기법

One-Shot Aggregation with an Identity Mapping and eSE is an image model block that extends one-shot aggregation with a residual connection and effective squeeze-and-excitation block. It is proposed as part of the VoVNetV2 CNN architecture. The module adds an identity mapping to the OSA module - the input path is connected to the end of an OSA module that is able to backpropagate the gradients of every OSA module in an end-to-end manner on each stage like a ResNet. Additionally, a channel attention module - effective Squeeze-Excitation - is used which is like regular squeeze-and-excitation but uses only one FC layer with $C$ channels instead of two FCs without a channel dimension reduction, which maintains channel information.

Object Dropout is a technique that perturbs object features in an image for noisy student training. It performs at par with standard data augmentation techniques while being significantly faster than the latter to implement.

A group of methods designed to generate outliers in tabular data, emphasizing the importance of such techniques as supported by extreme value theory. These methods are crucial for modeling, analyzing, and understanding anomalous or rare events within structured datasets.

PAFNet is an anchor-free detector for object detection that removes pre-defined anchors and regresses the locations directly, which can achieve higher efficiency. The overall network is composed of a backbone, an up-sampling module, an AGS module, a localization branch and a regression branch. Specifically, ResNet50-vd is chosen as the backbone for server side, and MobileNetV3 for mobile side. Besides, for mobile side, we replace traditional convolution layers with lite convolution operators.

PAR Transformer is a Transformer model that uses 63% fewer self-attention blocks, replacing them with feed-forward blocks, while retaining test accuracies. It is based on the Transformer-XL architecture and uses neural architecture search to find an an efficient pattern of blocks in the transformer architecture.

A variant of the popular k-means algorithm that integrates constraint satisfaction into its objective function. Original paper : Active Semi-Supervision for Pairwise Constrained Clustering, Basu et al. 2004

We present a new class of nearest-neighbor explanations (called Probable-Class Nearest Neighbors or PCNN) and show a novel utility of the XAI method: To improve predictions of a frozen, pretrained classifier C. Our method consistently improves fine-grained image classification accuracy on CUB-200, Cars-196, and Dogs-120. Also, a human study finds that showing lay-users our PCNN explanations improves their decision accuracy over showing only the top-1 class examples (as in prior work).

PIoU Loss is a loss function for oriented object detection which is formulated to exploit both the angle and IoU for accurate oriented bounding box regression. The PIoU loss is derived from IoU metric with a pixel-wise form.

The Parametric Mish, or PMish, is a modification of the Mish activation function that has a trainable parameter $\beta$. This $\beta$ parameter allows the network to dynamically adjust the smoothness of the activation function transition. \begin{equation} f(x) = x \cdot \tanh\left(\frac{\ln(1 + e^{\beta x})}{\beta}\right), \beta > 0, \end{equation}

A VQA model that marries two powerful ideas: probabilistic neural symbolic program execution for reasoning and a deep neural network with 3D generative representations of objects for robust visual scene parsing.

Representation learning is a pivotal area in the field of machine learning, focusing on the development of methods to automatically discover the representations or features needed for a given task from raw data. Unlike traditional feature engineering, which requires manual crafting of features, representation learning aims to learn features that are more useful and relevant for tasks such as classification, prediction, and clustering. We introduce Principal Orthogonal Latent Components Analysis Network (POLCA Net), an approach to mimic and extend PCA and LDA capabilities to non-linear domains. POLCA Net combines an autoencoder framework with a set of specialized loss functions to achieve effective dimensionality reduction, orthogonality, variance-based feature sorting, high-fidelity reconstructions, and additionally, when used with classification labels, a latent representation well suited for linear classifiers and low dimensional visualization of class distribution as well.

Prediction-aware One-To-One, or POTO, is an assignment rule for object detection which dynamically assigns the foreground samples according to the quality of classification and regression simultaneously.

Path Planning and Motion Control, or PPMC RL, is a training algorithm that teaches path planning and motion control to robots using reinforcement learning in a simulated environment. The focus is on promoting generalization where there are environmental uncertainties such as rough environments like lunar services. The algorithm is coupled with any generic reinforcement learning algorithm to teach robots how to respond to user commands and to travel to designated locations on a single neural network. The algorithm works independently of the robot structure, demonstrating that it works on a wheeled rover in addition to the past results on a quadruped walking robot.

PQ-Transformer, or PointQuad-Transformer, is a Transformer-based architecture that predicts 3D objects and layouts simultaneously, using point cloud inputs. Unlike existing methods that either estimate layout keypoints or edges, room layouts are directly parameterized as a set of quads. Along with the quad representation, a physical constraint loss function is used that discourages object-layout interference. Given an input 3D point cloud of $N$ points, the point cloud feature learning backbone extracts $M$ context-aware point features of $\left(3+C\right)$ dimensions, through sampling and grouping. A voting module and a farthest point sampling (FPS) module are used to generate $K\_{1}$ object proposals and $K\_{2}$ quad proposals respectively. Then the proposals are processed by a transformer decoder to further refine proposal features. Through several feedforward layers and non-maximum suppression (NMS), the proposals become the final object bounding boxes and layout quads.

PRNet+ is a multi-task neural network for outdoor position recovery from measurement record (MR) data. PRNet+ develops a feature extraction module to learn common local-, short- and long-term spatio-temporal locality from heterogeneous MR samples, with a convolutional neural network (CNN), long short-term memory cells (LSTM), and attention mechanisms. Specifically, PRNet+ 1) allows the various-length sequences of MR samples, such that the two components (CNN and LSTM) are able to capture spatial locality from the samples within each MR sequence, 2) exploits two attention mechanisms for the time-interval between neighbouring MR samples, together with the one between neighbouring MR sequences, to capture temporal locality, and 3) incorporates the detected transportation modes and predicted locations of heterogeneous MR data into a joint loss for better result.

PSANet is a semantic segmentation architecture that utilizes a Point-wise Spatial Attention (PSA) module to aggregate long-range contextual information in a flexible and adaptive manner. Each position in the feature map is connected with all other ones through self-adaptively predicted attention maps, thus harvesting various information nearby and far away. Furthermore, the authors design the bi-directional information propagation path for a comprehensive understanding of complex scenes. Each position collects information from all others to help the prediction of itself and vice versa, the information at each position can be distributed globally, assisting the prediction of all other positions. Finally, the bi-directionally aggregated contextual information is fused with local features to form the final representation of complex scenes. The authors use ResNet as an FCN backbone for PSANet, as the Figure to the right illustrates. The proposed PSA module is then used to aggregate long-range contextual information from the local representation. It follows stage-5 in ResNet, which is the final stage of the FCN backbone. Features in stage-5 are semantically stronger. Aggregating them together leads to a more comprehensive representation of long-range context. Moreover, the spatial size of the feature map at stage-5 is smaller and can reduce computation overhead and memory consumption. An auxiliary loss branch is applied apart from the main loss.

PSFR-GAN is a semantic-aware style transformation framework for face restoration. Given a pair of LQ face image and its corresponding parsing map, we first generate a multi-scale pyramid of the inputs, and then progressively modulate different scale features from coarse-to-fine in a semantic-aware style transfer way. Compared with previous networks, the proposed PSFR-GAN makes full use of the semantic (parsing maps) and pixel (LQ images) space information from different scales of inputs.

PanGu-$α$ is an autoregressive language model (ALM) with up to 200 billion parameters pretrained on a large corpus of text, mostly in Chinese language. The architecture of PanGu-$α$ is based on Transformer, which has been extensively used as the backbone of a variety of pretrained language models such as BERT and GPT. Different from them, there's an additional query layer developed on top of Transformer layers which aims to explicitly induce the expected output.

ParamCrop is a parametric cubic cropping for video contrastive learning, where cubic cropping refers to cropping a 3D cube from the input video. The central component of ParamCrop is a differentiable spatio-temporal cropping operation, which enables ParamCrop to be trained simultaneously with the video backbone and adjust the cropping strategy on the fly. The objective of ParamCrop is set to be adversarial to the video backbone, which is to increase the contrastive loss. Hence, initialized with the simplest setting where two cropped views largely overlaps, ParamCrop gradually increases the disparity between two views.

While the typical approach to leverage transfer learning in image segmentation models involves replacing the entire encoder, this can restrict the customization and unique strengths of the main network. To address this limitation, we propose a hybrid transfer learning strategy that incorporates pre-trained convolutional layers from two distinct architectures (e.g., VGG16 and DenseNet201), allowing us to leverage the advantages of transfer learning while preserving the core features and characteristics of the base model's architecture.

PatchMerger is a module for Vision Transformers that decreases the number of tokens/patches passed onto each individual transformer encoder block whilst maintaining performance and reducing compute. PatchMerger takes linearly transforms an input of shape N patches × D dimensions through a learnable weight matrix of shape M output patches × D. This generates M scores, in which a Softmax function is applied for each score. The resulting output has a shape of M × N, which is multiplied to the original input to get an output of shape M × D. Mathematically, $$Y = \text{softmax}({W^T}{X^T})X$$ Image and formula from: Renggli, C., Pinto, A. S., Houlsby, N., Mustafa, B., Puigcerver, J., & Riquelme, C. (2022). Learning to Merge Tokens in Vision Transformers. arXiv preprint arXiv:2202.12015.

PermuteFormer is a Performer-based model with relative position encoding that scales linearly on long sequences. PermuteFormer applies position-dependent transformation on queries and keys to encode positional information into the attention module. This transformation is carefully crafted so that the final output of self-attention is not affected by absolute positions of tokens. Each token’s query / key feature is illustrated as a row of blocks in the figure, and its elements are marked with different colors. The position-aware permutation permutes elements of each token’s query / key feature along the head size dimension in each attention head. Depending on the token’s position, the permutation applied to query / key feature is different.

A GCN method targeted at the unique spectral properties of dense graphs and hypergraphs, enabled by efficient numerical linear algebra.

PipeMare is an asynchronous (bubble-free) pipeline parallel method for training large neural networks. It involves two main techniques: learning rate rescheduling and discrepancy correction.

Pipelined Backpropagation is an asynchronous pipeline parallel training algorithm. It was first introduced by Petrowski et al (1993). It avoids fill and drain overhead by updating the weights without draining the pipeline first. This results in weight inconsistency, the use of different weights on the forward and backward passes for a given micro-batch. The weights used to produce a particular gradient may also have been updated when the gradient is applied, resulting in stale (or delayed) gradients. For these reasons PB resembles Asynchronous SGD and is not equivalent to standard SGD. Finegrained pipelining increases the number of pipeline stages and hence increases the weight inconsistency and delay.

PixLoc is a scene-agnostic neural network that estimates an accurate 6-DoF pose from an image and a 3D model. It is based on the direct alignment of multiscale deep features, casting camera localization as metric learning. PixLoc learns strong data priors by end-to-end training from pixels to pose and exhibits exceptional generalization to new scenes by separating model parameters and scene geometry. As the CNN never sees 3D points, PixLoc can generalize to any 3D structure available. This includes sparse SfM point clouds, dense depth maps from stereo or RGBD sensors, meshes, Lidar scans, but also lines and other primitives.

A trainable layer that encodes feature vectors onto 2 rotational coordinates $R_y(\theta),R_z(\gamma)$ for a unit sphere. Used to map data onto the Bloch Sphere surface for qubits

Poincaré Embeddings learn hierarchical representations of symbolic data by embedding them into hyperbolic space -- or more precisely into an $n$-dimensional Poincaré ball. Due to the underlying hyperbolic geometry, this allows for learning of parsimonious representations of symbolic data by simultaneously capturing hierarchy and similarity. Embeddings are learnt based on Riemannian optimization.

Point-GNN is a graph neural network for detecting objects from a LiDAR point cloud. It predicts the category and shape of the object that each vertex in the graph belongs to. In Point-GNN, there is an auto-registration mechanism to reduce translation variance, as well as a box merging and scoring operation to combine detections from multiple vertices accurately.

PointASNL is a non-local neural network for point clouds processing It consists of two general modules: adaptive sampling (AS) module and local-Nonlocal (L-NL) module. The AS module first re-weights the neighbors around the initial sampled points from farthest point sampling (FPS), and then adaptively adjusts the sampled points beyond the entire point cloud. The AS module can not only benefit the feature learning of point clouds, but also ease the biased effect of outliers. The L-NL module capture the neighbor and long-range dependencies of the sampled point, and enables the learning process to be insensitive to noise.

PointAugment is a an auto-augmentation framework that automatically optimizes and augments point cloud samples to enrich the data diversity when we train a classification network. Different from existing auto-augmentation methods for 2D images, PointAugment is sample-aware and takes an adversarial learning strategy to jointly optimize an augmentor network and a classifier network, such that the augmentor can learn to produce augmented samples that best fit the classifier.

The Pointer Sentinel-LSTM mixture model is a type of recurrent neural network that combines the advantages of standard softmax classifiers with those of a pointer component for effective and efficient language modeling. Rather than relying on the RNN hidden state to decide when to use the pointer, the model allows the pointer component itself to decide when to use the softmax vocabulary through a sentinel.