기법

Revision Network is a style transfer module that aims to revise the rough stylized image via generating residual details image $r_{c s}$, while the final stylized image is generated by combining $r\_{c s}$ and rough stylized image $\bar{x}\_{c s}$. This procedure ensures that the distribution of global style pattern in $\bar{x}\_{c s}$ is properly kept. Meanwhile, learning to revise local style patterns with residual details image is easier for the Revision Network. As shown in the Figure, the Revision Network is designed as a simple yet effective encoder-decoder architecture, with only one down-sampling and one up-sampling layer. Further, a patch discriminator is used to help Revision Network to capture fine patch textures under adversarial learning setting. The patch discriminator $D$ is defined following SinGAN, where $D$ owns 5 convolution layers and 32 hidden channels. A relatively shallow $D$ is chosen to (1) avoid overfitting since we only have one style image and (2) control the receptive field to ensure D can only capture local patterns.

RotNet is a self-supervision approach that relies on predicting image rotations as the pretext task in order to learn image representations.

SCCL, or Supporting Clustering with Contrastive Learning, is a framework to leverage contrastive learning to promote better separation in unsupervised clustering. It combines the top-down clustering with the bottom-up instance-wise contrastive learning to achieve better inter-cluster distance and intra-cluster distance. During training, we jointly optimize a clustering loss over the original data instances and an instance-wise contrastive loss over the associated augmented pairs.

SKNet is a type of convolutional neural network that employs selective kernel units, with selective kernel convolutions, in its architecture. This allows for a type of attention where the network can learn to attend to different receptive fields.

STDC, or Short-Term Dense Concatenate, is a module for semantic segmentation to extract deep features with scalable receptive field and multi-scale information. It aims to remove structure redundancy in the BiSeNet architecture, specifically BiSeNet adds an extra path to encode spatial information which can be time-consuming,. Instead, STDC gradually reduces the dimension of feature maps and use the aggregation of them for image representation. We concatenate response maps from multiple continuous layers, each of which encodes input image/feature in different scales and respective fields, leading to multi-scale feature representation. To speed up, the filter size of layers is gradually reduced with negligible loss in segmentation performance.

Self-adaptive Training is a training algorithm that dynamically corrects problematic training labels by model predictions to improve generalization of deep learning for potentially corrupted training data. Accumulated predictions are used to augment the training dynamics. The use of an exponential-moving-average scheme alleviates the instability issue of model predictions, smooths out the training target during the training process and enables the algorithm to completely change the training labels if necessary.

A method that randomly mask out all features coming from a specific sensor in multi-sensor models for Earth observation. Depending on the fusion strategy, the mask out can be done at the input, feature or decision level.

Siamese U-Net model with a pre-trained ResNet34 architecture as an encoder for data efficient Change Detection

SimAug, or Simulation as Augmentation, is a data augmentation method for trajectory prediction. It augments the representation such that it is robust to the variances in semantic scenes and camera views. First, to deal with the gap between real and synthetic semantic scene, it represents each training trajectory by high-level scene semantic segmentation features, and defends the model from adversarial examples generated by whitebox attack methods. Second, to overcome the changes in camera views, it generates multiple views for the same trajectory, and encourages the model to focus on the “hardest” view to which the model has learned. The classification loss is adopted and the view with the highest loss is favored during training. Finally, the augmented trajectory is computed as a convex combination of the trajectories generated in previous steps. The trajectory prediction model is built on a multi-scale representation and the final model is trained to minimize the empirical vicinal risk over the distribution of augmented trajectories.

SimCLRv2 is a semi-supervised learning method for learning from few labeled examples while making best use of a large amount of unlabeled data. It is a modification of a recently proposed contrastive learning framework, SimCLR. It improves upon it in three major ways: 1. To fully leverage the power of general pre-training, larger ResNet models are explored. Unlike SimCLR and other previous work, whose largest model is ResNet-50 (4×), SimCLRv2 trains models that are deeper but less wide. The largest model trained is a 152 layer ResNet with 3× wider channels and selective kernels (SK), a channel-wise attention mechanism that improves the parameter efficiency of the network. By scaling up the model from ResNet-50 to ResNet-152 (3×+SK), a 29% relative improvement is obtained in top-1 accuracy when fine-tuned on 1% of labeled examples. 2. The capacity of the non-linear network $g(·)$ (a.k.a. projection head) is increased, by making it deeper. Furthermore, instead of throwing away $g(·)$ entirely after pre-training as in SimCLR, fine-tuning occurs from a middle layer. This small change yields a significant improvement for both linear evaluation and fine-tuning with only a few labeled examples. Compared to SimCLR with 2-layer projection head, by using a 3-layer projection head and fine-tuning from the 1st layer of projection head, it results in as much as 14% relative improvement in top-1 accuracy when fine-tuned on 1% of labeled examples. 3. The memory mechanism of MoCo v2 is incorporated, which designates a memory network (with a moving average of weights for stabilization) whose output will be buffered as negative examples. Since training is based on large mini-batch which already supplies many contrasting negative examples, this change yields an improvement of ∼1% for linear evaluation as well as when fine-tuning on 1% of labeled examples.

Social-STGCNN is a method for human trajectory prediction. Pedestrian trajectories are not only influenced by the pedestrian itself but also by interaction with surrounding objects.

Spatial Attention Module (SAM) is a feature extraction module for object detection used in ThunderNet. The ThunderNet SAM explicitly re-weights the feature map before RoI warping over the spatial dimensions. The key idea of SAM is to use the knowledge from RPN to refine the feature distribution of the feature map. RPN is trained to recognize foreground regions under the supervision of ground truths. Therefore, the intermediate features in RPN can be used to distinguish foreground features from background features. SAM accepts two inputs: the intermediate feature map from RPN $\mathcal{F}^{RPN}$ and the thin feature map from the Context Enhancement Module $\mathcal{F}^{CEM}$. The output of SAM $\mathcal{F}^{SAM}$ is defined as: $$ \mathcal{F}^{SAM} = \mathcal{F}^{CEM} * \text{sigmoid}\left(\theta\left(\mathcal{F}^{RPN}\right)\right) $$ Here $\theta\left(·\right)$ is a dimension transformation to match the number of channels in both feature maps. The sigmoid function is used to constrain the values within $\left[0, 1\right]$. At last, $\mathcal{F}^{CEM}$ is re-weighted by the generated feature map for better feature distribution. For computational efficiency, we simply apply a 1×1 convolution as $\theta\left(·\right)$, so the computational cost of CEM is negligible. The Figure to the right shows the structure of SAM. SAM has two functions. The first one is to refine the feature distribution by strengthening foreground features and suppressing background features. The second one is to stabilize the training of RPN as SAM enables extra gradient flow from R-CNN subnet to RPN. As a result, RPN receives additional supervision from RCNN subnet, which helps the training of RPN.

Symbolic rule learning methods find regularities in data that can be expressed in the form of 'if-then' rules based on symbolic representations of the data.

TD-Gammon is a game-learning architecture for playing backgammon. It involves the use of a $TD\left(\lambda\right)$ learning algorithm and a feedforward neural network. Credit: Temporal Difference Learning and TD-Gammon

Teacher-Tutor-Student Knowledge Distillation is a method for image virtual try-on models. It treats fake images produced by the parser-based method as "tutor knowledge", where the artifacts can be corrected by real "teacher knowledge", which is extracted from the real person images in a self-supervised way. Other than using real images as supervisions, knowledge distillation is formulated in the try-on problem as distilling the appearance flows between the person image and the garment image, enabling the finding of dense correspondences between them to produce high-quality results.

ThunderNet is a two-stage object detection model. The design of ThunderNet aims at the computationally expensive structures in state-of-the-art two-stage detectors. The backbone utilises a ShuffleNetV2 inspired network called SNet designed for object detection. In the detection part, ThunderNet follows the detection head design in Light-Head R-CNN, and further compresses the RPN and R-CNN subnet. To eliminate the performance degradation induced by small backbones and small feature maps, ThunderNet uses two new efficient architecture blocks, Context Enhancement Module (CEM) and Spatial Attention Module (SAM). CEM combines the feature maps from multiple scales to leverage local and global context information, while SAM uses the information learned in RPN to refine the feature distribution in RoI warping.

A TridentNet Block is a feature extractor used in object detection models. Instead of feeding in multi-scale inputs like the image pyramid, in a TridentNet block we adapt the backbone network for different scales. These blocks create multiple scale-specific feature maps. With the help of dilated convolutions, different branches of trident blocks have the same network structure and share the same parameters yet have different receptive fields. Furthermore, to avoid training objects with extreme scales, a scale-aware training scheme is employed to make each branch specific to a given scale range matching its receptive field. Weight sharing is used to prevent overfitting.

UNIMO is a multi-modal pre-training architecture that can effectively adapt to both single modal and multimodal understanding and generation tasks. UNIMO learns visual representations and textual representations simultaneously, and unifies them into the same semantic space via cross-modal contrastive learning (CMCL) based on a large-scale corpus of image collections, text corpus and image-text pairs. The CMCL aligns the visual representation and textual representation, and unifies them into the same semantic space based on image-text pairs.

VL-BERT is pre-trained on a large-scale image-captions dataset together with text-only corpus. The input to the model are either words from the input sentences or regions-of-interest (RoI) from input images. It can be fine-tuned to fit most visual-linguistic downstream tasks. Its backbone is a multi-layer bidirectional Transformer encoder, modified to accommodate visual contents, and new type of visual feature embedding to the input feature embeddings. VL-BERT takes both visual and linguistic elements as input, represented as RoIs in images and subwords in input sentences. Four different types of embeddings are used to represent each input: token embedding, visual feature embedding, segment embedding, and sequence position embedding. VL-BERT is pre-trained using Conceptual Captions and text-only datasets. Two pre-training tasks are used: masked language modeling with visual clues, and masked RoI classification with linguistic clues.

VisuoSpatial Foresight is a method for robotic fabric manipulation that leverages a combination of RGB and depth information to learn goal conditioned fabric manipulation policies for a variety of long horizon tasks.

Virtual Data Augmentation, or VDA, is a framework for robustly fine-tuning pre-trained language model. Based on the original token embeddings, a multinomial mixture for augmenting virtual data is constructed, where a masked language model guarantees the semantic relevance and the Gaussian noise provides the augmentation diversity. Furthermore, a regularized training strategy is proposed to balance the two aspects.

Proposes a two-tower pre-training model called BriVL within the cross-modal contrastive learning framework. A cross-modal pre-training model is defined based on the image-text retrieval task. The main goal is thus to learn two encoders that can embed image and text samples into the same space for effective image-text retrieval. To enforce such cross-modal embedding learning, we introduce contrastive learning with the InfoNCE loss into the BriVL model. Given text embedding, the learning objective aims to find the best image embedding from a batch of image embeddings. Similarly, for a given image embedding, the learning objective is to find the best text embedding from a batch of text embeddings. The pre-training model learns a cross-modal embedding space by jointly training the image and text encoders to maximize the cosine similarity of the image and text embeddings of the true pair for each sample in the batch while minimizing the cosine similarity of the embeddings of the other incorrect pairs.

Cross-Covariance Image Transformers, or XCiT, is a type of vision transformer that aims to combine the accuracy of conventional transformers with the scalability of convolutional architectures. The self-attention operation underlying transformers yields global interactions between all tokens, i.e. words or image patches, and enables flexible modelling of image data beyond the local interactions of convolutions. This flexibility, however, comes with a quadratic complexity in time and memory, hindering application to long sequences and high-resolution images. The authors propose a “transposed” version of self-attention called cross-covariance attention that operates across feature channels rather than tokens, where the interactions are based on the cross-covariances matrix between keys and queries.

An XCiT Layer is the main building block of the XCiT architecture which uses a cross-covariance attention operator as its principal operation. The XCiT layer consists of three main blocks, each preceded by LayerNorm and followed by a residual connection: (i) the core cross-covariance attention (XCA) operation, (ii) the local patch interaction (LPI) module, and (iii) a feed-forward network (FFN). By transposing the query-key interaction, the computational complexity of XCA is linear in the number of data elements N, rather than quadratic as in conventional self-attention.

ZeRO-Offload is a sharded data parallel method for distributed training. It exploits both CPU memory and compute for offloading, while offering a clear path towards efficiently scaling on multiple GPUs by working with ZeRO-powered data parallelism. The symbiosis allows ZeRO-Offload to maintain a single copy of the optimizer states on the CPU memory regardless of the data parallel degree. Furthermore, it keeps the aggregate communication volume between GPU and CPU, as well as the aggregate CPU computation a constant regardless of data parallelism, allowing ZeRO-Offload to effectively utilize the linear increase in CPU compute with the increase in the data parallelism degree.

Please enter a description about the method here

To aggregate global spatial information, an SE block applies global pooling to the feature map. However, it ignores pixel-wise spatial information, which is important in dense prediction tasks. Therefore, Roy et al. proposed spatial and channel SE blocks (scSE). Like BAM, spatial SE blocks are used, complementing SE blocks, to provide spatial attention weights to focus on important regions. Given the input feature map $X$, two parallel modules, spatial SE and channel SE, are applied to feature maps to encode spatial and channel information respectively. The channel SE module is an ordinary SE block, while the spatial SE module adopts $1\times 1$ convolution for spatial squeezing. The outputs from the two modules are fused. The overall process can be written as \begin{align} s_c & = \sigma (W_{2} \delta (W_{1}\text{GAP}(X))) \end{align} \begin{align} X_\text{chn} & = s_c X \end{align} \begin{align} s_s &= \sigma(\text{Conv}^{1\times 1}(X)) \end{align} \begin{align} X_\text{spa} & = s_s X \end{align} \begin{align} Y &= f(X_\text{spa},X_\text{chn}) \end{align} where $f$ denotes the fusion function, which can be maximum, addition, multiplication or concatenation. The proposed scSE block combines channel and spatial attention to enhance features as well as capturing pixel-wise spatial information. Segmentation tasks are greatly benefited as a result. The integration of an scSE block in F-CNNs makes a consistent improvement in semantic segmentation at negligible extra cost.

3D ResNet-RS is an architecture and scaling strategy for 3D ResNets for video recognition. The key additions are: - 3D ResNet-D stem: The ResNet-D stem is adapted to 3D inputs by using three consecutive 3D convolutional layers. The first convolutional layer employs a temporal kernel size of 5 while the remaining two convolutional layers employ a temporal kernel size of 1. - 3D Squeeze-and-Excitation: Squeeze-and-Excite is adapted to spatio-temporal inputs by using a 3D global average pooling operation for the squeeze operation. A SE ratio of 0.25 is applied in each 3D bottleneck block for all experiments. - Self-gating: A self-gating module is used in each 3D bottleneck block after the SE module.

Adaptive Bezier-Curve Network, or ABCNet, is an end-to-end framework for arbitrarily-shaped scene text spotting. It adaptively fits arbitrary-shaped text by a parameterized bezier curve. It also utilizes a feature alignment layer, BezierAlign, to calculate convolutional features of text instances in curved shapes. These features are then passed to a light-weight recognition head.

ACGPN, or Adaptive Content Generating and Preserving Network, is a generative adversarial network for virtual try-on clothing applications. In Step I, the Semantic Generation Module (SGM) takes the target clothing image $\mathcal{T}\_{c}$, the pose map $\mathcal{M}\_{p}$, and the fused body part mask $\mathcal{M}^{F}$ as the input to predict the semantic layout and to output the synthesized body part mask $\mathcal{M}^{S}\_{\omega}$ and the target clothing mask $\mathcal{M}^{S\_{c}$. In Step II, the Clothes Warping Module (CWM) warps the target clothing image to $\mathcal{T}^{R}\_{c}$ according to the predicted semantic layout, where a second-order difference constraint is introduced to stabilize the warping process. In Steps III and IV, the Content Fusion Module (CFM) first produces the composited body part mask $\mathcal{M}^{C}\_{\omega}$ using the original clothing mask $\mathcal{M}\_{c}$, the synthesized clothing mask $\mathcal{M}^{S}\_{c}$, the body part mask $\mathcal{M}\_{\omega}$, and the synthesized body part mask $\mathcal{M}\_{\omega}^{S}$, and then exploits a fusion network to generate the try-on images $\mathcal{I}^{S}$ by utilizing the information $\mathcal{T}^{R}\_{c}$, $\mathcal{M}^{S}\_{c}$, and the body part image $I\_{\omega}$ from previous steps.

In the space of adversarial perturbation against classifier accuracy, the ARA is the area between a classifier's curve and the straight line defined by a naive classifier's maximum accuracy. Intuitively, the ARA measures a combination of the classifier’s predictive power and its ability to overcome an adversary. Importantly, when contrasted against existing robustness metrics, the ARA takes into account the classifier’s performance against all adversarial examples, without bounding them by some arbitrary $\epsilon$.

An Active Convolution is a type of convolution which does not have a fixed shape of the receptive field, and can be used to take more diverse forms of receptive fields for convolutions. Its shape can be learned through backpropagation during training. It can be seen as a generalization of convolution; it can define not only all conventional convolutions, but also convolutions with fractional pixel coordinates. We can freely change the shape of the convolution, which provides greater freedom to form CNN structures. Second, the shape of the convolution is learned while training and there is no need to tune it by hand

Adaptive Non-Maximum Suppression is a non-maximum suppression algorithm that applies a dynamic suppression threshold to an instance according to the target density. The motivation is to find an NMS algorithm that works well for pedestrian detection in a crowd. Intuitively, a high NMS threshold keeps more crowded instances while a low NMS threshold wipes out more false positives. The adaptive-NMS thus applies a dynamic suppression strategy, where the threshold rises as instances gather and occlude each other and decays when instances appear separately. To this end, an auxiliary and learnable sub-network is designed to predict the adaptive NMS threshold for each instance.

Adversarial Color Enhancement is an approach to generating unrestricted adversarial images by optimizing a color filter via gradient descent.