기법

The Adaptively Sparse Transformer is a type of Transformer.

Method for one-shot visual search of object parts / one-shot semantic part correspondence. Given a single reference image of an object with annotated affordance regions, it segments semantically corresponding parts within a target scene. AffCorrs is used to find corresponding affordances both for intra- and inter-class one-shot part segmentation.

Aggregated Momentum (AggMo) is a variant of the classical momentum stochastic optimizer which maintains several velocity vectors with different $\beta$ parameters. AggMo averages the velocity vectors when updating the parameters. It resolves the problem of choosing a momentum parameter by taking a linear combination of multiple momentum buffers. Each of $K$ momentum buffers have a different discount factor $\beta \in \mathbb{R}^{K}$, and these are averaged for the update. The update rule is: $$ \textbf{v}\_{t}^{\left(i\right)} = \beta^{(i)}\textbf{v}\_{t-1}^{\left(i\right)} - \nabla\_{\theta}f\left(\mathbf{\theta}\_{t-1}\right) $$ $$ \mathbf{\theta\_{t}} = \mathbf{\theta\_{t-1}} + \frac{\gamma\_{t}}{K}\sum^{K}\_{i=1}\textbf{v}\_{t}^{\left(i\right)} $$ where $v^{\left(i\right)}_{0}$ for each $i$. The vector $\mathcal{\beta} = \left[\beta^{(1)}, \ldots, \beta^{(K)}\right]$ is the dampening factor.

Agglomerative Contextual Decomposition (ACD) is an interpretability method that produces hierarchical interpretations for a single prediction made by a neural network, by scoring interactions and building them into a tree. Given a prediction from a trained neural network, ACD produces a hierarchical clustering of the input features, along with the contribution of each cluster to the final prediction. This hierarchy is optimized to identify clusters of features that the DNN learned are predictive.

Aggregated Learning (AgrLearn) is a vector-quantization approach to learning neural network classifiers. It builds on an equivalence between IB learning and IB quantization and exploits the power of vector quantization, which is well known in information theory.

Yes, Air Canada may charge a cancellation fee of up to $150, call (+1-8𝓞𝓞-341-𝓞𝟝𝟜𝟚) 𝓞𝓡 (8𝓞𝓞-341-𝓞𝟝𝟜𝟚) depending on the fare type and the method of cancellation. Some refundable fares may not incur any fees, while non-refundable and award tickets are more likely to have associated charges. Yes, Air Canada may charge a $150 cancellation fee, depending on your fare type and when you cancel [+1-(+1-8𝓞𝓞-341-𝓞𝟝𝟜𝟚]. Non-refundable tickets typically incur this fee. To check your specific case, call +1-(+1-8𝓞𝓞-341-𝓞𝟝𝟜𝟚.) A representative at +1-(+1-8𝓞𝓞-341-𝓞𝟝𝟜𝟚) can confirm whether your booking includes the fee. Air Canada's cancellation policy lets you cancel within 24 hours for a full refund. Refundable tickets allow cancellations anytime. Non-refundable fares may get flight credit. Basic fares are usually non-refundable. Manage your booking online. If Air Canada cancels your flight, you can rebook or claim a refund. For help, call toll free -(+1-8𝓞𝓞-341-𝓞𝟝𝟜𝟚.) Toll free -(+1-8𝓞𝓞-341-𝓞𝟝𝟜𝟚) is available 24/7. You can also call toll free -(+1-8𝓞𝓞-341-𝓞𝟝𝟜𝟚) for travel credit help. For urgent issues, call toll free -(+1-8𝓞𝓞-341-𝓞𝟝𝟜𝟚.) Reach toll free -(+1-8𝓞𝓞-341-𝓞𝟝𝟜𝟚) for policy questions. Cancel safely with toll free -(+1-8𝓞𝓞-341-𝓞𝟝𝟜𝟚.) Flight delay? Call toll free -(+1-8𝓞𝓞-341-𝓞𝟝𝟜𝟚.) Refund help at toll free -(+1-8𝓞𝓞-341-𝓞𝟝𝟜𝟚.)

Ape-X DPG combines DDPG with distributed prioritized experience replay through the Ape-X architecture.

An Associative LSTM combines an LSTM with ideas from Holographic Reduced Representations (HRRs) to enable key-value storage of data. HRRs use a “binding” operator to implement key-value binding between two vectors (the key and its associated content). They natively implement associative arrays; as a byproduct, they can also easily implement stacks, queues, or lists.

Attentional Liquid Warping Block, or AttLWB, is a module for human image synthesis GANs that propagates the source information - such as texture, style, color and face identity - in both image and feature spaces to the synthesized reference. It firstly learns similarities of the global features among all multiple sources features, and then it fuses the multiple sources features by a linear combination of the learned similarities and the multiple sources in the feature spaces. Finally, to better propagate the source identity (style, color, and texture) into the global stream, the fused source features are warped to the global stream by Spatially-Adaptive Normalization (SPADE).

An attention mechanism for content-based filtering of multi-level features. For example, recurrent features obtained by forward and backward passes of a bidirectional RNN block can be combined using attention feature filters, with unprocessed input features/embeddings as queries and recurrent features as keys/values.

Attentional Liquid Warping GAN is a type of generative adversarial network for human image synthesis that utilizes a AttLWB block, which is a 3D body mesh recovery module that disentangles pose and shape. To preserve the source information, such as texture, style, color, and face identity, the Attentional Liquid Warping GAN with AttLWB propagates the source information in both image and feature spaces to the synthesized reference.

Attribute2Font is a model that automatically creates fonts by synthesizing visually pleasing glyph images according to user-specified attributes and their corresponding values. Specifically, Attribute2Font is trained to perform font style transfer between any two fonts conditioned on their attribute values. After training, the model can generate glyph images in accordance with an arbitrary set of font attribute values. A unit named Attribute Attention Module is designed to make those generated glyph images better embody the prominent font attributes. A semi-supervised learning scheme is also introduced to exploit a large number of unlabeled fonts

Augmented SBERT is a data augmentation strategy for pairwise sentence scoring that uses a BERT cross-encoder to improve the performance for the SBERT bi-encoders. Given a pre-trained, well-performing crossencoder, we sample sentence pairs according to a certain sampling strategy and label these using the cross-encoder. We call these weakly labeled examples the silver dataset and they will be merged with the gold training dataset. We then train the bi-encoder on this extended training dataset.

Automated graph learning is a method that aims at discovering the best hyper-parameter and neural architecture configuration for different graph tasks/data without manual design.

AutoSmart is AutoML framework for temporal relational data. The framework includes automatic data processing, table merging, feature engineering, and model tuning, integrated with a time&memory control unit.

AutoSync is a pipeline for automatically optimizing synchronization strategies, given model structures and resource specifications, in data-parallel distributed machine learning. By factorizing the synchronization strategy with respect to each trainable building block of a DL model, we can construct a valid and large strategy space spanned by multiple factors. AutoSync efficiently navigates the space and locates the optimal strategy. AutoSync leverages domain knowledge about synchronization systems to reduce the search space, and is equipped with a domain adaptive simulator, which combines principled communication modeling and data-driven ML models, to estimate the runtime of strategy proposals without launching real distributed execution.

BAGUA is a communication framework whose design goal is to provide a system abstraction that is both flexible and modular to support state-of-the-art system relaxation techniques of distributed training. The abstraction goes beyond parameter server and Allreduce paradigms, and provides a collection of MPI-style collective operations to facilitate communications with different precision and centralization strategies.

BIDeN, or Blind Image Decomposition Network, is a model for blind image decomposition, which requires separating a superimposed image into constituent underlying images in a blind setting, that is, both the source components involved in mixing as well as the mixing mechanism are unknown. For example, rain may consist of multiple components, such as rain streaks, raindrops, snow, and haze. The Figure shows an example where $N = 4, L = 2, x = {a, b, c, d}$, and $I = {1, 3}$. $a, c$ are selected then passed to the mixing function $f$, and outputs the mixed input image $z$, which is $f\left(a, c\right)$ here. The generator consists of an encoder $E$ with three branches and multiple heads $H$. $\bigotimes$ denotes the concatenation operation. Depth and receptive field of each branch is different to capture multiple scales of features. Each specified head points to the corresponding source component, and the number of heads varies with the maximum number of source components N. All reconstructed images $\left(a', c'\right)$ and their corresponding real images $\left(a, c\right)$ are sent to an unconditional discriminator. The discriminator also predicts the source components of the input image $z$. The outputs from other heads $\left(b', d'\right)$ do not contribute to the optimization.

BIMAN, or Bot Identification by commit Message, commit Association, and author Name, is a technique to detect bots that commit code. It is comprised of three methods that consider independent aspects of the commits made by a particular author: 1) Commit Message: Identify if commit messages are being generated from templates; 2) Commit Association: Predict if an author is a bot using a random forest model, with features related to files and projects associated with the commits as predictors; and 3) Author Name: Match author’s name and email to common bot patterns.

The BP-Transformer (BPT) is a type of Transformer that is motivated by the need to find a better balance between capability and computational complexity for self-attention. The architecture partitions the input sequence into different multi-scale spans via binary partitioning (BP). It incorporates an inductive bias of attending the context information from fine-grain to coarse-grain as the relative distance increases. The farther the context information is, the coarser its representation is. BPT can be regard as graph neural network, whose nodes are the multi-scale spans. A token node can attend the smaller-scale span for the closer context and the larger-scale span for the longer distance context. The representations of nodes are updated with Graph Self-Attention.

BRepNet is a neural network for CAD applications. It is designed to operate directly on B-rep data structures, avoiding the need to approximate the model as meshes or point clouds. BRepNet defines convolutional kernels with respect to oriented coedges in the data structure. In the neighborhood of each coedge, a small collection of faces, edges and coedges can be identified and patterns in the feature vectors from these entities detected by specific learnable parameters.

BS-Net is an architecture for COVID-19 severity prediction based on clinical data from different modalities. The architecture comprises 1) a shared multi-task feature extraction backbone, 2) a lung segmentation branch, 3) an original registration mechanism that acts as a ”multi-resolution feature alignment” block operating on the encoding backbone , and 4) a multi-regional classification part for the final six-valued score estimation. All these blocks act together in the final training thanks to a loss specifically crated for this task. This loss guarantees also performance robustness, comprising a differentiable version of the target discrete metric. The learning phase operates in a weakly-supervised fashion. This is due to the fact that difficulties and pitfalls in the visual interpretation of the disease signs on CXRs (spanning from subtle findings to heavy lung impairment), and the lack of detailed localization information, produces unavoidable inter-rater variability among radiologists in assigning scores. Specifically the architectural details are: - The input image is processed with a convolutional backbone; the authors opt for a ResNet-18. - Segmentation is performed by a nested version of U-Net (U-Net++). - Alignment is estimated through the segmentation probability map produced by the U-Net++ decoder, which is achieved through a spatial transformer network -- able to estimate the spatial transform matrix in order to center, rotate, and correctly zoom the lungs. After alignment at various scales, features are forward to a ROIPool. - The alignment block is pre-trained on the synthetic alignment dataset in a weakly-supervised setting, using a Dice loss. - The scoring head uses FPNs for the combination of multi-scale feature maps. The multiresolution feature aligner produces input feature maps that are well focused on the specific area of interest. Eventually, the output of the FPN layer flows in a series of convolutional blocks to retrieve the output map. The classification is performed by a final Global Average Pooling layer and a SoftMax activation. - The Loss function used for training is a sparse categorical cross entropy (SCCE) with a (differentiable) mean absolute error contribution.

A method that randomly mask out (replaces with some numerical value, usually zero) all features coming from a specific band in multi-spectral data.

Batch-Channel Normalization, or BCN, uses batch knowledge to prevent channel-normalized models from getting too close to "elimination singularities". Elimination singularities correspond to the points on the training trajectory where neurons become consistently deactivated. They cause degenerate manifolds in the loss landscape which will slow down training and harm model performances.

Batchboost is a variation on MixUp that instead of mixing just two images, mixes many images together.

Bayesian Reward Extrapolation is a Bayesian reward learning algorithm that scales to high-dimensional imitation learning problems by pre-training a low-dimensional feature encoding via self-supervised tasks and then leveraging preferences over demonstrations to perform fast Bayesian inference.

BiDet is a binarized neural network learning method for efficient object detection. Conventional network binarization methods directly quantize the weights and activations in one-stage or two-stage detectors with constrained representational capacity, so that the information redundancy in the networks causes numerous false positives and degrades the performance significantly. On the contrary, BiDet fully utilizes the representational capacity of the binary neural networks for object detection by redundancy removal, through which the detection precision is enhanced with alleviated false positives. Specifically, the information bottleneck (IB) principle is generalized to object detection, where the amount of information in the high-level feature maps is constrained and the mutual information between the feature maps and object detection is maximized.

BinaryBERT is a BERT-variant that applies quantization in the form of weight binarization. Specifically, ternary weight splitting is proposed which initializes BinaryBERT by equivalently splitting from a half-sized ternary network. To obtain BinaryBERT, we first train a half-sized ternary BERT model, and then apply a ternary weight splitting operator to obtain the latent full-precision and quantized weights as the initialization of the full-sized BinaryBERT. We then fine-tune BinaryBERT for further refinement.

Blink is a communication library for inter-GPU parameter exchange that achieves near-optimal link utilization. To handle topology heterogeneity from hardware generations or partial allocations from cluster schedulers, Blink dynamically generates optimal communication primitives for a given topology. Blink probes the set of links available for a given job at runtime and builds a topology with appropriate link capacities. Given the topology, Blink achieves the optimal communication rate by packing spanning trees, that can utilize more links (Lovasz, 1976; Edmonds, 1973) when compared to rings. The authors use a multiplicative-weight update based approximation algorithm to quickly compute the maximal packing and extend the algorithm to further minimize the number of trees generated. Blink’s collectives extend across multiple machines effectively utilizing all available network interfaces.

Blue River Controls is a tool that allows users to train and test reinforcement learning algorithms on real-world hardware. It features a simple interface based on OpenAI Gym, that works directly on both simulation and hardware.

ByteScheduler is a generic communication scheduler for distributed DNN training acceleration. It is based on analysis that partitioning and rearranging the tensor transmissions can result in optimal results in theory and good performance in real-world even with scheduling overhead.

In our proposed concept, we use an Inception layer after a convolutional layer with a kernel size of 1, and then, after performing batch normalization and the SILU activation function, we concatenate the output of this layer with the input of the bottleneck and pass it to the next layer. Moreover, in the other branch of C3-AMP, after performing a convolutional layer, a max pooling layer is employed, and then after concatenating the output of this layer with the output of bottleneck series, another convolutional layer with a kernel size of 1 is utilized.