The classification of histopathological images is of great value in both cancer diagnosis and pathological studies. However, multiple reasons, such as variations caused by magnification factors and class imbalance, make it a challenging task where conventional methods that learn from image-label datasets perform unsatisfactorily in many cases. We observe that tumours of the same class often share common morphological patterns. To exploit this fact, we propose an approach that learns similarity-based multi-scale embeddings (SMSE) for magnification-independent histopathological image classification. In particular, a pair loss and a triplet loss are leveraged to learn similarity-based embeddings from image pairs or image triplets. The learned embeddings provide accurate measurements of similarities between images, which are regarded as a more effective form of representation for histopathological morphology than normal image features. Furthermore, in order to ensure the generated models are magnification-independent, images acquired at different magnification factors are simultaneously fed to networks during training for learning multi-scale embeddings. In addition to the SMSE, to eliminate the impact of class imbalance, instead of using the hard sample mining strategy that intuitively discards some easy samples, we introduce a new reinforced focal loss to simultaneously punish hard misclassified samples while suppressing easy well-classified samples. Experimental results show that the SMSE improves the performance for histopathological image classification tasks for both breast and liver cancers by a large margin compared to previous methods. In particular, the SMSE achieves the best performance on the BreakHis benchmark with an improvement ranging from 5% to 18% compared to previous methods using traditional features.
Federated learning is promising for its capability to collaboratively train models with multiple clients without accessing their data, but vulnerable when clients' data distributions diverge from each other. This divergence further leads to a dilemma: "Should we prioritize the learned model's generic performance (for future use at the server) or its personalized performance (for each client)?" These two, seemingly competing goals have divided the community to focus on one or the other, yet in this paper we show that it is possible to approach both at the same time. Concretely, we propose a novel federated learning framework that explicitly decouples a model's dual duties with two prediction tasks. On the one hand, we introduce a family of losses that are robust to non-identical class distributions, enabling clients to train a generic predictor with a consistent objective across them. On the other hand, we formulate the personalized predictor as a lightweight adaptive module that is learned to minimize each client's empirical risk on top of the generic predictor. With this two-loss, two-predictor framework which we name Federated Robust Decoupling (Fed-RoD), the learned model can simultaneously achieve state-of-the-art generic and personalized performance, essentially bridging the two tasks.
Active learning has proven to be useful for minimizing labeling costs by selecting the most informative samples. However, existing active learning methods do not work well in realistic scenarios such as imbalance or rare classes, out-of-distribution data in the unlabeled set, and redundancy. In this work, we propose SIMILAR (Submodular Information Measures based actIve LeARning), a unified active learning framework using recently proposed submodular information measures (SIM) as acquisition functions. We argue that SIMILAR not only works in standard active learning, but also easily extends to the realistic settings considered above and acts as a one-stop solution for active learning that is scalable to large real-world datasets. Empirically, we show that SIMILAR significantly outperforms existing active learning algorithms by as much as ~5% - 18% in the case of rare classes and ~5% - 10% in the case of out-of-distribution data on several image classification tasks like CIFAR-10, MNIST, and ImageNet. SIMILAR is available as a part of the DISTIL toolkit: "https://github.com/decile-team/distil".
We present CSWin Transformer, an efficient and effective Transformer-based backbone for general-purpose vision tasks. A challenging issue in Transformer design is that global self-attention is very expensive to compute whereas local self-attention often limits the field of interactions of each token. To address this issue, we develop the Cross-Shaped Window self-attention mechanism for computing self-attention in the horizontal and vertical stripes in parallel that form a cross-shaped window, with each stripe obtained by splitting the input feature into stripes of equal width. We provide a mathematical analysis of the effect of the stripe width and vary the stripe width for different layers of the Transformer network which achieves strong modeling capability while limiting the computation cost. We also introduce Locally-enhanced Positional Encoding (LePE), which handles the local positional information better than existing encoding schemes. LePE naturally supports arbitrary input resolutions, and is thus especially effective and friendly for downstream tasks. Incorporated with these designs and a hierarchical structure, CSWin Transformer demonstrates competitive performance on common vision tasks. Specifically, it achieves 85.4\% Top-1 accuracy on ImageNet-1K without any extra training data or label, 53.9 box AP and 46.4 mask AP on the COCO detection task, and 52.2 mIOU on the ADE20K semantic segmentation task, surpassing previous state-of-the-art Swin Transformer backbone by +1.2, +2.0, +1.4, and +2.0 respectively under the similar FLOPs setting. By further pretraining on the larger dataset ImageNet-21K, we achieve 87.5% Top-1 accuracy on ImageNet-1K and high segmentation performance on ADE20K with 55.7 mIoU. The code and models are available at https://github.com/microsoft/CSWin-Transformer.
Recently, pure transformer-based models have shown great potentials for vision tasks such as image classification and detection. However, the design of transformer networks is challenging. It has been observed that the depth, embedding dimension, and number of heads can largely affect the performance of vision transformers. Previous models configure these dimensions based upon manual crafting. In this work, we propose a new one-shot architecture search framework, namely AutoFormer, dedicated to vision transformer search. AutoFormer entangles the weights of different blocks in the same layers during supernet training. Benefiting from the strategy, the trained supernet allows thousands of subnets to be very well-trained. Specifically, the performance of these subnets with weights inherited from the supernet is comparable to those retrained from scratch. Besides, the searched models, which we refer to AutoFormers, surpass the recent state-of-the-arts such as ViT and DeiT. In particular, AutoFormer-tiny/small/base achieve 74.7%/81.7%/82.4% top-1 accuracy on ImageNet with 5.7M/22.9M/53.7M parameters, respectively. Lastly, we verify the transferability of AutoFormer by providing the performance on downstream benchmarks and distillation experiments. Code and models are available at https://github.com/microsoft/AutoML.
A set of novel approaches for estimating epistemic uncertainty in deep neural networks with a single forward pass has recently emerged as a valid alternative to Bayesian Neural Networks. On the premise of informative representations, these deterministic uncertainty methods (DUMs) achieve strong performance on detecting out-of-distribution (OOD) data while adding negligible computational costs at inference time. However, it remains unclear whether DUMs are well calibrated and can seamlessly scale to real-world applications - both prerequisites for their practical deployment. To this end, we first provide a taxonomy of DUMs, and evaluate their calibration under continuous distributional shifts. Then, we extend them to semantic segmentation. We find that, while DUMs scale to realistic vision tasks and perform well on OOD detection, the practicality of current methods is undermined by poor calibration under distributional shifts.
Recent advances in self-attention and pure multi-layer perceptrons (MLP) models for vision have shown great potential in achieving promising performance with fewer inductive biases. These models are generally based on learning interaction among spatial locations from raw data. The complexity of self-attention and MLP grows quadratically as the image size increases, which makes these models hard to scale up when high-resolution features are required. In this paper, we present the Global Filter Network (GFNet), a conceptually simple yet computationally efficient architecture, that learns long-term spatial dependencies in the frequency domain with log-linear complexity. Our architecture replaces the self-attention layer in vision transformers with three key operations: a 2D discrete Fourier transform, an element-wise multiplication between frequency-domain features and learnable global filters, and a 2D inverse Fourier transform. We exhibit favorable accuracy/complexity trade-offs of our models on both ImageNet and downstream tasks. Our results demonstrate that GFNet can be a very competitive alternative to transformer-style models and CNNs in efficiency, generalization ability and robustness. Code is available at https://github.com/raoyongming/GFNet
Recently, Vision Transformer and its variants have shown great promise on various computer vision tasks. The ability of capturing short- and long-range visual dependencies through self-attention is arguably the main source for the success. But it also brings challenges due to quadratic computational overhead, especially for the high-resolution vision tasks (e.g., object detection). In this paper, we present focal self-attention, a new mechanism that incorporates both fine-grained local and coarse-grained global interactions. Using this new mechanism, each token attends the closest surrounding tokens at fine granularity but the tokens far away at coarse granularity, and thus can capture both short- and long-range visual dependencies efficiently and effectively. With focal self-attention, we propose a new variant of Vision Transformer models, called Focal Transformer, which achieves superior performance over the state-of-the-art vision Transformers on a range of public image classification and object detection benchmarks. In particular, our Focal Transformer models with a moderate size of 51.1M and a larger size of 89.8M achieve 83.5 and 83.8 Top-1 accuracy, respectively, on ImageNet classification at 224x224 resolution. Using Focal Transformers as the backbones, we obtain consistent and substantial improvements over the current state-of-the-art Swin Transformers for 6 different object detection methods trained with standard 1x and 3x schedules. Our largest Focal Transformer yields 58.7/58.9 box mAPs and 50.9/51.3 mask mAPs on COCO mini-val/test-dev, and 55.4 mIoU on ADE20K for semantic segmentation, creating new SoTA on three of the most challenging computer vision tasks.
The memorization effect of deep neural network (DNN) plays a pivotal role in many state-of-the-art label-noise learning methods. To exploit this property, the early stopping trick, which stops the optimization at the early stage of training, is usually adopted. Current methods generally decide the early stopping point by considering a DNN as a whole. However, a DNN can be considered as a composition of a series of layers, and we find that the latter layers in a DNN are much more sensitive to label noise, while their former counterparts are quite robust. Therefore, selecting a stopping point for the whole network may make different DNN layers antagonistically affected each other, thus degrading the final performance. In this paper, we propose to separate a DNN into different parts and progressively train them to address this problem. Instead of the early stopping, which trains a whole DNN all at once, we initially train former DNN layers by optimizing the DNN with a relatively large number of epochs. During training, we progressively train the latter DNN layers by using a smaller number of epochs with the preceding layers fixed to counteract the impact of noisy labels. We term the proposed method as progressive early stopping (PES). Despite its simplicity, compared with the early stopping, PES can help to obtain more promising and stable results. Furthermore, by combining PES with existing approaches on noisy label training, we achieve state-of-the-art performance on image classification benchmarks.
Self-supervised contrastive learning has demonstrated great potential in learning visual representations. Despite their success in various downstream tasks such as image classification and object detection, self-supervised pre-training for fine-grained scenarios is not fully explored. We point out that current contrastive methods are prone to memorizing background/foreground texture and therefore have a limitation in localizing the foreground object. Analysis suggests that learning to extract discriminative texture information and localization are equally crucial for fine-grained self-supervised pre-training. Based on our findings, we introduce cross-view saliency alignment (CVSA), a contrastive learning framework that first crops and swaps saliency regions of images as a novel view generation and then guides the model to localize on foreground objects via a cross-view alignment loss. Extensive experiments on both small- and large-scale fine-grained classification benchmarks show that CVSA significantly improves the learned representation.
The architectures of deep artificial neural networks (DANNs) are routinely studied to improve their predictive performance. However, the relationship between the architecture of a DANN and its robustness to noise and adversarial attacks is less explored. We investigate how the robustness of DANNs relates to their underlying graph architectures or structures. This study: (1) starts by exploring the design space of architectures of DANNs using graph-theoretic robustness measures; (2) transforms the graphs to DANN architectures to train/validate/test on various image classification tasks; (3) explores the relationship between the robustness of trained DANNs against noise and adversarial attacks and the robustness of their underlying architectures estimated via graph-theoretic measures. We show that the topological entropy and Olivier-Ricci curvature of the underlying graphs can quantify the robustness performance of DANNs. The said relationship is stronger for complex tasks and large DANNs. Our work will allow autoML and neural architecture search community to explore design spaces of robust and accurate DANNs.
Deep Neural Networks (DNNs) have been shown to be susceptible to memorization or overfitting in the presence of noisily-labelled data. For the problem of robust learning under such noisy data, several algorithms have been proposed. A prominent class of algorithms rely on sample selection strategies wherein, essentially, a fraction of samples with loss values below a certain threshold are selected for training. These algorithms are sensitive to such thresholds, and it is difficult to fix or learn these thresholds. Often, these algorithms also require information such as label noise rates which are typically unavailable in practice. In this paper, we propose an adaptive sample selection strategy that relies only on batch statistics of a given mini-batch to provide robustness against label noise. The algorithm does not have any additional hyperparameters for sample selection, does not need any information on noise rates and does not need access to separate data with clean labels. We empirically demonstrate the effectiveness of our algorithm on benchmark datasets.
External knowledge (a.k.a. side information) plays a critical role in zero-shot learning (ZSL) which aims to predict with unseen classes that have never appeared in training data. Several kinds of external knowledge, such as text and attribute, have been widely investigated, but they alone are limited with incomplete semantics. Some very recent studies thus propose to use Knowledge Graph (KG) due to its high expressivity and compatibility for representing kinds of knowledge. However, the ZSL community is still in short of standard benchmarks for studying and comparing different external knowledge settings and different KG-based ZSL methods. In this paper, we proposed six resources covering three tasks, i.e., zero-shot image classification (ZS-IMGC), zero-shot relation extraction (ZS-RE), and zero-shot KG completion (ZS-KGC). Each resource has a normal ZSL benchmark and a KG containing semantics ranging from text to attribute, from relational knowledge to logical expressions. We have clearly presented these resources including their construction, statistics, data formats and usage cases w.r.t. different ZSL methods. More importantly, we have conducted a comprehensive benchmarking study, with two general and state-of-the-art methods, two setting-specific methods and one interpretable method. We discussed and compared different ZSL paradigms w.r.t. different external knowledge settings, and found that our resources have great potential for developing more advanced ZSL methods and more solutions for applying KGs for augmenting machine learning. All the resources are available at https://github.com/China-UK-ZSL/Resources_for_KZSL.
Dropout is a powerful and widely used technique to regularize the training of deep neural networks. In this paper, we introduce a simple regularization strategy upon dropout in model training, namely R-Drop, which forces the output distributions of different sub models generated by dropout to be consistent with each other. Specifically, for each training sample, R-Drop minimizes the bidirectional KL-divergence between the output distributions of two sub models sampled by dropout. Theoretical analysis reveals that R-Drop reduces the freedom of the model parameters and complements dropout. Experiments on $\bf{5}$ widely used deep learning tasks ($\bf{18}$ datasets in total), including neural machine translation, abstractive summarization, language understanding, language modeling, and image classification, show that R-Drop is universally effective. In particular, it yields substantial improvements when applied to fine-tune large-scale pre-trained models, e.g., ViT, RoBERTa-large, and BART, and achieves state-of-the-art (SOTA) performances with the vanilla Transformer model on WMT14 English$\to$German translation ($\bf{30.91}$ BLEU) and WMT14 English$\to$French translation ($\bf{43.95}$ BLEU), even surpassing models trained with extra large-scale data and expert-designed advanced variants of Transformer models. Our code is available at GitHub{\url{https://github.com/dropreg/R-Drop}}.
The success of deep ensembles on improving predictive performance, uncertainty estimation, and out-of-distribution robustness has been extensively studied in the machine learning literature. Albeit the promising results, naively training multiple deep neural networks and combining their predictions at inference leads to prohibitive computational costs and memory requirements. Recently proposed efficient ensemble approaches reach the performance of the traditional deep ensembles with significantly lower costs. However, the training resources required by these approaches are still at least the same as training a single dense model. In this work, we draw a unique connection between sparse neural network training and deep ensembles, yielding a novel efficient ensemble learning framework called FreeTickets. Instead of training multiple dense networks and averaging them, we directly train sparse subnetworks from scratch and extract diverse yet accurate subnetworks during this efficient, sparse-to-sparse training. Our framework, FreeTickets, is defined as the ensemble of these relatively cheap sparse subnetworks. Despite being an ensemble method, FreeTickets has even fewer parameters and training FLOPs than a single dense model. This seemingly counter-intuitive outcome is due to the ultra training/inference efficiency of dynamic sparse training. FreeTickets surpasses the dense baseline in all the following criteria: prediction accuracy, uncertainty estimation, out-of-distribution (OoD) robustness, as well as efficiency for both training and inference. Impressively, FreeTickets outperforms the naive deep ensemble with ResNet50 on ImageNet using around only 1/5 of the training FLOPs required by the latter. We have released our source code at https://github.com/VITA-Group/FreeTickets.
The recent vision transformer(i.e.for image classification) learns non-local attentive interaction of different patch tokens. However, prior arts miss learning the cross-scale dependencies of different pixels, the semantic correspondence of different labels, and the consistency of the feature representations and semantic embeddings, which are critical for biomedical segmentation. In this paper, we tackle the above issues by proposing a unified transformer network, termed Multi-Compound Transformer (MCTrans), which incorporates rich feature learning and semantic structure mining into a unified framework. Specifically, MCTrans embeds the multi-scale convolutional features as a sequence of tokens and performs intra- and inter-scale self-attention, rather than single-scale attention in previous works. In addition, a learnable proxy embedding is also introduced to model semantic relationship and feature enhancement by using self-attention and cross-attention, respectively. MCTrans can be easily plugged into a UNet-like network and attains a significant improvement over the state-of-the-art methods in biomedical image segmentation in six standard benchmarks. For example, MCTrans outperforms UNet by 3.64%, 3.71%, 4.34%, 2.8%, 1.88%, 1.57% in Pannuke, CVC-Clinic, CVC-Colon, Etis, Kavirs, ISIC2018 dataset, respectively. Code is available at https://github.com/JiYuanFeng/MCTrans.
We explore a new perspective on video understanding by casting the video recognition problem as an image recognition task. Our approach rearranges input video frames into super images, which allow for training an image classifier directly to fulfill the task of action recognition, in exactly the same way as image classification. With such a simple idea, we show that transformer-based image classifiers alone can suffice for action recognition. In particular, our approach demonstrates strong and promising performance against SOTA methods on several public datasets including Kinetics400, Moments In Time, Something-Something V2 (SSV2), Jester and Diving48. We also experiment with the prevalent ResNet image classifiers in computer vision to further validate our idea. The results on both Kinetics400 and SSV2 are comparable to some of the best-performed CNN approaches based on spatio-temporal modeling. Our source codes and models are available at https://github.com/IBM/sifar-pytorch.
In this paper, we demonstrate the implementation of our ultra-efficient deep convolutional neural network architecture: CondenseNeXt on NXP BlueBox, an autonomous driving development platform developed for self-driving vehicles. We show that CondenseNeXt is remarkably efficient in terms of FLOPs, designed for ARM-based embedded computing platforms with limited computational resources and can perform image classification without the need of a CUDA enabled GPU. CondenseNeXt utilizes the state-of-the-art depthwise separable convolution and model compression techniques to achieve a remarkable computational efficiency. Extensive analyses are conducted on CIFAR-10, CIFAR-100 and ImageNet datasets to verify the performance of CondenseNeXt Convolutional Neural Network (CNN) architecture. It achieves state-of-the-art image classification performance on three benchmark datasets including CIFAR-10 (4.79% top-1 error), CIFAR-100 (21.98% top-1 error) and ImageNet (7.91% single model, single crop top-5 error). CondenseNeXt achieves final trained model size improvement of 2.9+ MB and up to 59.98% reduction in forward FLOPs compared to CondenseNet and can perform image classification on ARM-Based computing platforms without needing a CUDA enabled GPU support, with outstanding efficiency.
Transformer recently has presented encouraging progress in computer vision. In this work, we present new baselines by improving the original Pyramid Vision Transformer (PVT v1) by adding three designs, including (1) linear complexity attention layer, (2) overlapping patch embedding, and (3) convolutional feed-forward network. With these modifications, PVT v2 reduces the computational complexity of PVT v1 to linear and achieves significant improvements on fundamental vision tasks such as classification, detection, and segmentation. Notably, the proposed PVT v2 achieves comparable or better performances than recent works such as Swin Transformer. We hope this work will facilitate state-of-the-art Transformer researches in computer vision. Code is available at https://github.com/whai362/PVT.
Recent advances in data augmentation enable one to translate images by learning the mapping between a source domain and a target domain. Existing methods tend to learn the distributions by training a model on a variety of datasets, with results evaluated largely in a subjective manner. Relatively few works in this area, however, study the potential use of image synthesis methods for recognition tasks. In this paper, we propose and explore the problem of image translation for data augmentation. We first propose a lightweight yet efficient model for translating texture to augment images based on a single input of source texture, allowing for fast training and testing, referred to as Single Image Texture Translation for data Augmentation (SITTA). Then we explore the use of augmented data in long-tailed and few-shot image classification tasks. We find the proposed augmentation method and workflow is capable of translating the texture of input data into a target domain, leading to consistently improved image recognition performance. Finally, we examine how SITTA and related image translation methods can provide a basis for a data-efficient, "augmentation engineering" approach to model training. Codes are available at https://github.com/Boyiliee/SITTA.