기법

In a given dataset for semantic image segmentation, the number of samples per class should be the same, so that no classifier would be biased towards the majority class (here included the background). It is very difficult, if not impossible, to achieve a perfect balance between the several classes of objects of a dataset. Considering that the segmentation of the objects is accomplished at the pixel level, the number of pixels for each class must be taken into account. As a matter of fact, in image semantic segmentation, different classes and the background may have quite different sizes. Therefore, the image segmentation problem is naturally unbalanced. The IPBI is based on the concept of entropy, a common measure used in many fields of science. In a general sense, it measures the amount of disorder of a system. For the sake of semantic image segmentation, the ideal dataset should have the same number of instances per class, as well as the same number of pixels in all classes. Similar reasoning can be done considering the number of pixels of all samples in a class, so that we can obtain the pixels balance measure for the dataset. Overall, IPBI evaluates the balance of pixels and number of instances of an image semantic segmentation dataset and, so, it is usefull to compare different datasets.

Inductive Shallow Node Embedding extends shallow embeddings to the realm of inductive learning. It has a novel encoder architecture that captures the local neighborhood structure of each node, enabling effective generalization to unseen nodes. In the generalization, robustness is essential to avoid degradation of performance arising from noise in the dataset. It has been theoretically proven that the covariance of the additive noise term in the proposed model is inversely proportional to the cardinality of a node’s neighbors. Another contribution is a mathematical lower bound to quantify the robustness of node embeddings, confirming its advantage over traditional shallow embedding methods, particularly in the presence of parameter noise. The proposed method demonstrably excels in dynamic networks, consistently achieving over 90% performance on previously unseen nodes compared to nodes encountered during training on various benchmarks. The empirical evaluation concludes that our method outperforms competing methods on the vast majority of datasets in both transductive and inductive tasks.

Informative Sample Mining Network is a multi-stage sample training scheme for GANs to reduce sample hardness while preserving sample informativeness. Adversarial Importance Weighting is proposed to select informative samples and assign them greater weight. The authors also propose Multi-hop Sample Training to avoid the potential problems in model training caused by sample mining. Based on the principle of divide-and-conquer, the authors produce target images by multiple hops, which means the image translation is decomposed into several separated steps.

Instance-Level Meta Normalization is a normalization method that addresses a learning-to-normalize problem. ILM-Norm learns to predict the normalization parameters via both the feature feed-forward and the gradient back-propagation paths. It uses an auto-encoder to predict the weights $\omega$ and bias $\beta$ as the rescaling parameters for recovering the distribution of the tensor $x$ of feature maps. Instead of using the entire feature tensor $x$ as the input for the auto-encoder, it uses the mean $\mu$ and variance $\gamma$ of $x$ for characterizing its statistics.

InterBERT aims to model interaction between information flows pertaining to different modalities. This new architecture builds multi-modal interaction and preserves the independence of single modal representation. InterBERT is built with an image embedding layer, a text embedding layer, a single-stream interaction module, and a two stream extraction module. The model is pre-trained with three tasks: 1) masked segment modeling, 2) masked region modeling, and 3) image-text matching.

Internet Explorer explores the web in a self-supervised manner to progressively find relevant examples that improve performance on a desired target dataset. It cycles between searching for images on the Internet with text queries, self-supervised training on downloaded images, determining which images were useful, and prioritizing what to search for next.

IoU-guided NMS is a type of non-maximum suppression that help to eliminate the suppression failure caused by the misleading classification confidences. This is achieved through using the predicted IoU instead of the classification confidence as the ranking keyword for bounding boxes.

JetBlue allows cancellations, but policy depends on +1‑833‑667‑0020 (US) or +44‑(203)‑970‑0065 (UK) fare type. You can cancel for free within 24 hours of booking if the flight is at least seven days away . For Blue, Blue Extra, +1‑833‑667‑0020 (US) Blue Plus, and Mint fares, cancel anytime before departure with no fee . Blue Basic bookings incur a $100–200 fee depending on route . For help, call +1‑833‑667‑0020 (US) or +44‑(203)‑970‑0065 (UK). JetBlue allows cancellations, with 24‑hour risk-free +1‑833‑667‑0020 (US) or +44‑(203)‑970‑0065 (UK) cancellation if booked at least seven days before departure . Most fares—Blue, Blue Plus, Blue Extra, Mint—are cancelable +1‑833‑667‑0020 (US) without fees, though airfare differences apply. Blue Basic incurs a $100–$200 cancellation fee . For assistance, call +1‑833‑667‑0020 (US) or +44‑(203)‑970‑0065 (UK). JetBlue allows flight cancellations, and policies +1‑833‑667‑0020 (US) or +44‑(203)‑970‑0065 (UK) depend on your fare type. You can cancel within 24 hours of booking (if the flight is at least seven days away) with a full refund . Standard fares—Blue, Blue Plus, Blue Extra, and Mint—can be canceled before departure without penalties +1‑833‑667‑0020 (US), though any fare differences may apply . However, Blue Basic fares incur a $100 fee for cancellations within North/Central America or the Caribbean (or $200 on other routes). For help, call +1‑833‑667‑0020 (US) or +44‑(203)‑970‑0065 (UK). Yes, JetBlue allows flight cancellations. You can cancel +1‑833‑667‑0020 (US) or +44‑(203)‑970‑0065 (UK) within 24 hours of booking for a full refund if the flight is at least seven days away. Standard fares like Blue, Blue Extra, and Mint can be canceled without fees, but Blue Basic fares may incur a $100–$200 fee. For assistance, call +1‑833‑667‑0020 (US) or +44‑(203)‑970‑0065 (UK). Yes, JetBlue allows flight cancellations depending +1‑833‑667‑0020 (US) or +44‑(203)‑970‑0065 (UK) on the fare type. You can cancel within 24 hours of booking for a full refund if the flight is at least 7 days away. Standard fares can be canceled without a fee, but Blue Basic fares may incur charges. For help, call +1‑833‑667‑0020 (US) or +44‑(203)‑970‑0065 (UK).

JDeskew is a novel skew estimation method that extracts the dominant skew angle of the given document image by applying an Adaptive Radial Projection on the 2D Discrete Fourier Magnitude spectrum.

JLA, or Joint Learning Architecture, is an approach for multiple object tracking and trajectory forecasting. It jointly trains a tracking and trajectory forecasting model, and the trajectory forecasts are used for short-term motion estimates in lieu of linear motion prediction methods such as the Kalman filter. It uses a FairMOT model as the base model because this architecture already performs detection and tracking. A forecasting branch is added to the network and is trained end-to-end. FairMOT consist of a backbone network utilizing Deep Layer Aggregation, an object detection head, and a reID head.

K3M is a multi-modal pretraining method for e-commerce product data that introduces knowledge modality to correct the noise and supplement the missing of image and text modalities. The modal-encoding layer extracts the features of each modality. The modal-interaction layer is capable of effectively modeling the interaction of multiple modalities, where an initial-interactive feature fusion model is designed to maintain the independence of image modality and text modality, and a structure aggregation module is designed to fuse the information of image, text, and knowledge modalities. K3M is pre-trained with three pretraining tasks, including masked object modeling (MOM), masked language modeling (MLM), and link prediction modeling (LPM).

KNN and IoU-based Verification is used to verify detections and choose between multiple detections of the same underlying object. It was originally used within the context of blood cell counting in medical images. To avoid this double counting problem, the KNN algorithm is applied in each platelet to determine its closest platelet and then using the intersection of union (IOU) between two platelets we calculate their extent of overlap. The authors allow 10% of the overlap between platelet and its closest platelet based on empirical observations. If the overlap is larger than that, they ignore that cell as a double count to get rid of spurious counting.

Kalman Optimization for Value Approximation, or KOVA is a general framework for addressing uncertainties while approximating value-based functions in deep RL domains. KOVA minimizes a regularized objective function that concerns both parameter and noisy return uncertainties. It is feasible when using non-linear approximation functions as DNNs and can estimate the value in both on-policy and off-policy settings. It can be incorporated as a policy evaluation component in policy optimization algorithms.

KungFu is a distributed ML library for TensorFlow that is designed to enable adaptive training. KungFu allows users to express high-level Adaptation Policies (APs) that describe how to change hyper- and system parameters during training. APs take real-time monitored metrics (e.g. signal-to-noise ratios and noise scale) as input and trigger control actions (e.g. cluster rescaling or synchronisation strategy updates). For execution, APs are translated into monitoring and control operators, which are embedded in the dataflow graph. APs exploit an efficient asynchronous collective communication layer, which ensures concurrency and consistency of monitoring and adaptation operations.

Method that adapts expectation-maximization (EM) to aggregate annotations that work on tasks with combined localization and classification like object detection and instance segmentation.

Our main contribution is the Guiding Points Network, where we integrate all information from the conditions to generate guiding points. By applying transformation matrices to scene entities (human/objects) with attention weighting, we can forecast the spanning of the target object.

Label Quality Model is an intermediate supervised task aimed at predicting the clean labels from noisy labels by leveraging rater features and a paired subset for supervision. The LQM technique assumes the existence of rater features and a subset of training data with both noisy and clean labels, which we call paired-subset. In real world scenarios, some level of label noise may be unavoidable. The LQM approach still works as long as the clean(er) label is less noisy than a label from a rater that is randomly selected from the pool, e.g., clean labels can be from either expert raters or aggregation of multiple raters. LQM is trained on the paired-subset using rater features and noisy label as input, and inferred on the entire training corpus. The output of LQM is used during model training as a more accurate alternative to the noisy labels.

** LayoutReader** is a sequence-to-sequence model for reading order detection that uses both textual and layout information, where the layout-aware language model LayoutLM is leveraged as an encoder. The generation step in the encoder-decoder structure tis modified to generate the reading order sequence. In the encoding stage, LayoutReader packs the pair of source and target segments into a contiguous input sequence of LayoutLM and carefully designs the self-attention mask to control the visibility between tokens. As shown in the Figure, LayoutReader allows the tokens in the source segment to attend to each other while preventing the tokens in the target segment from attending to the rightward context. If 1 means allowing and 0 means preventing, the detail of the mask $M$ is as follows: $$ M\_{i, j}= \begin{cases}1, & \text { if } i<j \text { or } i, j \in \operatorname{src} \\ 0, & \text { otherwise }\end{cases} $$ where $i, j$ are the indices in the packed input sequence, so they may be from source or target segments; $i, j \in$ src means both tokens are from source segment. In the decoding stage, since the source and target are reordered sequences, the prediction candidates can be constrained to the source segment. Therefore, we ask the model to predict the indices in the source sequence. The probability is calculated as follows: $$ \mathcal{P}\left(x_{k}=i \mid x_{<k}\right)=\frac{\exp \left(e_{i}^{T} h\_{k}+b\_{k}\right)}{\sum_{j} \exp \left(e\_{j}^{T} h_{k}+b\_{k}\right)} $$ where $i$ is an index in the source segment; $e\_{i}$ and $e\_{j}$ are the $\mathrm{i}$-th and $\mathrm{j}$-th input embeddings of the source segment; $h\_{k}$ is the hidden states at the $\mathrm{k}$-th time step; $b\_{k}$ is the bias at the $\mathrm{k}$-th time step.

LightAutoML is an AutoML solution targeted for financial services companies. A typical LightAutoML pipeline scheme is presented in the Figure, each pipeline containing: - Reader: object that receives raw data and task as input, calculates some useful metadata, performs initial data cleaning and decides about data manipulations that should be done before fitting different model types. - LightAutoML inner datasets that contains metadata and CV iterators that implements validation scheme for the datasets. - Multiple ML Pipelines that are stacked and/or blended to get a single prediction. An ML pipeline in LightAutoML is one or multiple ML models that share a single data preprocessing and validation scheme. The preprocessing step may have up to two feature selection steps, a feature engineering step or even just be empty if no preprocessing is needed. The ML pipelines can be computed independently on the same datasets and then blended together using averaging (or weighted averaging). Alternatively, a stacking ensemble scheme can be used to build multi level ensemble architectures.

The Linear Combination of Activations, or LinComb, is a type of activation function that has trainable parameters and uses the linear combination of other activation functions. $$LinComb(x) = \sum\limits_{i=0}^{n} w_i \mathcal{F}_i(x)$$

LiteSeg is a lightweight architecture for semantic segmentation that uses a deeper version of Atrous Spatial Pyramid Pooling module (ASPP) and applies short and long residual connections, and depthwise separable convolution, resulting in a faster, more efficient model.

Local Importance-based Pooling (LIP) is a pooling layer that can enhance discriminative features during the downsampling procedure by learning adaptive importance weights based on inputs. By using a learnable network $G$ in $F$, the importance function now is not limited in hand-crafted forms and able to learn the criterion for the discriminativeness of features. Also, the window size of LIP is restricted to be not less than stride to fully utilize the feature map and avoid the issue of fixed interval sampling scheme. More specifically, the importance function in LIP is implemented by a tiny fully convolutional network, which learns to produce the importance map based on inputs in an end-to-end manner.

Based on the theoretical analyses in RAN paper, a novel multi-scale backbone structure is designed in the paper. This structure enables the network to efficiently predict motion patterns with larger separable upper bounds by using optimized dilation convolution on high-resolution feature maps, while maintaining a capturable range of motion with low computational complexity. To quantify the network's capacity for large deformation capturing, the accessible motion capture range is defined as: Definition 1: Accessible Motion Range The radius of capture range of the $k^{\text{th}}$-level registration by the registration module$\mathcal{R}_k$ is defined as the smallest upper bound of its accessible Deformation Displacement Field: $$ a_k := \min_{\mathbf{x}}(\{\sup(\|\varphi_{k}[\mathbf{x}]\|_{\infty})\}) $$ where $\|\cdot\|_{\infty}$ denotes the L-$\infty$ norm of a vector, $\sup(\cdot)$ denotes the supremum or the maximum value of a given function with varying inputs and trainable weights of networks, and $\mathbf{x}$ denotes one coordinate entry of the images or Deformation Displacement Fields. To quantify the Degree-of-Freedom limitation in the discontinuity of the estimated Deformation Displacement Field, we define the separability of the predicted motion: Definition 2: Separability Bottleneck of Predicted Motion The motion separability bottleneck is defined as the minimum value of the upper bound of the Chebyshev difference of a network's predicted DDF $\phi$ between two locations $\mathbf{x}, \mathbf{y} \in \mathbb{Z}^d$ with the specific Chebyshev distance $p \in \mathbb{Z}^d$: $$ \Delta_\infty(p) := \min_{\mathbf{x}, \mathbf{y}}\left\{\sup(\|\phi[\mathbf{x}] - \phi[\mathbf{y}]\|_{\infty}) : \|\mathbf{x} - \mathbf{y}\|_{\infty} = p\right\} $$ where $p$ denotes the L-$\infty$ distance between the two pixels. Theorem: Regional Dependency The upper boundary of motion difference is related to $a_k$ and $p_k$: $$ \begin{align*} \forall \mathbf{x}, \mathbf{y} \in \mathbb{Z}^d, \|\mathbf{x} - \mathbf{y}\|_\infty \geq p_{k''} + 2\sum_{k'=k''+1}^{k} a_{k'}, &\quad \sup(\|\phi_{k}[\mathbf{x}] - \phi_{k}[\mathbf{y}]\|_\infty) \geq 2\sum_{k'=k''}^{k} a_{k'}; \\ \exists \mathbf{x}, \mathbf{y} \in \mathbb{Z}^d, \|\mathbf{x} - \mathbf{y}\|_\infty < p_{k''-1} + 2\sum_{k'=k''}^{k} a_{k'}, &\quad \sup(\|\phi_{k}[\mathbf{x}] - \phi_{k}[\mathbf{y}]\|_\infty) = 2\sum_{k'=k''}^{k} a_{k'}; \end{align*} $$ where $k'', k,$ denote two recursive numbers satisfying $0 \leq k'' < k$, and $\mathbf{x}, \mathbf{y}$ denote two coordinate entries of images or DDFs. Thus a Motion-Separable structure is designed with the upsampled feature maps processed by the corresponding atrous convolution layers.

Model Agnostic Confidence Estimator, or MACEst, is a model-agnostic confidence estimator. Using a set of nearest neighbours, the algorithm differs from other methods by estimating confidence independently as a local quantity which explicitly accounts for both aleatoric and epistemic uncertainty. This approach differs from standard calibration methods that use a global point prediction model as a starting point for the confidence estimate.

Memory-Associated Differential (MAD) Learning was developed to inference from the memorized facts that we already know to predict what we want to know. Image source: Luo et al.

The MADGRAD method contains a series of modifications to the AdaGrad-DA method to improve its performance on deep learning optimization problems. It gives state-of-the-art generalization performance across a diverse set of problems, including those that Adam normally under-performs on.

MEUZZ is a machine learning-based hybrid fuzzer which employs supervised machine learning for adaptive and generalizable seed scheduling -- a prominent factor in determining the yields of hybrid fuzzing. MEUZZ determines which new seeds are expected to produce better fuzzing yields based on the knowledge learned from past seed scheduling decisions made on the same or similar programs. MEUZZ's learning is based on a series of features extracted via code reachability and dynamic analysis, which incurs negligible runtime overhead (in microseconds). Moreover, MEUZZ automatically infers the data labels by evaluating the fuzzing performance of each selected seed.