (AOT) models discriminatively from weakly annotated data for object detection.
Learning Mixtures of Bernoulli Templates by Two-Round EM with Performance Guarantee
Each template is a binary vector, and a template generates examples by randomly switching its binary components independently with a certain probability.
