Search Results for author:
Found 71 papers, 31 papers with code
Fixing Localization Errors to Improve Image Classification
This way, in an effort to fix localization errors, our loss provides an extra supervisory signal that helps the model to better discriminate between similar classes.
High-level Feature Guided Decoding for Semantic Segmentation
One crucial design of the HFG is to protect the high-level features from being contaminated by using proper stop-gradient operations so that the backbone does not update according to the noisy gradient from the upsampler.
DC-Former: Diverse and Compact Transformer for Person Re-Identification
In this paper, we propose a Diverse and Compact Transformer (DC-Former) that can achieve a similar effect by splitting embedding space into multiple diverse and compact subspaces.
Event-triggered Hybrid Energy-aware Scheduling in Manufacturing Systems
When the model does not work well, it is triggered as the variable to tune to improve the performance.
Harmonious Teacher for Cross-Domain Object Detection
Self-training approaches recently achieved promising results in cross-domain object detection, where people iteratively generate pseudo labels for unlabeled target domain samples with a model, and select high-confidence samples to refine the model.
SGLoc: Scene Geometry Encoding for Outdoor LiDAR Localization
In this work, we propose a novel LiDAR localization framework, SGLoc, which decouples the pose estimation to point cloud correspondence regression and pose estimation via this correspondence.
Minimizing Maximum Model Discrepancy for Transferable Black-box Targeted Attacks
On the algorithmic side, we derive a new algorithm for black-box targeted attacks based on our theoretical analysis, in which we additionally minimize the maximum model discrepancy(M3D) of the substitute models when training the generator to generate adversarial examples.
Coarse-Super-Resolution-Fine Network (CoSF-Net): A Unified End-to-End Neural Network for 4D-MRI with Simultaneous Motion Estimation and Super-Resolution
Four-dimensional magnetic resonance imaging (4D-MRI) is an emerging technique for tumor motion management in image-guided radiation therapy (IGRT).
Motion and Appearance Adaptation for Cross-Domain Motion Transfer
Motion transfer aims to transfer the motion of a driving video to a source image.
Motion Transformer for Unsupervised Image Animation
Image animation aims to animate a source image by using motion learned from a driving video.
Revisiting AP Loss for Dense Object Detection: Adaptive Ranking Pair Selection
However, a deep understanding of how AP loss affects the detector from a pairwise ranking perspective has not yet been developed. In this work, we revisit the average precision (AP)loss and reveal that the crucial element is that of selecting the ranking pairs between positive and negative samples. Based on this observation, we propose two strategies to improve the AP loss.
Solutions for Fine-grained and Long-tailed Snake Species Recognition in SnakeCLEF 2022
Automatic snake species recognition is important because it has vast potential to help lower deaths and disabilities caused by snakebites.
Adversarial Laser Spot: Robust and Covert Physical-World Attack to DNNs
It realizes robust and covert physical attack by using low-cost laser equipment.
Cross-domain Detection Transformer based on Spatial-aware and Semantic-aware Token Alignment
In particular, we take advantage of the characteristics of cross-attention as used in detection transformer and propose the spatial-aware token alignment (SpaTA) and the semantic-aware token alignment (SemTA) strategies to guide the token alignment across domains.
Revisiting Random Channel Pruning for Neural Network Compression
The proposed approach provides a new way to compare different methods, namely how well they behave compared with random pruning.
Undoing the Damage of Label Shift for Cross-domain Semantic Segmentation
Existing works typically treat cross-domain semantic segmentation (CDSS) as a data distribution mismatch problem and focus on aligning the marginal distribution or conditional distribution.
Structure-Aware Motion Transfer with Deformable Anchor Model
Specifically, inspired by the known deformable part model (DPM), our DAM introduces two types of anchors or keypoints: i) a number of motion anchors that capture both appearance and motion information from the source image and driving video; ii) a latent root anchor, which is linked to the motion anchors to facilitate better learning of the representations of the object structure information.
Learning Pixel-Level Distinctions for Video Highlight Detection
To this end, we propose to learn pixel-level distinctions to improve the video highlight detection.
Adversarial Neon Beam: A Light-based Physical Attack to DNNs
Moreover, we validate the robustness of our approach by successfully attacking advanced DNNs with a success rate of over 75% in all cases.
Semantic-Aware Domain Generalized Segmentation
In this paper, we address domain generalized semantic segmentation, where a segmentation model is trained to be domain-invariant without using any target domain data.
Diverse Preference Augmentation with Multiple Domains for Cold-start Recommendations
Motivated by the idea of meta-augmentation, in this paper, by treating a user's preference over items as a task, we propose a so-called Diverse Preference Augmentation framework with multiple source domains based on meta-learning (referred to as MetaDPA) to i) generate diverse ratings in a new domain of interest (known as target domain) to handle overfitting on the case of sparse interactions, and to ii) learn a preference model in the target domain via a meta-learning scheme to alleviate cold-start issues.
Revisiting Deep Semi-supervised Learning: An Empirical Distribution Alignment Framework and Its Generalization Bound
Benefited from this new perspective, we first propose a new deep semi-supervised learning framework called Semi-supervised Learning by Empirical Distribution Alignment (SLEDA), in which existing technologies from the domain adaptation community can be readily used to address the semi-supervised learning problem through reducing the empirical distribution distance between labeled and unlabeled data.
Meta Distribution Alignment for Generalizable Person Re-Identification
Domain Generalizable (DG) person ReID is a challenging task which trains a model on source domains yet generalizes well on target domains.
Domain Generalization
Generalizable Person Re-identification
+1
Move As You Like: Image Animation in E-Commerce Scenario
Creative image animations are attractive in e-commerce applications, where motion transfer is one of the import ways to generate animations from static images.
HBReID: Harder Batch for Re-identification
Triplet loss is a widely adopted loss function in ReID task which pulls the hardest positive pairs close and pushes the hardest negative pairs far away.
Counterfactual Debiasing Inference for Compositional Action Recognition
By doing that, our proposed CDN method can better recognize unseen action instances by debiasing the effect of appearances.
LZ1904 at SemEval-2021 Task 5: Bi-LSTM-CRF for Toxic Span Detection using Pretrained Word Embedding
And then we construct Bidirectional Long Short Term Memory-Conditional Random Field (Bi-LSTM-CRF) model by Baidu research to predict whether each word in the sentence is toxic or not.
Sparse-to-dense Feature Matching: Intra and Inter domain Cross-modal Learning in Domain Adaptation for 3D Semantic Segmentation
Domain adaptation is critical for success when confronting with the lack of annotations in a new domain.
SRDAN: Scale-Aware and Range-Aware Domain Adaptation Network for Cross-Dataset 3D Object Detection
In this work, we propose a new cross-dataset 3D object detection method named Scale-aware and Range-aware Domain Adaptation Network (SRDAN).
Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Report
Video super-resolution has recently become one of the most important mobile-related problems due to the rise of video communication and streaming services.
VDM-DA: Virtual Domain Modeling for Source Data-free Domain Adaptation
On the other hand, we also design an effective distribution alignment method to reduce the distribution divergence between the virtual domain and the target domain by gradually improving the compactness of the target domain distribution through model learning.
BAPA-Net: Boundary Adaptation and Prototype Alignment for Cross-Domain Semantic Segmentation
By integrating the boundary adaptation and prototype alignment, we are able to train a discriminative and domain-invariant model for cross-domain semantic segmentation.
Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation
Open compound domain adaptation (OCDA) is a domain adaptation setting, where target domain is modeled as a compound of multiple unknown homogeneous domains, which brings the advantage of improved generalization to unseen domains.
mDALU: Multi-Source Domain Adaptation and Label Unification with Partial Datasets
One challenge of object recognition is to generalize to new domains, to more classes and/or to new modalities.
Region Comparison Network for Interpretable Few-shot Image Classification
For that, in this work, we propose a metric learning based method named Region Comparison Network (RCN), which is able to reveal how few-shot learning works as in a neural network as well as to find out specific regions that are related to each other in images coming from the query and support sets.
Ranked #32 on
Few-Shot Image Classification
on CIFAR-FS 5-way (5-shot)
Zero-Shot Heterogeneous Transfer Learning from Recommender Systems to Cold-Start Search Retrieval
In light of these problems, we observed that most online content platforms have both a search and a recommender system that, while having heterogeneous input spaces, can be connected through their common output item space and a shared semantic representation.
Off-Policy Reinforcement Learning for Efficient and Effective GAN Architecture Search
In this paper, we introduce a new reinforcement learning (RL) based neural architecture search (NAS) methodology for effective and efficient generative adversarial network (GAN) architecture search.
Ranked #12 on
Image Generation
on STL-10
The Heterogeneity Hypothesis: Finding Layer-Wise Differentiated Network Architectures
Based on that, we articulate the heterogeneity hypothesis: with the same training protocol, there exists a layer-wise differentiated network architecture (LW-DNA) that can outperform the original network with regular channel configurations but with a lower level of model complexity.
Analogical Image Translation for Fog Generation
AIT achieves this zero-shot image translation capability by coupling a supervised training scheme in the synthetic domain, a cycle consistency strategy in the real domain, an adversarial training scheme between the two domains, and a novel network design.
Deeply Aligned Adaptation for Cross-domain Object Detection
Cross-domain object detection has recently attracted more and more attention for real-world applications, since it helps build robust detectors adapting well to new environments.
Unbiased Mean Teacher for Cross-domain Object Detection
We reveal that there often exists a considerable model bias for the simple mean teacher (MT) model in cross-domain scenarios, and eliminate the model bias with several simple yet highly effective strategies.
Ensemble Methods to Distinguish Mainland and Taiwan Chinese
This paper describes the IUCL system at VarDial 2019 evaluation campaign for the task of discriminating between Mainland and Taiwan variation of mandarin Chinese.
NULI at SemEval-2019 Task 6: Transfer Learning for Offensive Language Detection using Bidirectional Transformers
Transfer learning and domain adaptive learning have been applied to various fields including computer vision (e. g., image recognition) and natural language processing (e. g., text classification).
Semi-Supervised Learning by Augmented Distribution Alignment
We reveal that an essential sampling bias exists in semi-supervised learning due to the limited number of labeled samples, which often leads to a considerable empirical distribution mismatch between labeled data and unlabeled data.
Known-class Aware Self-ensemble for Open Set Domain Adaptation
Particularly, in open set domain adaptation, we allow the classes from the source and target domains to be partially overlapped.
Sliced Wasserstein Generative Models
In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions.
Ranked #1 on
Video Generation
on TrailerFaces
DLOW: Domain Flow for Adaptation and Generalization
In this work, we present a domain flow generation(DLOW) model to bridge two different domains by generating a continuous sequence of intermediate domains flowing from one domain to the other.
Learning Semantic Segmentation from Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach
In this work, we take the advantage of additional geometric information from synthetic data, a powerful yet largely neglected cue, to bridge the domain gap.
Dividing and Aggregating Network for Multi-view Action Recognition
We then train view-specific action classifiers based on the view-specific representation for each view and a view classifier based on the shared representation at lower layers.
Collaborative and Adversarial Network for Unsupervised Domain Adaptation
In this paper, we propose a new unsupervised domain adaptation approach called Collaborative and Adversarial Network (CAN) through domain-collaborative and domain-adversarial training of neural networks.
Detecting Syntactic Features of Translated Chinese
We present a machine learning approach to distinguish texts translated to Chinese (by humans) from texts originally written in Chinese, with a focus on a wide range of syntactic features.
Ensemble Manifold Segmentation for Model Distillation and Semi-supervised Learning
We mitigate this by introducing ensemble manifold segmentation (EMS).
Domain Adaptive Faster R-CNN for Object Detection in the Wild
The results demonstrate the effectiveness of our proposed approach for robust object detection in various domain shift scenarios.
ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenes
To this end, we propose a new reality oriented adaptation approach for urban scene semantic segmentation by learning from synthetic data.
Appearance-and-Relation Networks for Video Classification
Specifically, SMART blocks decouple the spatiotemporal learning module into an appearance branch for spatial modeling and a relation branch for temporal modeling.
Ranked #50 on
Action Recognition
on UCF101
Gender Prediction for Chinese Social Media Data
The goal of this project is to predict the gender of users based on their posts on Weibo, a Chinese micro-blogging platform.
Classifier Stacking for Native Language Identification
We also report the performance of each feature type, as well as the best features of a type.
WebVision Database: Visual Learning and Understanding from Web Data
Our new WebVision database and relevant studies in this work would benefit the advance of learning state-of-the-art visual models with minimum supervision based on web data.
Deep Domain Adaptation by Geodesic Distance Minimization
Our work builds on the recently proposed Deep CORAL method, which proposed to train a convolutional neural network and simultaneously minimize the Euclidean distance of convariance matrices between the source and target domains.
Sliced Wasserstein Generative Models
In generative modeling, the Wasserstein distance (WD) has emerged as a useful metric to measure the discrepancy between generated and real data distributions.
WebVision Challenge: Visual Learning and Understanding With Web Data
The 2017 WebVision challenge consists of two tracks, the image classification task on WebVision test set, and the transfer learning task on PASCAL VOC 2012 dataset.
Approximate Nearest Neighbor Search on High Dimensional Data --- Experiments, Analyses, and Improvement (v1.0)
Approximate Nearest neighbor search (ANNS) is fundamental and essential operation in applications from many domains, such as databases, machine learning, multimedia, and computer vision.
Databases
Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation
In this paper, we propose a novel unsupervised domain adaptation algorithm based on deep learning for visual object recognition.
Fast Algorithms for Linear and Kernel SVM+
The SVM+ approach has shown excellent performance in visual recognition tasks for exploiting privileged information in the training data.
Multi-View Domain Generalization for Visual Recognition
Considering the recent works show the domain generalization capability can be enhanced by fusing multiple SVM classifiers, we build upon exemplar SVMs to learn a set of SVM classifiers by using one positive sample and all negative samples in the source domain each time.
FaLRR: A Fast Low Rank Representation Solver
In this paper, we develop a fast LRR solver called FaLRR, by reformulating LRR as a new optimization problem with regard to factorized data (which is obtained by skinny SVD of the original data matrix).
Visual Recognition by Learning From Web Data: A Weakly Supervised Domain Generalization Approach
In this work, we formulate a new weakly supervised domain generalization problem for the visual recognition task by using loosely labeled web images/videos as training data.
Recognizing RGB Images by Learning from RGB-D Data
In this work, we propose a new framework for recognizing RGB images captured by the conventional cameras by leveraging a set of labeled RGB-D data, in which the depth features can be additionally extracted from the depth images.
Fusing Robust Face Region Descriptors via Multiple Metric Learning for Face Recognition in the Wild
Spatial-Temporal Face Region Descriptor, STFRD) for images (resp.
