PyTorchKR Papers

“Image Classification”

총 18,403편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:1709.03582

Art of singular vectors and universal adversarial perturbations

Vulnerability of Deep Neural Networks (DNNs) to adversarial attacks has been attracting a lot of attention in recent studies. It has been shown that for many state of the art DNNs performing image classification there exist universal adversarial perturbations --- image-agnostic perturbations mere addition of which to natural images with high probability leads to their misclassification. In this work we propose a new algorithm for constructing such universal perturbations. Our approach is based on computing the so-called $(p, q)$-singular vectors of the Jacobian matrices of hidden layers of a network. Resulting perturbations present interesting visual patterns, and by using only 64 images we were able to construct universal perturbations with more than 60 \% fooling rate on the dataset consisting of 50000 images. We also investigate a correlation between the maximal singular value of the Jacobian matrix and the fooling rate of the corresponding singular vector, and show that the constructed perturbations generalize across networks.

arXiv:1811.04380

ReSet: Learning Recurrent Dynamic Routing in ResNet-like Neural Networks

Neural Network is a powerful Machine Learning tool that shows outstanding performance in Computer Vision, Natural Language Processing, and Artificial Intelligence. In particular, recently proposed ResNet architecture and its modifications produce state-of-the-art results in image classification problems. ResNet and most of the previously proposed architectures have a fixed structure and apply the same transformation to all input images. In this work, we develop a ResNet-based model that dynamically selects Computational Units (CU) for each input object from a learned set of transformations. Dynamic selection allows the network to learn a sequence of useful transformations and apply only required units to predict the image label. We compare our model to ResNet-38 architecture and achieve better results than the original ResNet on CIFAR-10.1 test set. While examining the produced paths, we discovered that the network learned different routes for images from different classes and similar routes for similar images.

arXiv:1902.11111

Target-based Hyperspectral Demixing via Generalized Robust PCA

Localizing targets of interest in a given hyperspectral (HS) image has applications ranging from remote sensing to surveillance. This task of target detection leverages the fact that each material/object possesses its own characteristic spectral response, depending upon its composition. As $\textit{signatures}$ of different materials are often correlated, matched filtering based approaches may not be appropriate in this case. In this work, we present a technique to localize targets of interest based on their spectral signatures. We also present the corresponding recovery guarantees, leveraging our recent theoretical results. To this end, we model a HS image as a superposition of a low-rank component and a dictionary sparse component, wherein the dictionary consists of the $\textit{a priori}$ known characteristic spectral responses of the target we wish to localize. Finally, we analyze the performance of the proposed approach via experimental validation on real HS data for a classification task, and compare it with related techniques.

arXiv:2003.11617

Covid-19: Automatic detection from X-Ray images utilizing Transfer Learning with Convolutional Neural Networks

In this study, a dataset of X-Ray images from patients with common pneumonia, Covid-19, and normal incidents was utilized for the automatic detection of the Coronavirus. The aim of the study is to evaluate the performance of state-of-the-art Convolutional Neural Network architectures proposed over recent years for medical image classification. Specifically, the procedure called transfer learning was adopted. With transfer learning, the detection of various abnormalities in small medical image datasets is an achievable target, often yielding remarkable results. The dataset utilized in this experiment is a collection of 1427 X-Ray images. 224 images with confirmed Covid-19, 700 images with confirmed common pneumonia, and 504 images of normal conditions are included. The data was collected from the available X-Ray images on public medical repositories. With transfer learning, an overall accuracy of 97.82% in the detection of Covid-19 is achieved.

arXiv:2104.11227공식 코드 · Papers with Code

Multiscale Vision Transformers

We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. Multiscale Transformers have several channel-resolution scale stages. Starting from the input resolution and a small channel dimension, the stages hierarchically expand the channel capacity while reducing the spatial resolution. This creates a multiscale pyramid of features with early layers operating at high spatial resolution to model simple low-level visual information, and deeper layers at spatially coarse, but complex, high-dimensional features. We evaluate this fundamental architectural prior for modeling the dense nature of visual signals for a variety of video recognition tasks where it outperforms concurrent vision transformers that rely on large scale external pre-training and are 5-10x more costly in computation and parameters. We further remove the temporal dimension and apply our model for image classification where it outperforms prior work on vision transformers. Code is available at: https://github.com/facebookresearch/SlowFast

arXiv:2408.11804공식 코드 · Papers with Code

Approaching Deep Learning through the Spectral Dynamics of Weights

We propose an empirical approach centered on the spectral dynamics of weights -- the behavior of singular values and vectors during optimization -- to unify and clarify several phenomena in deep learning. We identify a consistent bias in optimization across various experiments, from small-scale ``grokking'' to large-scale tasks like image classification with ConvNets, image generation with UNets, speech recognition with LSTMs, and language modeling with Transformers. We also demonstrate that weight decay enhances this bias beyond its role as a norm regularizer, even in practical systems. Moreover, we show that these spectral dynamics distinguish memorizing networks from generalizing ones, offering a novel perspective on this longstanding conundrum. Additionally, we leverage spectral dynamics to explore the emergence of well-performing sparse subnetworks (lottery tickets) and the structure of the loss surface through linear mode connectivity. Our findings suggest that spectral dynamics provide a coherent framework to better understand the behavior of neural networks across diverse settings.

arXiv:2409.18314공식 코드 · Papers with Code

Realistic Evaluation of Model Merging for Compositional Generalization

Merging has become a widespread way to cheaply combine individual models into a single model that inherits their capabilities and attains better performance. This popularity has spurred rapid development of many new merging methods, which are typically validated in disparate experimental settings and frequently differ in the assumptions made about model architecture, data availability, and computational budget. In this work, we characterize the relative merits of different merging methods by evaluating them in a shared experimental setting and precisely identifying the practical requirements of each method. Specifically, our setting focuses on using merging for compositional generalization of capabilities in image classification, image generation, and natural language processing. Additionally, we measure the computational costs of different merging methods as well as how they perform when scaling the number of models being merged. Taken together, our results clarify the state of the field of model merging and provide a comprehensive and rigorous experimental setup to test new methods.

arXiv:2410.07081공식 코드 · Papers with Code

JPEG Inspired Deep Learning

Although it is traditionally believed that lossy image compression, such as JPEG compression, has a negative impact on the performance of deep neural networks (DNNs), it is shown by recent works that well-crafted JPEG compression can actually improve the performance of deep learning (DL). Inspired by this, we propose JPEG-DL, a novel DL framework that prepends any underlying DNN architecture with a trainable JPEG compression layer. To make the quantization operation in JPEG compression trainable, a new differentiable soft quantizer is employed at the JPEG layer, and then the quantization operation and underlying DNN are jointly trained. Extensive experiments show that in comparison with the standard DL, JPEG-DL delivers significant accuracy improvements across various datasets and model architectures while enhancing robustness against adversarial attacks. Particularly, on some fine-grained image classification datasets, JPEG-DL can increase prediction accuracy by as much as 20.9%. Our code is available on https://github.com/JpegInspiredDl/JPEG-Inspired-DL.git.

arXiv:2607.11509v2cs.CV

CFR-Net: 의료 영상 이상치 탐지를 위한 협력적 특징 정제 네트워크

CFR-Net:Collaborative Feature Refinement Network for Medical Image Anomaly Detection

자연 영상으로 사전학습된 네트워크는 비정상 패턴이 미세한 국소적 변화, 다중 스케일 문맥 불일치, 방향에 민감한 구조적 편차로 나타나는 의료 영상에 대해 제한적인 적응성을 보이는 경우가 많아, 의료 영상 이상치 탐지는 여전히 어려운 과제로 남아 있습니다. 이를 해결하기 위해 디코딩 전 공유된 교사-학생 특징 정제와 디코딩 후 공간 간 일관성을 결합한 협력적 특징 정제 네트워크(CFR-Net)를 제안합니다. CFR-Net은 파라미터를 공유하는 다중 경로 특징 정제 모듈(MPFRM)을 사용하여 동결된 교사 특징과 학습 가능한 학생 특징을 정제하며, 일반적인 시각적 참조와 의료 도메인에 적응된 표현에 공통의 다중 경로 정제 규칙을 적용합니다. 이를 통해 도메인 불일치를 완화하는 동시에 국소적, 다중 스케일, 방향에 민감한 특징 특성을 모델링합니다. 또한 분산 민감 목적 함수와 동적 '숙제 세트' 재구성을 통해 층 적응형 일관성 학습을 추가로 지원합니다. 의료 벤치마크에 대한 실험 결과는 정상 데이터로만 학습했을 때 CFR-Net이 경쟁력 있는 이상치 분류 및 우수한 이상치 위치 추정 성능을 달성함을 보여줍니다.

arXiv:2608.21792v1cs.AI

HIRA: 규제 산업 문서 분류를 위한 휴먼-인-더-루프 검색-증강 캐스케이드

HIRA: A Human-in-the-Loop Retrieval-Augmented Cascade for Document Classification in Regulated Industries

규제 산업의 문서 분류는 데이터 상주(data residency) 요건, 제한적인 콜드 스타트 레이블, 부족한 검토 인력, 그리고 비용이 많이 드는 모델 거버넌스 절차로 인해 제약을 받는다. 본 논문에서는 규제 환경 배포를 위한 문서 분류용 학습이 필요 없는(training-free) 온프레미스 검색-증강 캐스케이드인 HIRA를 제안한다. HIRA는 OCR 텍스트에 대한 BM25, 밀집 텍스트 임베딩(dense text embedding), 이미지 수준 표현을 검증 데이터로 보정한 가중 역순위 결합(weighted reciprocal-rank fusion)을 통해 결합한다. 확신도가 높은 문서는 검색만으로 직접 분류되며, 불확실하거나 시각적으로 혼동되기 쉬운 문서는 로컬에서 호스팅되는 LLM 검증기(verifier)로 전달된다. 이 검증기는 OCR 텍스트, 검색된 예시(exemplar), 레이블 설명, 그리고 혼동 유형별 용어를 입력으로 받는다. 검증기 역시 불확실한 경우 해당 문서는 사람의 검토로 넘겨진다. 각 수정 사항은 마진 가중(margin-weighted) 검색 예시로 저장되고 Dirichlet 평활(Dirichlet-smoothed) 혼동 그래프를 갱신하므로, 시스템은 모델 가중치를 업데이트하지 않고도 성능을 개선할 수 있다. 비공개 80개 클래스 무역금융 코퍼스에서 HIRA는 실제 운영 스트림 30,233건 전체를 처리하면서 사람의 수정은 1,945건(6.4%)에 대해서만 요청하였고, Macro-F1을 0.6218에서 0.8548로 향상시켰다. 수정된 Tobacco-3482 벤치마크에서 HIRA는 로컬에서 호스팅되는 DeepSeek-R1-Distill-Qwen-32B 검증기를 사용하여 Macro-F1 0.9423을 달성했으며, 이는 제로샷 LLM 기준선보다 17.4%p 높은 수치이다. 이때 검증기는 전체 문서의 약 40%에 대해서만 호출되어 LLM 호출이 약 60% 감소했다. 사람의 수정 518건(풀의 24.8%)만으로 HIRA는 풀 전체 문서 2,086건을 정답 레이블과 함께 색인한 완전 레이블 풀 오라클(fully labelled pool oracle)과 동등한 성능을 보였다. 이러한 결과는 선별적인 사람의 피드백과 검색 메모리 기반 적응이, 규제 환경에 배포된 롱테일 문서 분류에서 반복적인 모델 재학습을 대체할 수 있는 실용적인 대안이 될 수 있음을 보여준다.

arXiv:2405.08911

CLIP with Quality Captions: A Strong Pretraining for Vision Tasks

CLIP models perform remarkably well on zero-shot classification and retrieval tasks. But recent studies have shown that learnt representations in CLIP are not well suited for dense prediction tasks like object detection, semantic segmentation or depth estimation. More recently, multi-stage training methods for CLIP models was introduced to mitigate the weak performance of CLIP on downstream tasks. In this work, we find that simply improving the quality of captions in image-text datasets improves the quality of CLIP's visual representations, resulting in significant improvement on downstream dense prediction vision tasks. In fact, we find that CLIP pretraining with good quality captions can surpass recent supervised, self-supervised and weakly supervised pretraining methods. We show that when CLIP model with ViT-B/16 as image encoder is trained on well aligned image-text pairs it obtains 12.1% higher mIoU and 11.5% lower RMSE on semantic segmentation and depth estimation tasks over recent state-of-the-art Masked Image Modeling (MIM) pretraining methods like Masked Autoencoder (MAE). We find that mobile architectures also benefit significantly from CLIP pretraining. A recent mobile vision architecture, MCi2, with CLIP pretraining obtains similar performance as Swin-L, pretrained on ImageNet-22k for semantic segmentation task while being 6.1$\times$ smaller. Moreover, we show that improving caption quality results in $10\times$ data efficiency when finetuning for dense prediction tasks.

arXiv:2406.11331

They're All Doctors: Synthesizing Diverse Counterfactuals to Mitigate Associative Bias

Vision Language Models (VLMs) such as CLIP are powerful models; however they can exhibit unwanted biases, making them less safe when deployed directly in applications such as text-to-image, text-to-video retrievals, reverse search, or classification tasks. In this work, we propose a novel framework to generate synthetic counterfactual images to create a diverse and balanced dataset that can be used to fine-tune CLIP. Given a set of diverse synthetic base images from text-to-image models, we leverage off-the-shelf segmentation and inpainting models to place humans with diverse visual appearances in context. We show that CLIP trained on such datasets learns to disentangle the human appearance from the context of an image, i.e., what makes a doctor is not correlated to the person's visual appearance, like skin color or body type, but to the context, such as background, the attire they are wearing, or the objects they are holding. We demonstrate that our fine-tuned CLIP model, $CF_\alpha$, improves key fairness metrics such as MaxSkew, MinSkew, and NDKL by 40-66\% for image retrieval tasks, while still achieving similar levels of performance in downstream tasks. We show that, by design, our model retains maximal compatibility with the original CLIP models, and can be easily controlled to support different accuracy versus fairness trade-offs in a plug-n-play fashion.

논문 ID: document/9424414

Fast Adaptive Meta-Learning for Few-Shot Image Generation

Generative Adversarial Networks (GANs) are capable of effectively synthesising new realistic images and estimating the potential distribution of samples utilising adversarial learning. Nevertheless, conventional GANs require a large amount of training data samples to produce plausible results. Inspired by the capacity for humans to quickly learn new concepts from a small number of examples, several meta-learning approaches for the few-shot datasets are presented. However, most of meta-learning algorithms are designed to tackle few-shot classification and reinforcement learning tasks. Moreover, the existing meta-learning models for image generation are complex, thereby affecting the length of training time required. Fast Adaptive Meta-Learning (FAML) based on GAN and the encoder network is proposed in this study for few-shot image generation. This model demonstrates the capability to generate new realistic images from previously unseen target classes with only a small number of examples required. With 10 times faster convergence, FAML requires only one-fourth of the trainable parameters in comparison baseline models by training a simpler network with conditional feature vectors from the encoder, while increasing the number of generator iterations. The visualisation results are demonstrated in the paper. This model is able to improve few-shot image generation with the lowest FID score, highest IS, and comparable LPIPS to MNIST, Omniglot, VGG-Faces, and miniImageNet datasets. The source code is available on https://github.com/phaphuang/FAML.

arXiv:2607.23673v1cs.CV

다중 모달 원격 탐사 영상 생성을 위한 대조적 매개변수 분리

Contrastive Parameter Disentanglement for Multi-modal Remote Sensing Image Generation

기존 원격 탐사 영상 생성 방법은 대부분 단일 모달리티 합성에 국한되어 있어, 다중 모달 영상에 내재된 상보적 정보를 활용하지 못한다. 이 한계를 해결하기 위해, 우리는 다중 모달 원격 탐사 영상 생성을 위한 대조적 매개변수 분리(contrastive parameter disentanglement) 프레임워크를 제안한다. 이 프레임워크는 단일 텍스트 프롬프트로부터 광학(optical), 적외선(infrared), 합성개구레이더(SAR, synthetic aperture radar) 등 여러 모달리티에 걸쳐 의미적으로 일관되고 구조적으로 정렬된 영상을 생성한다. 구체적으로, 우리는 직교 코어 부공간(orthogonal core subspace) 내에서 매개변수 수준에서 공유 의미와 모달리티별 속성을 분리하는 대조적 매개변수 분리 모듈을 도입한다. 이 모듈을 기반으로, 우리는 먼저 LoRA 어댑터의 매개변수 행렬 A가 다중 모달 대조 목적 함수를 통해 모달리티 불변 의미를 포착하도록 제약하고, 이어서 텍스트 조건화(text conditioning) 하에 여러 매개변수 행렬 B가 모달리티별 속성을 학습하도록 유도하는 분리 최적화 전략을 개발한다. 이 전략은 일관된 의미 내용과 뚜렷한 모달리티 특성을 갖는 다중 모달 영상의 동시 생성을 가능하게 한다. 또한 생성된 영상 간 구조적 정렬을 보장하기 위해, 우리는 추론 시 앵커(anchor) 모달리티로부터 나머지 모달리티로 구조적 상관 사전(structural correlation priors)을 전달함으로써 다중 모달 샘플링 궤적을 공동으로 모델링하는 쿼리-키(query-key) 구조 전달 메커니즘을 설계한다. 광범위한 실험을 통해 우리 방법이 생성 품질, 의미적 일관성, 구조적 정렬 측면에서 최신(state-of-the-art) 원격 탐사 영상 생성 접근법을 능가하며, 하류 객체 분류 작업에서도 우수한 성능을 달성함을 보인다.

arXiv:1810.10337

Projecting Trouble: Light Based Adversarial Attacks on Deep Learning Classifiers

This work demonstrates a physical attack on a deep learning image classification system using projected light onto a physical scene. Prior work is dominated by techniques for creating adversarial examples which directly manipulate the digital input of the classifier. Such an attack is limited to scenarios where the adversary can directly update the inputs to the classifier. This could happen by intercepting and modifying the inputs to an online API such as Clarifai or Cloud Vision. Such limitations have led to a vein of research around physical attacks where objects are constructed to be inherently adversarial or adversarial modifications are added to cause misclassification. Our work differs from other physical attacks in that we can cause misclassification dynamically without altering physical objects in a permanent way. We construct an experimental setup which includes a light projection source, an object for classification, and a camera to capture the scene. Experiments are conducted against 2D and 3D objects from CIFAR-10. Initial tests show projected light patterns selected via differential evolution could degrade classification from 98% to 22% and 89% to 43% probability for 2D and 3D targets respectively. Subsequent experiments explore sensitivity to physical setup and compare two additional baseline conditions for all 10 CIFAR classes. Some physical targets are more susceptible to perturbation. Simple attacks show near equivalent success, and 6 of the 10 classes were disrupted by light.

arXiv:2606.29102v1cs.CV

BTI-Net: Bidirectional Decoder-Level Task Interaction via Uncertainty-Aware Gating for Multi-Task Medical Image Analysis

Jointly learning to segment and classify medical images demands cross-task synergy, yet encoder-sharing architectures limit decoder reconstruction to task-private representations, permanently discarding the boundary cues and semantic priors each branch could supply to the other. This work introduces BTI-Net, which establishes bidirectional communication at every decoder level through two parallel pathways via Task Interaction Modules (TIM). Spatial boundary context is gated into the classification branch, while global semantic priors multiplicatively modulate the decoder, with refined features propagating progressively from coarse semantics to fine boundary detail across all four decoder resolutions. Since cross-task interaction is not equally reliable for every input, Uncertainty Proxy Attention (UPA) gates each TIM output per instance and per level using three signals that capture cross-task alignment, scene complexity, and prediction confidence, without external annotations or additional inference passes. Experiments on three medical benchmarks spanning ultrasound, dermoscopy, and brain MRI demonstrate consistent improvements in segmentation IoU and classification accuracy over both encoder-sharing and decoder-interaction baselines. Ablation confirms adaptive gating contributes +2.36 IoU over fixed bidirectional interaction, and classification accuracy improves by up to +2.26 points over the strongest multi-task baseline. UPA's uncertainty proxies serve as reliable single-pass task-failure signals without the overhead of stochastic sampling. Code: https://github.com/C-loud-Nine/BTI-Net_MTL

arXiv:2302.13345

Analysis of Deep Image Quality Models

Subjective image quality measures based on deep neural networks are very related to models of visual neuroscience. This connection benefits engineering but, more interestingly, the freedom to optimize deep networks in different ways, make them an excellent tool to explore the principles behind visual perception (both human and artificial). Recently, a myriad of networks have been successfully optimized for many interesting visual tasks. Although these nets were not specifically designed to predict image quality or other psychophysics, they have shown surprising human-like behavior. The reasons for this remain unclear. In this work, we perform a thorough analysis of the perceptual properties of pre-trained nets (particularly their ability to predict image quality) by isolating different factors: the goal (the function), the data (learning environment), the architecture, and the readout: selected layer(s), fine-tuning of channel relevance, and use of statistical descriptors as opposed to plain readout of responses. Several conclusions can be drawn. All the models correlate better with human opinion than SSIM. More importantly, some of the nets are in pair of state-of-the-art with no extra refinement or perceptual information. Nets trained for supervised tasks such as classification correlate substantially better with humans than LPIPS (a net specifically tuned for image quality). Interestingly, self-supervised tasks such as jigsaw also perform better than LPIPS. Simpler architectures are better than very deep nets. In simpler nets, correlation with humans increases with depth as if deeper layers were closer to human judgement. This is not true in very deep nets. Consistently with reports on illusions and contrast sensitivity, small changes in the image environment does not make a big difference. Finally, the explored statistical descriptors and concatenations had no major impact.

arXiv:1805.03144

High-resolution medical image synthesis using progressively grown generative adversarial networks

Generative adversarial networks (GANs) are a class of unsupervised machine learning algorithms that can produce realistic images from randomly-sampled vectors in a multi-dimensional space. Until recently, it was not possible to generate realistic high-resolution images using GANs, which has limited their applicability to medical images that contain biomarkers only detectable at native resolution. Progressive growing of GANs is an approach wherein an image generator is trained to initially synthesize low resolution synthetic images (8x8 pixels), which are then fed to a discriminator that distinguishes these synthetic images from real downsampled images. Additional convolutional layers are then iteratively introduced to produce images at twice the previous resolution until the desired resolution is reached. In this work, we demonstrate that this approach can produce realistic medical images in two different domains; fundus photographs exhibiting vascular pathology associated with retinopathy of prematurity (ROP), and multi-modal magnetic resonance images of glioma. We also show that fine-grained details associated with pathology, such as retinal vessels or tumor heterogeneity, can be preserved and enhanced by including segmentation maps as additional channels. We envisage several applications of the approach, including image augmentation and unsupervised classification of pathology.

arXiv:1610.02984

Person Re-identification: Past, Present and Future

Person re-identification (re-ID) has become increasingly popular in the community due to its application and research significance. It aims at spotting a person of interest in other cameras. In the early days, hand-crafted algorithms and small-scale evaluation were predominantly reported. Recent years have witnessed the emergence of large-scale datasets and deep learning systems which make use of large data volumes. Considering different tasks, we classify most current re-ID methods into two classes, i.e., image-based and video-based; in both tasks, hand-crafted and deep learning systems will be reviewed. Moreover, two new re-ID tasks which are much closer to real-world applications are described and discussed, i.e., end-to-end re-ID and fast re-ID in very large galleries. This paper: 1) introduces the history of person re-ID and its relationship with image classification and instance retrieval; 2) surveys a broad selection of the hand-crafted systems and the large-scale methods in both image- and video-based re-ID; 3) describes critical future directions in end-to-end re-ID and fast retrieval in large galleries; and 4) finally briefs some important yet under-developed issues.

arXiv:2010.06440

RMDL: Recalibrated multi-instance deep learning for whole slide gastric image classification

The whole slide histopathology images (WSIs) play a critical role in gastric cancer diagnosis. However, due to the large scale of WSIs and various sizes of the abnormal area, how to select informative regions and analyze them are quite challenging during the automatic diagnosis process. The multi-instance learning based on the most discriminative instances can be of great benefit for whole slide gastric image diagnosis. In this paper, we design a recalibrated multi-instance deep learning method (RMDL) to address this challenging problem. We first select the discriminative instances, and then utilize these instances to diagnose diseases based on the proposed RMDL approach. The designed RMDL network is capable of capturing instance-wise dependencies and recalibrating instance features according to the importance coefficient learned from the fused features. Furthermore, we build a large whole-slide gastric histopathology image dataset with detailed pixel-level annotations. Experimental results on the constructed gastric dataset demonstrate the significant improvement on the accuracy of our proposed framework compared with other state-of-the-art multi-instance learning methods. Moreover, our method is general and can be extended to other diagnosis tasks of different cancer types based on WSIs.