The new transferability measure accurately quantifies the inclination of a target example to the open classes.
Ranked #2 on Universal Domain Adaptation on DomainNet
This paper explores a new research problem of unsupervised transfer learning across multiple spatiotemporal prediction tasks.
Finally, we further extend the localized discrepancies for achieving super transfer and derive generalization bounds that could be even more sample-efficient on source domain.
In this paper, we delve into the open problem of Calibration in DA, which is extremely challenging due to the coexistence of domain shift and the lack of target labels.
It can be characterized as (1) a non-adversarial DA method without explicitly deploying domain alignment, enjoying faster convergence speed; (2) a versatile approach that can handle four existing scenarios: Closed-Set, Partial-Set, Multi-Source, and Multi-Target DA, outperforming the state-of-the-art methods in these scenarios, especially on one of the largest and hardest datasets to date (7. 3% on DomainNet).
Ranked #2 on Multi-target Domain Adaptation on DomainNet
Deep neural networks (DNNs) excel at learning representations when trained on large-scale datasets.
Before sufficient training data is available, fine-tuning neural networks pre-trained on large-scale datasets substantially outperforms training from random initialization.
Despite the popularity of these common beliefs, experiments suggest that they are insufficient in explaining the general effectiveness of lrDecay in training modern neural networks that are deep, wide, and nonconvex.
Process model extraction (PME) is a recently emerged interdiscipline between natural language processing (NLP) and business process management (BPM), which aims to extract process models from textual descriptions.
In addition, for unordered medical activity set, existing medical RL methods utilize a simple pooling strategy, which would result in indistinguishable contributions among the activities for learning.
Under the condition that target labels are unknown, the key challenge of PDA is how to transfer relevant examples in the shared classes to promote positive transfer, and ignore irrelevant ones in the specific classes to mitigate negative transfer.
Ranked #3 on Partial Domain Adaptation on ImageNet-Caltech
We propose Deep Triplet Quantization (DTQ), a novel approach to learning deep quantization models from the similarity triplets.
Ranked #1 on Quantization on CIFAR-10
In this paper, we propose a novel framework, FANE, to integrate structure and property information in the network embedding process.
Rev2Net is shown to be effective on the classic action recognition task.
Natural spatiotemporal processes can be highly non-stationary in many ways, e. g. the low-level non-stationarity such as spatial correlations or temporal dependencies of local pixel values; and the high-level variations such as the accumulation, deformation or dissipation of radar echoes in precipitation forecasting.
Ranked #2 on Video Prediction on Human3.6M
We apply three BLR models with different prescriptions of BLR clouds distributions and find that the best model for fitting the data of Mrk 142 is a two-zone BLR model, consistent with the theoretical BLR model surrounding slim accretion disks.
Astrophysics of Galaxies Instrumentation and Methods for Astrophysics
Recent advances in deep domain adaptation reveal that adversarial learning can be embedded into deep networks to learn transferable features that reduce distribution discrepancy between the source and target domains.
Ranked #18 on Domain Adaptation on Office-31
Deep hashing enables image retrieval by end-to-end learning of deep representations and hash codes from training data with pairwise similarity information.
Extensive experiments demonstrate that CMHH can generate highly concentrated hash codes and achieve state-of-the-art cross-modal retrieval performance for both hash lookups and linear scan scenarios on three benchmark datasets, NUS-WIDE, MIRFlickr-25K, and IAPR TC-12.
We present Partial Adversarial Domain Adaptation (PADA), which simultaneously alleviates negative transfer by down-weighing the data of outlier source classes for training both source classifier and domain adversary, and promotes positive transfer by matching the feature distributions in the shared label space.
Predicting future frames in videos remains an unsolved but challenging problem.
Ranked #3 on Pose Prediction on Filtered NTU RGB+D
Due to its computation efficiency and retrieval quality, hashing has been widely applied to approximate nearest neighbor search for large-scale image retrieval, while deep hashing further improves the retrieval quality by end-to-end representation learning and hash coding.
The main idea is to augment the training data with nearly real images synthesized from a new Pair Conditional Wasserstein GAN (PC-WGAN) conditioned on the pairwise similarity information.
Existing work on deep hashing assumes that the database in the target domain is identically distributed with the training set in the source domain.
The core of this network is a new Spatiotemporal LSTM (ST-LSTM) unit that extracts and memorizes spatial and temporal representations simultaneously.
Ranked #3 on Video Prediction on Human3.6M
Hence, we formulate a new problem, called "fine-grained pattern matching", which allows users to specify varied granularities of matching deviation to different segments of a given pattern, and fuzzy regions for adaptive breakpoints determination between consecutive segments.
This paper presents a compact coding solution with a focus on the deep learning to quantization approach, which improves retrieval quality by end-to-end representation learning and compact encoding and has already shown the superior performance over the hashing solutions for similarity retrieval.
Instead of simply discarding anomalies, we propose to (iteratively) repair them in time series data, by creatively bonding the beauty of temporal nature in anomaly detection with the widely considered minimum change principle in data repairing.
Adversarial learning has been embedded into deep networks to learn disentangled and transferable representations for domain adaptation.
Ranked #5 on Domain Adaptation on USPS-to-MNIST
Learning to hash has been widely applied to approximate nearest neighbor search for large-scale multimedia retrieval, due to its computation efficiency and retrieval quality.
Deep networks have been successfully applied to learn transferable features for adapting models from a source domain to a different target domain.
Ranked #1 on Unsupervised Domain Adaptation on Office-Home
This paper presents a Correlation Hashing Network (CHN) approach to cross-modal hashing, which jointly learns good data representation tailored to hash coding and formally controls the quantization error.
In this paper, we propose a new approach to domain adaptation in deep networks that can jointly learn adaptive classifiers and transferable features from labeled data in the source domain and unlabeled data in the target domain.
With benefits of low storage costs and high query speeds, hashing methods are widely researched for efficiently retrieving large-scale data, which commonly contains multiple views, e. g. a news report with images, videos and texts.
Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation.
Ranked #2 on Unsupervised Domain Adaptation on Office-Home
Visual domain adaptation, which learns an accurate classifier for a new domain using labeled images from an old domain, has shown promising value in computer vision yet still been a challenging problem.
In this paper, we propose a Transfer Sparse Coding (TSC) approach to construct robust sparse representations for classifying cross-distribution images accurately.
Though widely utilized for facilitating image management, user-provided image tags are usually incomplete and insufficient to describe the whole semantic content of corresponding images, resulting in performance degradations in tag-dependent applications and thus necessitating effective tag completion methods.