Moreover, two new datasets (Tamper-Syn2k and Tamper-Scene) are proposed to fill the blank of public evaluation datasets.
We consider knowledge transfer and retention of the learning on growing snapshots of a KG without having to learn embeddings from scratch.
One-shot neural architecture search (NAS) substantially improves the search efficiency by training one supernet to estimate the performance of every possible child architecture (i. e., subnet).
In this paper, we argue that the limited capacity of language models comes from 1) implicit language modeling; 2) unidirectional feature representation; and 3) language model with noise input.
In this paper, starting from the intuition that discovering intents could be beneficial to the identification of the known intents, we propose a probabilistic framework for discovering intents where intent assignments are treated as latent variables.
Most existing methods of Out-of-Domain (OOD) intent classification, which rely on extensive auxiliary OOD corpora or specific training paradigms, are underdeveloped in the underlying principle that the models should have differentiated confidence in In- and Out-of-domain intent.
In this paper, we propose an end-to-end Hierarchical and Progressive Attention Matting Network (HAttMatting++), which can better predict the opacity of the foreground from single RGB images without additional input.
This paper reviews recent deep-learning-based matting research and conceives our wider and higher motivation for image matting.
First, we attempt to bridge the characteristic gap between different levels of features by developing a Discriminability Enhancement (DE) module which enables level-specific features to be a more discriminative representation, alleviating the features incompatibility for fusion.
To solve these tasks efficiently, we propose a novel self-guided continual RL framework, RelayHER (RHER).
To avoid retraining an entire model on the whole KGs whenever new entities and triples come, we present a continual alignment method for this task.
Transformers have made progress in miscellaneous tasks, but suffer from quadratic computational and memory complexities.
Acquiring the most representative examples via active learning (AL) can benefit many data-dependent computer vision tasks by minimizing efforts of image-level or pixel-wise annotations.
Such operation guides the vision model to use not only the visual texture of characters, but also the linguistic information in visual context for recognition when the visual cues are confused (e. g. occlusion, noise, etc.).
Jointly exploiting multiple different yet complementary domain information has been proven to be an effective way to perform robust object tracking.
However, there exists two problems: 1) the implicit erasure guidance causes the excessive erasure to non-text areas; 2) the one-stage erasure lacks the exhaustive removal of text region.
In this technical report, we present our solution of KDD Cup 2021 OGB Large-Scale Challenge - PCQM4M-LSC Track.
Recently, deep convolutional neural networks (CNNs) have been widely explored in single image super-resolution (SISR) and contribute remarkable progress.
Additionally, based on the ensemble of iterative predictions, we propose a self-training method which can learn from unlabeled images effectively.
Image matting is a long-standing problem in computer graphics and vision, mostly identified as the accurate estimation of the foreground in input images.
We propose CheckDP, the first automated and integrated approach for proving or disproving claims that a mechanism is differentially private.
Programming Languages D.3.1
Then a novel Local Orthogonal Texture-aware Module (LOTM) models the local texture information of proposal features in two orthogonal directions and represents text region with a set of contour points.
Our results show that object detection can help improve the accuracy of some skin disease classes.
Different from the existing end-to-end benchmarks which only present the training time, We try to investigate the impact of hardware, vendor's software library, and deep learning framework on the performance and energy consumption of AI training.
We show that it can also release for free the noisy gap between the approximate maximizer and runner-up.
Sometimes, combining those two requires substantial changes to program logics: one recent paper is able to verify Report Noisy Max automatically, but it involves a complex verification system using customized program logics and verifiers.
Programming Languages D.2.4
Current methods that use AllGather to accumulate the sparse gradients have a communication complexity of $O(kP)$, where $P$ is the number of workers, which is inefficient on low bandwidth networks with a large number of workers.
The widespread acceptance of differential privacy has led to the publication of many sophisticated algorithms for protecting privacy.
Cryptography and Security