기법

Activation Normalization is a type of normalization used for flow-based generative models; specifically it was introduced in the GLOW architecture. An ActNorm layer performs an affine transformation of the activations using a scale and bias parameter per channel, similar to batch normalization. These parameters are initialized such that the post-actnorm activations per-channel have zero mean and unit variance given an initial minibatch of data. This is a form of data dependent initilization. After initialization, the scale and bias are treated as regular trainable parameters that are independent of the data.

UNet++ is an architecture for semantic segmentation based on the U-Net. Through the use of densely connected nested decoder sub-networks, it enhances extracted feature processing and was reported by its authors to outperform the U-Net in Electron Microscopy (EM), Cell, Nuclei, Brain Tumor, Liver and Lung Nodule medical image segmentation tasks.

Pythia is a suite of decoder-only autoregressive language models all trained on public data seen in the exact same order and ranging in size from 70M to 12B parameters. The model architecture and hyperparameters largely follow GPT-3, with a few notable deviations based on recent advances in best practices for large scale language modeling.

Soft Actor Critic, or SAC, is an off-policy actor-critic deep RL algorithm based on the maximum entropy reinforcement learning framework. In this framework, the actor aims to maximize expected reward while also maximizing entropy. That is, to succeed at the task while acting as randomly as possible. Prior deep RL methods based on this framework have been formulated as Q-learning methods. SAC combines off-policy updates with a stable stochastic actor-critic formulation. The SAC objective has a number of advantages. First, the policy is incentivized to explore more widely, while giving up on clearly unpromising avenues. Second, the policy can capture multiple modes of near-optimal behavior. In problem settings where multiple actions seem equally attractive, the policy will commit equal probability mass to those actions. Lastly, the authors present evidence that it improves learning speed over state-of-art methods that optimize the conventional RL objective function.

A3C, Asynchronous Advantage Actor Critic, is a policy gradient algorithm in reinforcement learning that maintains a policy $\pi\left(a\_{t}\mid{s}\_{t}; \theta\right)$ and an estimate of the value function $V\left(s\_{t}; \theta\_{v}\right)$. It operates in the forward view and uses a mix of $n$-step returns to update both the policy and the value-function. The policy and the value function are updated after every $t\_{\text{max}}$ actions or when a terminal state is reached. The update performed by the algorithm can be seen as $\nabla\_{\theta{'}}\log\pi\left(a\_{t}\mid{s\_{t}}; \theta{'}\right)A\left(s\_{t}, a\_{t}; \theta, \theta\_{v}\right)$ where $A\left(s\_{t}, a\_{t}; \theta, \theta\_{v}\right)$ is an estimate of the advantage function given by: $$\sum^{k-1}\_{i=0}\gamma^{i}r\_{t+i} + \gamma^{k}V\left(s\_{t+k}; \theta\_{v}\right) - V\left(s\_{t}; \theta\_{v}\right)$$ where $k$ can vary from state to state and is upper-bounded by $t\_{max}$. The critics in A3C learn the value function while multiple actors are trained in parallel and get synced with global parameters every so often. The gradients are accumulated as part of training for stability - this is like parallelized stochastic gradient descent. Note that while the parameters $\theta$ of the policy and $\theta\_{v}$ of the value function are shown as being separate for generality, we always share some of the parameters in practice. We typically use a convolutional neural network that has one softmax output for the policy $\pi\left(a\_{t}\mid{s}\_{t}; \theta\right)$ and one linear output for the value function $V\left(s\_{t}; \theta\_{v}\right)$, with all non-output layers shared.

Training a denoiser on signals gives you a powerful prior over this signal that you can then use to sample examples of this signal.

A Sparse Autoencoder is a type of autoencoder that employs sparsity to achieve an information bottleneck. Specifically the loss function is constructed so that activations are penalized within a layer. The sparsity constraint can be imposed with L1 regularization or a KL divergence between expected average neuron activation to an ideal distribution $p$. Image: Jeff Jordan. Read his blog post (click) for a detailed summary of autoencoders.

XLM is a Transformer based architecture that is pre-trained using one of three language modelling objectives: 1. Causal Language Modeling - models the probability of a word given the previous words in a sentence. 2. Masked Language Modeling - the masked language modeling objective of BERT. 3. Translation Language Modeling - a (new) translation language modeling objective for improving cross-lingual pre-training. The authors find that both the CLM and MLM approaches provide strong cross-lingual features that can be used for pretraining models.

Activation Regularization (AR), or $L\_{2}$ activation regularization, is regularization performed on activations as opposed to weights. It is usually used in conjunction with RNNs. It is defined as: $$\alpha{L}\_{2}\left(m\circ{h\_{t}}\right) $$ where $m$ is a dropout mask used by later parts of the model, $L\_{2}$ is the $L\_{2}$ norm, and $h_{t}$ is the output of an RNN at timestep $t$, and $\alpha$ is a scaling coefficient. When applied to the output of a dense layer, AR penalizes activations that are substantially away from 0, encouraging activations to remain small.

Sarsa is an on-policy TD control algorithm: $$Q\left(S\_{t}, A\_{t}\right) \leftarrow Q\left(S\_{t}, A\_{t}\right) + \alpha\left[R_{t+1} + \gamma{Q}\left(S\_{t+1}, A\_{t+1}\right) - Q\left(S\_{t}, A\_{t}\right)\right] $$ This update is done after every transition from a nonterminal state $S\_{t}$. if $S\_{t+1}$ is terminal, then $Q\left(S\_{t+1}, A\_{t+1}\right)$ is defined as zero. To design an on-policy control algorithm using Sarsa, we estimate $q\_{\pi}$ for a behaviour policy $\pi$ and then change $\pi$ towards greediness with respect to $q\_{\pi}$. Source: Sutton and Barto, Reinforcement Learning, 2nd Edition

Please enter a description about the method here

Group Normalization is a normalization layer that divides channels into groups and normalizes the features within each group. GN does not exploit the batch dimension, and its computation is independent of batch sizes. In the case where the group size is 1, it is equivalent to Instance Normalization. As motivation for the method, many classical features like SIFT and HOG had group-wise features and involved group-wise normalization. For example, a HOG vector is the outcome of several spatial cells where each cell is represented by a normalized orientation histogram. Formally, Group Normalization is defined as: $$ \mu\_{i} = \frac{1}{m}\sum\_{k\in\mathcal{S}\_{i}}x\_{k} $$ $$ \sigma^{2}\_{i} = \frac{1}{m}\sum\_{k\in\mathcal{S}\_{i}}\left(x\_{k}-\mu\_{i}\right)^{2} $$ $$ \hat{x}\_{i} = \frac{x\_{i} - \mu\_{i}}{\sqrt{\sigma^{2}\_{i}+\epsilon}} $$ Here $x$ is the feature computed by a layer, and $i$ is an index. Formally, a Group Norm layer computes $\mu$ and $\sigma$ in a set $\mathcal{S}\_{i}$ defined as: $\mathcal{S}\_{i} = ${$k \mid k\_{N} = i\_{N} ,\lfloor\frac{k\_{C}}{C/G}\rfloor = \lfloor\frac{I\_{C}}{C/G}\rfloor $}. Here $G$ is the number of groups, which is a pre-defined hyper-parameter ($G = 32$ by default). $C/G$ is the number of channels per group. $\lfloor$ is the floor operation, and the final term means that the indexes $i$ and $k$ are in the same group of channels, assuming each group of channels are stored in a sequential order along the $C$ axis.

SwaV, or Swapping Assignments Between Views, is a self-supervised learning approach that takes advantage of contrastive methods without requiring to compute pairwise comparisons. Specifically, it simultaneously clusters the data while enforcing consistency between cluster assignments produced for different augmentations (or views) of the same image, instead of comparing features directly as in contrastive learning. Simply put, SwaV uses a swapped prediction mechanism where we predict the cluster assignment of a view from the representation of another view.

YOLOv2, or YOLO9000, is a single-stage real-time object detection model. It improves upon YOLOv1 in several ways, including the use of Darknet-19 as a backbone, batch normalization, use of a high-resolution classifier, and the use of anchor boxes to predict bounding boxes, and more.

ERNIE is a transformer-based model consisting of two stacked modules: 1) textual encoder and 2) knowledgeable encoder, which is responsible to integrate extra token-oriented knowledge information into textual information. This layer consists of stacked aggregators, designed for encoding both tokens and entities as well as fusing their heterogeneous features. To integrate this layer of enhancing representations via knowledge, a special pre-training task is adopted for ERNIE - it involves randomly masking token-entity alignments and training the model to predict all corresponding entities based on aligned tokens (aka denoising entity auto-encoder).

PEGASUS proposes a transformer-based model for abstractive summarization. It uses a special self-supervised pre-training objective called gap-sentences generation (GSG) that's designed to perform well on summarization-related downstream tasks. As reported in the paper, "both GSG and MLM are applied simultaneously to this example as pre-training objectives. Originally there are three sentences. One sentence is masked with [MASK1] and used as target generation text (GSG). The other two sentences remain in the input, but some tokens are randomly masked by [MASK2]."

ASGD Weight-Dropped LSTM, or AWD-LSTM, is a type of recurrent neural network that employs DropConnect for regularization, as well as NT-ASGD for optimization - non-monotonically triggered averaged SGD - which returns an average of last iterations of weights. Additional regularization techniques employed include variable length backpropagation sequences, variational dropout, embedding dropout, weight tying, independent embedding/hidden size, activation regularization and temporal activation regularization.

SimCSE is a contrastive learning framework for generating sentence embeddings. It utilizes an unsupervised approach, which takes an input sentence and predicts itself in contrastive objective, with only standard dropout used as noise. The authors find that dropout acts as minimal “data augmentation” of hidden representations, while removing it leads to a representation collapse. Afterwards a supervised approach is used, which incorporates annotated pairs from natural language inference datasets into the contrastive framework, by using “entailment” pairs as positives and “contradiction

ShuffleNet is a convolutional neural network designed specially for mobile devices with very limited computing power. The architecture utilizes two new operations, pointwise group convolution and channel shuffle, to reduce computation cost while maintaining accuracy.

A ShuffleNet Block is an image model block that utilises a channel shuffle operation, along with depthwise convolutions, for an efficient architectural design. It was proposed as part of the ShuffleNet architecture. The starting point is the Residual Block unit from ResNets, which is then modified with a pointwise group convolution and a channel shuffle operation.

The Maxout Unit is a generalization of the ReLU and the leaky ReLU functions. It is a piecewise linear function that returns the maximum of the inputs, designed to be used in conjunction with dropout. Both ReLU and leaky ReLU are special cases of Maxout. $$f\left(x\right) = \max\left(w^{T}\_{1}x + b\_{1}, w^{T}\_{2}x + b\_{2}\right)$$ The main drawback of Maxout is that it is computationally expensive as it doubles the number of parameters for each neuron.

OASIS is a GAN-based model to translate semantic label maps into realistic-looking images. The model builds on preceding work such as Pix2Pix and SPADE. OASIS introduces the following innovations: 1. The method is not dependent on the perceptual loss, which is commonly used for the semantic image synthesis task. A VGG network trained on ImageNet is routinely employed as the perceptual loss to strongly improve the synthesis quality. The authors show that this perceptual loss also has negative effects: First, it reduces the diversity of the generated images. Second, it negatively influences the color distribution to be more biased towards ImageNet. OASIS eliminates the dependence on the perceptual loss by changing the common discriminator design: The OASIS discriminator segments an image into one of the real classes or an additional fake class. In doing so, it makes more efficient use of the label maps that the discriminator normally receives. This distinguishes the discriminator from the commonly used encoder-shaped discriminators, which concatenate the label maps to the input image and predict a single score per image. With the more fine-grained supervision through the loss of the OASIS discriminator, the perceptual loss is shown to become unnecessary. 2. A user can generate a diverse set of images per label map by simply resampling noise. This is achieved by conditioning the spatially-adaptive denormalization module in each layer of the GAN generator directly on spatially replicated input noise. A side effect of this conditioning is that at inference time an image can be resampled either globally or locally (either the complete image changes or a restricted region in the image).

AMSGrad is a stochastic optimization method that seeks to fix a convergence issue with Adam based optimizers. AMSGrad uses the maximum of past squared gradients $v\_{t}$ rather than the exponential average to update the parameters: $$m\_{t} = \beta\_{1}m\_{t-1} + \left(1-\beta\_{1}\right)g\_{t} $$ $$v\_{t} = \beta\_{2}v\_{t-1} + \left(1-\beta\_{2}\right)g\_{t}^{2}$$ $$ \hat{v}\_{t} = \max\left(\hat{v}\_{t-1}, v\_{t}\right) $$ $$\theta\_{t+1} = \theta\_{t} - \frac{\eta}{\sqrt{\hat{v}_{t}} + \epsilon}m\_{t}$$

Hyperboloid Embeddings (HypE) is a novel self-supervised dynamic reasoning framework, that utilizes positive first-order existential queries on a KG to learn representations of its entities and relations as hyperboloids in a Poincaré ball. HypE models the positive first-order queries as geometrical translation (t), intersection ($\cap$), and union ($\cup$). For the problem of KG reasoning in real-world datasets, the proposed HypE model significantly outperforms the state-of-the art results. HypE is also applied to an anomaly detection task on a popular e-commerce website product taxonomy as well as hierarchically organized web articles and demonstrate significant performance improvements compared to existing baseline methods. Finally, HypE embeddings can also be visualized in a Poincaré ball to clearly interpret and comprehend the representation space.

StyleGAN2 is a generative adversarial network that builds on StyleGAN with several improvements. First, adaptive instance normalization is redesigned and replaced with a normalization technique called weight demodulation. Secondly, an improved training scheme upon progressively growing is introduced, which achieves the same goal - training starts by focusing on low-resolution images and then progressively shifts focus to higher and higher resolutions - without changing the network topology during training. Additionally, new types of regularization like lazy regularization and path length regularization are proposed.

UNETR, or UNet Transformer, is a Transformer-based architecture for medical image segmentation that utilizes a pure transformer as the encoder to learn sequence representations of the input volume -- effectively capturing the global multi-scale information. The transformer encoder is directly connected to a decoder via skip connections at different resolutions like a U-Net to compute the final semantic segmentation output.

A BiFPN, or Weighted Bi-directional Feature Pyramid Network, is a type of feature pyramid network which allows easy and fast multi-scale feature fusion. It incorporates the multi-level feature fusion idea from FPN, PANet and NAS-FPN that enables information to flow in both the top-down and bottom-up directions, while using regular and efficient connections. It also utilizes a fast normalized fusion technique. Traditional approaches usually treat all features input to the FPN equally, even those with different resolutions. However, input features at different resolutions often have unequal contributions to the output features. Thus, the BiFPN adds an additional weight for each input feature allowing the network to learn the importance of each. All regular convolutions are also replaced with less expensive depthwise separable convolutions. Comparing with PANet, PANet added an extra bottom-up path for information flow at the expense of more computational cost. Whereas BiFPN optimizes these cross-scale connections by removing nodes with a single input edge, adding an extra edge from the original input to output node if they are on the same level, and treating each bidirectional path as one feature network layer (repeating it several times for more high-level future fusion).

Random Ensemble Mixture (REM) is an easy to implement extension of DQN inspired by Dropout. The key intuition behind REM is that if one has access to multiple estimates of Q-values, then a weighted combination of the Q-value estimates is also an estimate for Q-values. Accordingly, in each training step, REM randomly combines multiple Q-value estimates and uses this random combination for robust training.

CenterNet is a one-stage object detector that detects each object as a triplet, rather than a pair, of keypoints. It utilizes two customized modules named cascade corner pooling and center pooling, which play the roles of enriching information collected by both top-left and bottom-right corners and providing more recognizable information at the central regions, respectively. The intuition is that, if a predicted bounding box has a high IoU with the ground-truth box, then the probability that the center keypoint in its central region is predicted as the same class is high, and vice versa. Thus, during inference, after a proposal is generated as a pair of corner keypoints, we determine if the proposal is indeed an object by checking if there is a center keypoint of the same class falling within its central region.

Mix-FFN is a feedforward layer used in the SegFormer architecture. ViT uses positional encoding (PE) to introduce the location information. However, the resolution of $\mathrm{PE}$ is fixed. Therefore, when the test resolution is different from the training one, the positional code needs to be interpolated and this often leads to dropped accuracy. To alleviate this problem, CPVT uses $3 \times 3$ Conv together with the PE to implement a data-driven PE. The authors of Mix-FFN argue that positional encoding is actually not necessary for semantic segmentation. Instead, they use Mix-FFN which considers the effect of zero padding to leak location information, by directly using a $3 \times 3$ Conv in the feed-forward network (FFN). Mix-FFN can be formulated as: $$ \mathbf{x}\_{\text {out }}=\operatorname{MLP}\left(\operatorname{GELU}\left(\operatorname{Conv}\_{3 \times 3}\left(\operatorname{MLP}\left(\mathbf{x}\_{i n}\right)\right)\right)\right)+\mathbf{x}\_{i n} $$ where $\mathbf{x}\_{i n}$ is the feature from a self-attention module. Mix-FFN mixes a $3 \times 3$ convolution and an MLP into each FFN.