PyTorchKR Papers

“Image Classification”

총 5,746편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2212.04097공식 코드 · Papers with Code

Generating and Weighting Semantically Consistent Sample Pairs for Ultrasound Contrastive Learning

Well-annotated medical datasets enable deep neural networks (DNNs) to gain strong power in extracting lesion-related features. Building such large and well-designed medical datasets is costly due to the need for high-level expertise. Model pre-training based on ImageNet is a common practice to gain better generalization when the data amount is limited. However, it suffers from the domain gap between natural and medical images. In this work, we pre-train DNNs on ultrasound (US) domains instead of ImageNet to reduce the domain gap in medical US applications. To learn US image representations based on unlabeled US videos, we propose a novel meta-learning-based contrastive learning method, namely Meta Ultrasound Contrastive Learning (Meta-USCL). To tackle the key challenge of obtaining semantically consistent sample pairs for contrastive learning, we present a positive pair generation module along with an automatic sample weighting module based on meta-learning. Experimental results on multiple computer-aided diagnosis (CAD) problems, including pneumonia detection, breast cancer classification, and breast tumor segmentation, show that the proposed self-supervised method reaches state-of-the-art (SOTA). The codes are available at https://github.com/Schuture/Meta-USCL.

arXiv:2302.02451공식 코드 · Papers with Code

KDEformer: Accelerating Transformers via Kernel Density Estimation

Dot-product attention mechanism plays a crucial role in modern deep architectures (e.g., Transformer) for sequence modeling, however, na\"ive exact computation of this model incurs quadratic time and memory complexities in sequence length, hindering the training of long-sequence models. Critical bottlenecks are due to the computation of partition functions in the denominator of softmax function as well as the multiplication of the softmax matrix with the matrix of values. Our key observation is that the former can be reduced to a variant of the kernel density estimation (KDE) problem, and an efficient KDE solver can be further utilized to accelerate the latter via subsampling-based fast matrix products. Our proposed KDEformer can approximate the attention in sub-quadratic time with provable spectral norm bounds, while all prior results merely provide entry-wise error bounds. Empirically, we verify that KDEformer outperforms other attention approximations in terms of accuracy, memory, and runtime on various pre-trained models. On BigGAN image generation, we achieve better generative scores than the exact computation with over $4\times$ speedup. For ImageNet classification with T2T-ViT, KDEformer shows over $18\times$ speedup while the accuracy drop is less than $0.5\%$.

arXiv:2304.05895공식 코드 · Papers with Code

Towards Understanding How Data Augmentation Works with Imbalanced Data

Data augmentation forms the cornerstone of many modern machine learning training pipelines; yet, the mechanisms by which it works are not clearly understood. Much of the research on data augmentation (DA) has focused on improving existing techniques, examining its regularization effects in the context of neural network over-fitting, or investigating its impact on features. Here, we undertake a holistic examination of the effect of DA on three different classifiers, convolutional neural networks, support vector machines, and logistic regression models, which are commonly used in supervised classification of imbalanced data. We support our examination with testing on three image and five tabular datasets. Our research indicates that DA, when applied to imbalanced data, produces substantial changes in model weights, support vectors and feature selection; even though it may only yield relatively modest changes to global metrics, such as balanced accuracy or F1 measure. We hypothesize that DA works by facilitating variances in data, so that machine learning models can associate changes in the data with labels. By diversifying the range of feature amplitudes that a model must recognize to predict a label, DA improves a model's capacity to generalize when learning with imbalanced data.

arXiv:2405.13985공식 코드 · Papers with Code

LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate

High-resolution images offer more information about scenes that can improve model accuracy. However, the dominant model architecture in computer vision, the vision transformer (ViT), cannot effectively leverage larger images without finetuning -- ViTs poorly extrapolate to more patches at test time, although transformers offer sequence length flexibility. We attribute this shortcoming to the current patch position encoding methods, which create a distribution shift when extrapolating. We propose a drop-in replacement for the position encoding of plain ViTs that restricts attention heads to fixed fields of view, pointed in different directions, using 2D attention masks. Our novel method, called LookHere, provides translation-equivariance, ensures attention head diversity, and limits the distribution shift that attention heads face when extrapolating. We demonstrate that LookHere improves performance on classification (avg. 1.6%), against adversarial attack (avg. 5.4%), and decreases calibration error (avg. 1.5%) -- on ImageNet without extrapolation. With extrapolation, LookHere outperforms the current SoTA position encoding method, 2D-RoPE, by 21.7% on ImageNet when trained at $224^2$ px and tested at $1024^2$ px. Additionally, we release a high-resolution test set to improve the evaluation of high-resolution image classifiers, called ImageNet-HR.

arXiv:2406.08840공식 코드 · Papers with Code

Conceptual Learning via Embedding Approximations for Reinforcing Interpretability and Transparency

Concept bottleneck models (CBMs) have emerged as critical tools in domains where interpretability is paramount. These models rely on predefined textual descriptions, referred to as concepts, to inform their decision-making process and offer more accurate reasoning. As a result, the selection of concepts used in the model is of utmost significance. This study proposes \underline{\textbf{C}}onceptual \underline{\textbf{L}}earning via \underline{\textbf{E}}mbedding \underline{\textbf{A}}pproximations for \underline{\textbf{R}}einforcing Interpretability and Transparency, abbreviated as CLEAR, a framework for constructing a CBM for image classification. Using score matching and Langevin sampling, we approximate the embedding of concepts within the latent space of a vision-language model (VLM) by learning the scores associated with the joint distribution of images and concepts. A concept selection process is then employed to optimize the similarity between the learned embeddings and the predefined ones. The derived bottleneck offers insights into the CBM's decision-making process, enabling more comprehensive interpretations. Our approach was evaluated through extensive experiments and achieved state-of-the-art performance on various benchmarks. The code for our experiments is available at https://github.com/clearProject/CLEAR/tree/main

arXiv:2506.01942v3cs.CV공식 코드 · Papers with Code

OD3: 객체 검출을 위한 최적화 없는 데이터셋 증류

OD3: Optimization-free Dataset Distillation for Object Detection

대규모 데이터셋으로 큰 신경망을 학습하려면 상당한 계산 자원이 필요하며, 특히 객체 검출과 같은 밀집 예측(dense prediction) 작업에서 그렇다. 데이터셋 증류(DD)는 더 큰 데이터셋으로부터 소형 데이터셋을 합성하여 이러한 부담을 줄이려는 방법으로 제안되었지만, 기존 연구의 대부분은 이미지 분류에만 집중하여 더 복잡한 검출 설정은 거의 다루지 않았다. 본 논문에서는 객체 검출을 위해 특별히 설계된 새로운 최적화 없는 데이터 증류 프레임워크인 OD3를 제안한다. 우리 접근법은 두 단계로 이루어진다. 첫째, 객체 인스턴스를 적합한 위치에 따라 합성 이미지에 반복적으로 배치하는 후보 선택 과정이고, 둘째, 사전학습된 observer 모델로 낮은 신뢰도 객체를 제거하는 후보 스크리닝 과정이다. MS COCO와 PASCAL VOC라는 두 대표적인 검출 데이터셋에서 압축률 0.25%부터 5%까지 데이터 합성 프레임워크를 적용하였다. 검출을 위한 기존 유일한 데이터셋 증류 방법 및 기존 코어셋 선택(core set selection) 방법과 비교했을 때, OD3는 더 높은 정확도를 보이며 새로운 최신(state-of-the-art) 결과를 달성하고, 압축률 1.0%에서 COCO mAP50 기준 이전 최고 방법보다 14% 이상 앞선다. 코드는 https://github.com/VILA-Lab/OD3 에서 제공된다.

arXiv:2404.13648공식 코드 · Papers with Code

Data-independent Module-aware Pruning for Hierarchical Vision Transformers

Hierarchical vision transformers (ViTs) have two advantages over conventional ViTs. First, hierarchical ViTs achieve linear computational complexity with respect to image size by local self-attention. Second, hierarchical ViTs create hierarchical feature maps by merging image patches in deeper layers for dense prediction. However, existing pruning methods ignore the unique properties of hierarchical ViTs and use the magnitude value as the weight importance. This approach leads to two main drawbacks. First, the "local" attention weights are compared at a "global" level, which may cause some "locally" important weights to be pruned due to their relatively small magnitude "globally". The second issue with magnitude pruning is that it fails to consider the distinct weight distributions of the network, which are essential for extracting coarse to fine-grained features at various hierarchical levels. To solve the aforementioned issues, we have developed a Data-independent Module-Aware Pruning method (DIMAP) to compress hierarchical ViTs. To ensure that "local" attention weights at different hierarchical levels are compared fairly in terms of their contribution, we treat them as a module and examine their contribution by analyzing their information distortion. Furthermore, we introduce a novel weight metric that is solely based on weights and does not require input images, thereby eliminating the dependence on the patch merging process. Our method validates its usefulness and strengths on Swin Transformers of different sizes on ImageNet-1k classification. Notably, the top-5 accuracy drop is only 0.07% when we remove 52.5% FLOPs and 52.7% parameters of Swin-B. When we reduce 33.2% FLOPs and 33.2% parameters of Swin-S, we can even achieve a 0.8% higher relative top-5 accuracy than the original model. Code is available at: https://github.com/he-y/Data-independent-Module-Aware-Pruning

arXiv:1710.00925공식 코드 · Papers with Code

Fine-Grained Head Pose Estimation Without Keypoints

Estimating the head pose of a person is a crucial problem that has a large amount of applications such as aiding in gaze estimation, modeling attention, fitting 3D models to video and performing face alignment. Traditionally head pose is computed by estimating some keypoints from the target face and solving the 2D to 3D correspondence problem with a mean human head model. We argue that this is a fragile method because it relies entirely on landmark detection performance, the extraneous head model and an ad-hoc fitting step. We present an elegant and robust way to determine pose by training a multi-loss convolutional neural network on 300W-LP, a large synthetically expanded dataset, to predict intrinsic Euler angles (yaw, pitch and roll) directly from image intensities through joint binned pose classification and regression. We present empirical tests on common in-the-wild pose benchmark datasets which show state-of-the-art results. Additionally we test our method on a dataset usually used for pose estimation using depth and start to close the gap with state-of-the-art depth pose methods. We open-source our training and testing code as well as release our pre-trained models.

arXiv:1806.06987공식 코드 · Papers with Code

Fast Multiple Landmark Localisation Using a Patch-based Iterative Network

We propose a new Patch-based Iterative Network (PIN) for fast and accurate landmark localisation in 3D medical volumes. PIN utilises a Convolutional Neural Network (CNN) to learn the spatial relationship between an image patch and anatomical landmark positions. During inference, patches are repeatedly passed to the CNN until the estimated landmark position converges to the true landmark location. PIN is computationally efficient since the inference stage only selectively samples a small number of patches in an iterative fashion rather than a dense sampling at every location in the volume. Our approach adopts a multi-task learning framework that combines regression and classification to improve localisation accuracy. We extend PIN to localise multiple landmarks by using principal component analysis, which models the global anatomical relationships between landmarks. We have evaluated PIN using 72 3D ultrasound images from fetal screening examinations. PIN achieves quantitatively an average landmark localisation error of 5.59mm and a runtime of 0.44s to predict 10 landmarks per volume. Qualitatively, anatomical 2D standard scan planes derived from the predicted landmark locations are visually similar to the clinical ground truth. Source code is publicly available at https://github.com/yuanwei1989/landmark-detection.

arXiv:1904.06593공식 코드 · Papers with Code

Shakeout: A New Approach to Regularized Deep Neural Network Training

Recent years have witnessed the success of deep neural networks in dealing with a plenty of practical problems. Dropout has played an essential role in many successful deep neural networks, by inducing regularization in the model training. In this paper, we present a new regularized training approach: Shakeout. Instead of randomly discarding units as Dropout does at the training stage, Shakeout randomly chooses to enhance or reverse each unit's contribution to the next layer. This minor modification of Dropout has the statistical trait: the regularizer induced by Shakeout adaptively combines $L_0$, $L_1$ and $L_2$ regularization terms. Our classification experiments with representative deep architectures on image datasets MNIST, CIFAR-10 and ImageNet show that Shakeout deals with over-fitting effectively and outperforms Dropout. We empirically demonstrate that Shakeout leads to sparser weights under both unsupervised and supervised settings. Shakeout also leads to the grouping effect of the input units in a layer. Considering the weights in reflecting the importance of connections, Shakeout is superior to Dropout, which is valuable for the deep model compression. Moreover, we demonstrate that Shakeout can effectively reduce the instability of the training process of the deep architecture.

arXiv:1910.00643공식 코드 · Papers with Code

SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum

Distributed optimization is essential for training large models on large datasets. Multiple approaches have been proposed to reduce the communication overhead in distributed training, such as synchronizing only after performing multiple local SGD steps, and decentralized methods (e.g., using gossip algorithms) to decouple communications among workers. Although these methods run faster than AllReduce-based methods, which use blocking communication before every update, the resulting models may be less accurate after the same number of updates. Inspired by the BMUF method of Chen & Huo (2016), we propose a slow momentum (SlowMo) framework, where workers periodically synchronize and perform a momentum update, after multiple iterations of a base optimization algorithm. Experiments on image classification and machine translation tasks demonstrate that SlowMo consistently yields improvements in optimization and generalization performance relative to the base optimizer, even when the additional overhead is amortized over many updates so that the SlowMo runtime is on par with that of the base optimizer. We provide theoretical convergence guarantees showing that SlowMo converges to a stationary point of smooth non-convex losses. Since BMUF can be expressed through the SlowMo framework, our results also correspond to the first theoretical convergence guarantees for BMUF.

arXiv:1910.05577공식 코드 · Papers with Code

Context-Gated Convolution

As the basic building block of Convolutional Neural Networks (CNNs), the convolutional layer is designed to extract local patterns and lacks the ability to model global context in its nature. Many efforts have been recently devoted to complementing CNNs with the global modeling ability, especially by a family of works on global feature interaction. In these works, the global context information is incorporated into local features before they are fed into convolutional layers. However, research on neuroscience reveals that the neurons' ability of modifying their functions dynamically according to context is essential for the perceptual tasks, which has been overlooked in most of CNNs. Motivated by this, we propose one novel Context-Gated Convolution (CGC) to explicitly modify the weights of convolutional layers adaptively under the guidance of global context. As such, being aware of the global context, the modulated convolution kernel of our proposed CGC can better extract representative local patterns and compose discriminative features. Moreover, our proposed CGC is lightweight and applicable with modern CNN architectures, and consistently improves the performance of CNNs according to extensive experiments on image classification, action recognition, and machine translation. Our code of this paper is available at https://github.com/XudongLinthu/context-gated-convolution.

arXiv:2011.12450공식 코드 · Papers with Code

Sparse R-CNN: End-to-End Object Detection with Learnable Proposals

We present Sparse R-CNN, a purely sparse method for object detection in images. Existing works on object detection heavily rely on dense object candidates, such as $k$ anchor boxes pre-defined on all grids of image feature map of size $H\times W$. In our method, however, a fixed sparse set of learned object proposals, total length of $N$, are provided to object recognition head to perform classification and location. By eliminating $HWk$ (up to hundreds of thousands) hand-designed object candidates to $N$ (e.g. 100) learnable proposals, Sparse R-CNN completely avoids all efforts related to object candidates design and many-to-one label assignment. More importantly, final predictions are directly output without non-maximum suppression post-procedure. Sparse R-CNN demonstrates accuracy, run-time and training convergence performance on par with the well-established detector baselines on the challenging COCO dataset, e.g., achieving 45.0 AP in standard $3\times$ training schedule and running at 22 fps using ResNet-50 FPN model. We hope our work could inspire re-thinking the convention of dense prior in object detectors. The code is available at: https://github.com/PeizeSun/SparseR-CNN.

arXiv:2103.05950공식 코드 · Papers with Code

FSCE: Few-Shot Object Detection via Contrastive Proposal Encoding

Emerging interests have been brought to recognize previously unseen objects given very few training examples, known as few-shot object detection (FSOD). Recent researches demonstrate that good feature embedding is the key to reach favorable few-shot learning performance. We observe object proposals with different Intersection-of-Union (IoU) scores are analogous to the intra-image augmentation used in contrastive approaches. And we exploit this analogy and incorporate supervised contrastive learning to achieve more robust objects representations in FSOD. We present Few-Shot object detection via Contrastive proposals Encoding (FSCE), a simple yet effective approach to learning contrastive-aware object proposal encodings that facilitate the classification of detected objects. We notice the degradation of average precision (AP) for rare objects mainly comes from misclassifying novel instances as confusable classes. And we ease the misclassification issues by promoting instance level intra-class compactness and inter-class variance via our contrastive proposal encoding loss (CPE loss). Our design outperforms current state-of-the-art works in any shot and all data splits, with up to +8.8% on standard benchmark PASCAL VOC and +2.7% on challenging COCO benchmark. Code is available at: https: //github.com/MegviiDetection/FSCE

arXiv:2103.15365공식 코드 · Papers with Code

Visual Distant Supervision for Scene Graph Generation

Scene graph generation aims to identify objects and their relations in images, providing structured image representations that can facilitate numerous applications in computer vision. However, scene graph models usually require supervised learning on large quantities of labeled data with intensive human annotation. In this work, we propose visual distant supervision, a novel paradigm of visual relation learning, which can train scene graph models without any human-labeled data. The intuition is that by aligning commonsense knowledge bases and images, we can automatically create large-scale labeled data to provide distant supervision for visual relation learning. To alleviate the noise in distantly labeled data, we further propose a framework that iteratively estimates the probabilistic relation labels and eliminates the noisy ones. Comprehensive experimental results show that our distantly supervised model outperforms strong weakly supervised and semi-supervised baselines. By further incorporating human-labeled data in a semi-supervised fashion, our model outperforms state-of-the-art fully supervised models by a large margin (e.g., 8.3 micro- and 7.8 macro-recall@50 improvements for predicate classification in Visual Genome evaluation). We make the data and code for this paper publicly available at https://github.com/thunlp/VisualDS.

arXiv:2104.04163공식 코드 · Papers with Code

Combined Depth Space based Architecture Search For Person Re-identification

Most works on person re-identification (ReID) take advantage of large backbone networks such as ResNet, which are designed for image classification instead of ReID, for feature extraction. However, these backbones may not be computationally efficient or the most suitable architectures for ReID. In this work, we aim to design a lightweight and suitable network for ReID. We propose a novel search space called Combined Depth Space (CDS), based on which we search for an efficient network architecture, which we call CDNet, via a differentiable architecture search algorithm. Through the use of the combined basic building blocks in CDS, CDNet tends to focus on combined pattern information that is typically found in images of pedestrians. We then propose a low-cost search strategy named the Top-k Sample Search strategy to make full use of the search space and avoid trapping in local optimal result. Furthermore, an effective Fine-grained Balance Neck (FBLNeck), which is removable at the inference time, is presented to balance the effects of triplet loss and softmax loss during the training process. Extensive experiments show that our CDNet (~1.8M parameters) has comparable performance with state-of-the-art lightweight networks.

arXiv:2108.00708공식 코드 · Papers with Code

Group Fisher Pruning for Practical Network Compression

Network compression has been widely studied since it is able to reduce the memory and computation cost during inference. However, previous methods seldom deal with complicated structures like residual connections, group/depth-wise convolution and feature pyramid network, where channels of multiple layers are coupled and need to be pruned simultaneously. In this paper, we present a general channel pruning approach that can be applied to various complicated structures. Particularly, we propose a layer grouping algorithm to find coupled channels automatically. Then we derive a unified metric based on Fisher information to evaluate the importance of a single channel and coupled channels. Moreover, we find that inference speedup on GPUs is more correlated with the reduction of memory rather than FLOPs, and thus we employ the memory reduction of each channel to normalize the importance. Our method can be used to prune any structures including those with coupled channels. We conduct extensive experiments on various backbones, including the classic ResNet and ResNeXt, mobile-friendly MobileNetV2, and the NAS-based RegNet, both on image classification and object detection which is under-explored. Experimental results validate that our method can effectively prune sophisticated networks, boosting inference speed without sacrificing accuracy.

arXiv:2108.11535공식 코드 · Papers with Code

ChessMix: Spatial Context Data Augmentation for Remote Sensing Semantic Segmentation

Labeling semantic segmentation datasets is a costly and laborious process if compared with tasks like image classification and object detection. This is especially true for remote sensing applications that not only work with extremely high spatial resolution data but also commonly require the knowledge of experts of the area to perform the manual labeling. Data augmentation techniques help to improve deep learning models under the circumstance of few and imbalanced labeled samples. In this work, we propose a novel data augmentation method focused on exploring the spatial context of remote sensing semantic segmentation. This method, ChessMix, creates new synthetic images from the existing training set by mixing transformed mini-patches across the dataset in a chessboard-like grid. ChessMix prioritizes patches with more examples of the rarest classes to alleviate the imbalance problems. The results in three diverse well-known remote sensing datasets show that this is a promising approach that helps to improve the networks' performance, working especially well in datasets with few available data. The results also show that ChessMix is capable of improving the segmentation of objects with few labeled pixels when compared to the most common data augmentation methods widely used.

arXiv:2112.09747공식 코드 · Papers with Code

A Simple Single-Scale Vision Transformer for Object Localization and Instance Segmentation

This work presents a simple vision transformer design as a strong baseline for object localization and instance segmentation tasks. Transformers recently demonstrate competitive performance in image classification tasks. To adopt ViT to object detection and dense prediction tasks, many works inherit the multistage design from convolutional networks and highly customized ViT architectures. Behind this design, the goal is to pursue a better trade-off between computational cost and effective aggregation of multiscale global contexts. However, existing works adopt the multistage architectural design as a black-box solution without a clear understanding of its true benefits. In this paper, we comprehensively study three architecture design choices on ViT -- spatial reduction, doubled channels, and multiscale features -- and demonstrate that a vanilla ViT architecture can fulfill this goal without handcrafting multiscale features, maintaining the original ViT design philosophy. We further complete a scaling rule to optimize our model's trade-off on accuracy and computation cost / model size. By leveraging a constant feature resolution and hidden size throughout the encoder blocks, we propose a simple and compact ViT architecture called Universal Vision Transformer (UViT) that achieves strong performance on COCO object detection and instance segmentation tasks.

arXiv:2206.05981공식 코드 · Papers with Code

Efficient Human-in-the-loop System for Guiding DNNs Attention

Attention guidance is an approach to addressing dataset bias in deep learning, where the model relies on incorrect features to make decisions. Focusing on image classification tasks, we propose an efficient human-in-the-loop system to interactively direct the attention of classifiers to the regions specified by users, thereby reducing the influence of co-occurrence bias and improving the transferability and interpretability of a DNN. Previous approaches for attention guidance require the preparation of pixel-level annotations and are not designed as interactive systems. We present a new interactive method to allow users to annotate images with simple clicks, and study a novel active learning strategy to significantly reduce the number of annotations. We conducted both a numerical evaluation and a user study to evaluate the proposed system on multiple datasets. Compared to the existing non-active-learning approach which usually relies on huge amounts of polygon-based segmentation masks to fine-tune or train the DNNs, our system can save lots of labor and money and obtain a fine-tuned network that works better even when the dataset is biased. The experiment results indicate that the proposed system is efficient, reasonable, and reliable.