Explainable artificial intelligence is the attempt to elucidate the workings of systems too complex to be directly accessible to human cognition through suitable side-information referred to as "explanations". We present a trainable explanation module for convolutional image classifiers we call bounded logit attention (BLA). The BLA module learns to select a subset of the convolutional feature map for each input instance, which then serves as an explanation for the classifier's prediction. BLA overcomes several limitations of the instancewise feature selection method "learning to explain" (L2X) introduced by Chen et al. (2018): 1) BLA scales to real-world sized image classification problems, and 2) BLA offers a canonical way to learn explanations of variable size. Due to its modularity BLA lends itself to transfer learning setups and can also be employed as a post-hoc add-on to trained classifiers. Beyond explainability, BLA may serve as a general purpose method for differentiable approximation of subset selection. In a user study we find that BLA explanations are preferred over explanations generated by the popular (Grad-)CAM method.
In this paper, we propose an energy-efficient federated meta-learning framework. The objective is to enable learning a meta-model that can be fine-tuned to a new task with a few number of samples in a distributed setting and at low computation and communication energy consumption. We assume that each task is owned by a separate agent, so a limited number of tasks is used to train a meta-model. Assuming each task was trained offline on the agent's local data, we propose a lightweight algorithm that starts from the local models of all agents, and in a backward manner using projected stochastic gradient ascent (P-SGA) finds a meta-model. The proposed method avoids complex computations such as computing hessian, double looping, and matrix inversion, while achieving high performance at significantly less energy consumption compared to the state-of-the-art methods such as MAML and iMAML on conducted experiments for sinusoid regression and image classification tasks.
Recently, it has been demonstrated that the performance of a deep convolutional neural network can be effectively improved by embedding an attention module into it. In this work, a novel lightweight and effective attention method named Pyramid Squeeze Attention (PSA) module is proposed. By replacing the 3x3 convolution with the PSA module in the bottleneck blocks of the ResNet, a novel representational block named Efficient Pyramid Squeeze Attention (EPSA) is obtained. The EPSA block can be easily added as a plug-and-play component into a well-established backbone network, and significant improvements on model performance can be achieved. Hence, a simple and efficient backbone architecture named EPSANet is developed in this work by stacking these ResNet-style EPSA blocks. Correspondingly, a stronger multi-scale representation ability can be offered by the proposed EPSANet for various computer vision tasks including but not limited to, image classification, object detection, instance segmentation, etc. Without bells and whistles, the performance of the proposed EPSANet outperforms most of the state-of-the-art channel attention methods. As compared to the SENet-50, the Top-1 accuracy is improved by 1.93% on ImageNet dataset, a larger margin of +2.7 box AP for object detection and an improvement of +1.7 mask AP for instance segmentation by using the Mask-RCNN on MS-COCO dataset are obtained. Our source code is available at:https://github.com/murufeng/EPSANet.
In this paper, we focus on the unsupervised setting for structure learning of deep neural networks and propose to adopt the efficient coding principle, rooted in information theory and developed in computational neuroscience, to guide the procedure of structure learning without label information. This principle suggests that a good network structure should maximize the mutual information between inputs and outputs, or equivalently maximize the entropy of outputs under mild assumptions. We further establish connections between this principle and the theory of Bayesian optimal classification, and empirically verify that larger entropy of the outputs of a deep neural network indeed corresponds to a better classification accuracy. Then as an implementation of the principle, we show that sparse coding can effectively maximize the entropy of the output signals, and accordingly design an algorithm based on global group sparse coding to automatically learn the inter-layer connection and determine the depth of a neural network. Our experiments on a public image classification dataset demonstrate that using the structure learned from scratch by our proposed algorithm, one can achieve a classification accuracy comparable to the best expert-designed structure (i.e., convolutional neural networks (CNN)). In addition, our proposed algorithm successfully discovers the local connectivity (corresponding to local receptive fields in CNN) and invariance structure (corresponding to pulling in CNN), as well as achieves a good tradeoff between marginal performance gain and network depth.
For classification tasks, deep neural networks are prone to overfitting in the presence of label noise. Although existing methods are able to alleviate this problem at low noise levels, they encounter significant performance reduction at high noise levels, or even at medium noise levels when the label noise is asymmetric. To train classifiers that are universally robust to all noise levels, and that are not sensitive to any variation in the noise model, we propose a distillation-based framework that incorporates a new subcategory of Positive-Unlabeled learning. In particular, we shall assume that a small subset of any given noisy dataset is known to have correct labels, which we treat as "positive", while the remaining noisy subset is treated as "unlabeled". Our framework consists of the following two components: (1) We shall generate, via iterative updates, an augmented clean subset with additional reliable "positive" samples filtered from "unlabeled" samples; (2) We shall train a teacher model on this larger augmented clean set. With the guidance of the teacher model, we then train a student model on the whole dataset. Experiments were conducted on the CIFAR-10 dataset with synthetic label noise at multiple noise levels for both symmetric and asymmetric noise. The results show that our framework generally outperforms at medium to high noise levels. We also evaluated our framework on Clothing1M, a real-world noisy dataset, and we achieved 2.94% improvement in accuracy over existing state-of-the-art methods.
Cases of diabetes and related diabetic retinopathy (DR) have been increasing at an alarming rate in modern times. Early detection of DR is an important problem since it may cause permanent blindness in the late stages. In the last two decades, many different approaches have been applied in DR detection. Reviewing academic literature shows that deep neural networks (DNNs) have become the most preferred approach for DR detection. Among these DNN approaches, Convolutional Neural Network (CNN) models are the most used ones in the field of medical image classification. Designing a new CNN architecture is a tedious and time-consuming approach. Additionally, training an enormous number of parameters is also a difficult task. Due to this reason, instead of training CNNs from scratch, using pre-trained models has been suggested in recent years as transfer learning approach. Accordingly, the present study as a review focuses on DNN and Transfer Learning based applications of DR detection considering 38 publications between 2015 and 2020. The published papers are summarized using 9 figures and 10 tables, giving information about 22 pre-trained CNN models, 12 DR data sets and standard performance metrics.
Data sampling acts as a pivotal role in training deep learning models. However, an effective sampling schedule is difficult to learn due to the inherently high dimension of parameters in learning the sampling schedule. In this paper, we propose an AutoSampling method to automatically learn sampling schedules for model training, which consists of the multi-exploitation step aiming for optimal local sampling schedules and the exploration step for the ideal sampling distribution. More specifically, we achieve sampling schedule search with shortened exploitation cycle to provide enough supervision. In addition, we periodically estimate the sampling distribution from the learned sampling schedules and perturb it to search in the distribution space. The combination of two searches allows us to learn a robust sampling schedule. We apply our AutoSampling method to a variety of image classification tasks illustrating the effectiveness of the proposed method.
This paper presents an efficient multi-scale vision Transformer, called ResT, that capably served as a general-purpose backbone for image recognition. Unlike existing Transformer methods, which employ standard Transformer blocks to tackle raw images with a fixed resolution, our ResT have several advantages: (1) A memory-efficient multi-head self-attention is built, which compresses the memory by a simple depth-wise convolution, and projects the interaction across the attention-heads dimension while keeping the diversity ability of multi-heads; (2) Position encoding is constructed as spatial attention, which is more flexible and can tackle with input images of arbitrary size without interpolation or fine-tune; (3) Instead of the straightforward tokenization at the beginning of each stage, we design the patch embedding as a stack of overlapping convolution operation with stride on the 2D-reshaped token map. We comprehensively validate ResT on image classification and downstream tasks. Experimental results show that the proposed ResT can outperform the recently state-of-the-art backbones by a large margin, demonstrating the potential of ResT as strong backbones. The code and models will be made publicly available at https://github.com/wofmanaf/ResT.
Recently many first and second order variants of SGD have been proposed to facilitate training of Deep Neural Networks (DNNs). A common limitation of these works stem from the fact that they use the same learning rate across all instances present in the dataset. This setting is widely adopted under the assumption that loss functions for each instance are similar in nature, and hence, a common learning rate can be used. In this work, we relax this assumption and propose an optimization framework which accounts for difference in loss function characteristics across instances. More specifically, our optimizer learns a dynamic learning rate for each instance present in the dataset. Learning a dynamic learning rate for each instance allows our optimization framework to focus on different modes of training data during optimization. When applied to an image classification task, across different CNN architectures, learning dynamic learning rates leads to consistent gains over standard optimizers. When applied to a dataset containing corrupt instances, our framework reduces the learning rates on noisy instances, and improves over the state-of-the-art. Finally, we show that our optimization framework can be used for personalization of a machine learning model towards a known targeted data distribution.
Deep Neural Networks (DNNs) training can be difficult due to vanishing and exploding gradients during weight optimization through backpropagation. To address this problem, we propose a general class of Hamiltonian DNNs (H-DNNs) that stem from the discretization of continuous-time Hamiltonian systems and include several existing DNN architectures based on ordinary differential equations. Our main result is that a broad set of H-DNNs ensures non-vanishing gradients by design for an arbitrary network depth. This is obtained by proving that, using a semi-implicit Euler discretization scheme, the backward sensitivity matrices involved in gradient computations are symplectic. We also provide an upper-bound to the magnitude of sensitivity matrices and show that exploding gradients can be controlled through regularization. Finally, we enable distributed implementations of backward and forward propagation algorithms in H-DNNs by characterizing appropriate sparsity constraints on the weight matrices. The good performance of H-DNNs is demonstrated on benchmark classification problems, including image classification with the MNIST dataset.
In computer vision, it is standard practice to draw a single sample from the data augmentation procedure for each unique image in the mini-batch. However recent work has suggested drawing multiple samples can achieve higher test accuracies. In this work, we provide a detailed empirical evaluation of how the number of augmentation samples per unique image influences model performance on held out data when training deep ResNets. We demonstrate drawing multiple samples per image consistently enhances the test accuracy achieved for both small and large batch training. Crucially, this benefit arises even if different numbers of augmentations per image perform the same number of parameter updates and gradient evaluations (requiring the same total compute). Although prior work has found variance in the gradient estimate arising from subsampling the dataset has an implicit regularization benefit, our experiments suggest variance which arises from the data augmentation process harms generalization. We apply these insights to the highly performant NFNet-F5, achieving 86.8$\%$ top-1 w/o extra data on ImageNet.
We present an architecture that is effective for continual learning in an especially demanding setting, where task boundaries do not exist or are unknown, and where classes have to be learned online (with each example presented only once). To obtain good performance under these constraints, while mitigating catastrophic forgetting, we exploit recent advances in contrastive, self-supervised learning, allowing us to use a pre-trained, general purpose image encoder whose weights can be frozen, which precludes forgetting. The pre-trained encoder also greatly simplifies the downstream task of classification, which we solve with an ensemble of very simple classifiers. Collectively, the ensemble exhibits much better performance than any individual classifier, an effect which is amplified through specialisation and competitive selection. We assess the performance of the encoders-and-ensembles architecture on standard continual learning benchmarks, where it outperforms prior state-of-the-art by a large margin on the hardest problems, as well as in less familiar settings where the data distribution changes gradually or the classes are presented one at a time.
Pretraining has sparked groundswell of interest in deep learning workflows to learn from limited data and improve generalization. While this is common for 2D image classification tasks, its application to 3D medical imaging tasks like chest CT interpretation is limited. We explore the idea of whether pretraining a model on realistic videos could improve performance rather than training the model from scratch, intended for tuberculosis type classification from chest CT scans. To incorporate both spatial and temporal features, we develop a hybrid convolutional neural network (CNN) and recurrent neural network (RNN) model, where the features are extracted from each axial slice of the CT scan by a CNN, these sequence of image features are input to a RNN for classification of the CT scan. Our model termed as ViPTT-Net, was trained on over 1300 video clips with labels of human activities, and then fine-tuned on chest CT scans with labels of tuberculosis type. We find that pretraining the model on videos lead to better representations and significantly improved model validation performance from a kappa score of 0.17 to 0.35, especially for under-represented class samples. Our best method achieved 2nd place in the ImageCLEF 2021 Tuberculosis - TBT classification task with a kappa score of 0.20 on the final test set with only image information (without using clinical meta-data). All codes and models are made available.
Hierarchical structures are popular in recent vision transformers, however, they require sophisticated designs and massive datasets to work well. In this paper, we explore the idea of nesting basic local transformers on non-overlapping image blocks and aggregating them in a hierarchical way. We find that the block aggregation function plays a critical role in enabling cross-block non-local information communication. This observation leads us to design a simplified architecture that requires minor code changes upon the original vision transformer. The benefits of the proposed judiciously-selected design are threefold: (1) NesT converges faster and requires much less training data to achieve good generalization on both ImageNet and small datasets like CIFAR; (2) when extending our key ideas to image generation, NesT leads to a strong decoder that is 8$\times$ faster than previous transformer-based generators; and (3) we show that decoupling the feature learning and abstraction processes via this nested hierarchy in our design enables constructing a novel method (named GradCAT) for visually interpreting the learned model. Source code is available https://github.com/google-research/nested-transformer.
Unstructured neural network pruning algorithms have achieved impressive compression rates. However, the resulting - typically irregular - sparse matrices hamper efficient hardware implementations, leading to additional memory usage and complex control logic that diminishes the benefits of unstructured pruning. This has spurred structured coarse-grained pruning solutions that prune entire filters or even layers, enabling efficient implementation at the expense of reduced flexibility. Here we propose a flexible new pruning mechanism that facilitates pruning at different granularities (weights, kernels, filters/feature maps), while retaining efficient memory organization (e.g. pruning exactly k-out-of-n weights for every output neuron, or pruning exactly k-out-of-n kernels for every feature map). We refer to this algorithm as Dynamic Probabilistic Pruning (DPP). DPP leverages the Gumbel-softmax relaxation for differentiable k-out-of-n sampling, facilitating end-to-end optimization. We show that DPP achieves competitive compression rates and classification accuracy when pruning common deep learning models trained on different benchmark datasets for image classification. Relevantly, the non-magnitude-based nature of DPP allows for joint optimization of pruning and weight quantization in order to even further compress the network, which we show as well. Finally, we propose novel information theoretic metrics that show the confidence and pruning diversity of pruning masks within a layer.
We propose Predict then Interpolate (PI), a simple algorithm for learning correlations that are stable across environments. The algorithm follows from the intuition that when using a classifier trained on one environment to make predictions on examples from another environment, its mistakes are informative as to which correlations are unstable. In this work, we prove that by interpolating the distributions of the correct predictions and the wrong predictions, we can uncover an oracle distribution where the unstable correlation vanishes. Since the oracle interpolation coefficients are not accessible, we use group distributionally robust optimization to minimize the worst-case risk across all such interpolations. We evaluate our method on both text classification and image classification. Empirical results demonstrate that our algorithm is able to learn robust classifiers (outperforms IRM by 23.85% on synthetic environments and 12.41% on natural environments). Our code and data are available at https://github.com/YujiaBao/Predict-then-Interpolate.
The proliferation of optical, electron, and scanning probe microscopies gives rise to large volumes of imaging data of objects as diversified as cells, bacteria, pollen, to nanoparticles and atoms and molecules. In most cases, the experimental data streams contain images having arbitrary rotations and translations within the image. At the same time, for many cases, small amounts of labeled data are available in the form of prior published results, image collections, and catalogs, or even theoretical models. Here we develop an approach that allows generalizing from a small subset of labeled data with a weak orientational disorder to a large unlabeled dataset with a much stronger orientational (and positional) disorder, i.e., it performs a classification of image data given a small number of examples even in the presence of a distribution shift between the labeled and unlabeled parts. This approach is based on the semi-supervised rotationally invariant variational autoencoder (ss-rVAE) model consisting of the encoder-decoder "block" that learns a rotationally (and translationally) invariant continuous latent representation of data and a classifier that encodes data into a finite number of discrete classes. The classifier part of the trained ss-rVAE inherits the rotational (and translational) invariances and can be deployed independently of the other parts of the model. The performance of the ss-rVAE is illustrated using the synthetic data sets with known factors of variation. We further demonstrate its application for experimental data sets of nanoparticles, creating nanoparticle libraries and disentangling the representations defining the physical factors of variation in the data. The code reproducing the results is available at https://github.com/ziatdinovmax/Semi-Supervised-VAE-nanoparticles.
Large pre-trained language models achieve state-of-the-art results when fine-tuned on downstream NLP tasks. However, they almost exclusively focus on text-only representation, while neglecting cell-level layout information that is important for form image understanding. In this paper, we propose a new pre-training approach, StructuralLM, to jointly leverage cell and layout information from scanned documents. Specifically, we pre-train StructuralLM with two new designs to make the most of the interactions of cell and layout information: 1) each cell as a semantic unit; 2) classification of cell positions. The pre-trained StructuralLM achieves new state-of-the-art results in different types of downstream tasks, including form understanding (from 78.95 to 85.14), document visual question answering (from 72.59 to 83.94) and document image classification (from 94.43 to 96.08).
Recently, learning a model that generalizes well on out-of-distribution (OOD) data has attracted great attention in the machine learning community. In this paper, after defining OOD generalization via Wasserstein distance, we theoretically show that a model robust to input perturbation generalizes well on OOD data. Inspired by previous findings that adversarial training helps improve input-robustness, we theoretically show that adversarially trained models have converged excess risk on OOD data, and empirically verify it on both image classification and natural language understanding tasks. Besides, in the paradigm of first pre-training and then fine-tuning, we theoretically show that a pre-trained model that is more robust to input perturbation provides a better initialization for generalization on downstream OOD data. Empirically, after fine-tuning, this better-initialized model from adversarial pre-training also has better OOD generalization.
Neural networks trained on real-world datasets with long-tailed label distributions are biased towards frequent classes and perform poorly on infrequent classes. The imbalance in the ratio of positive and negative samples for each class skews network output probabilities further from ground-truth distributions. We propose a method, Partial Label Masking (PLM), which utilizes this ratio during training. By stochastically masking labels during loss computation, the method balances this ratio for each class, leading to improved recall on minority classes and improved precision on frequent classes. The ratio is estimated adaptively based on the network's performance by minimizing the KL divergence between predicted and ground-truth distributions. Whereas most existing approaches addressing data imbalance are mainly focused on single-label classification and do not generalize well to the multi-label case, this work proposes a general approach to solve the long-tail data imbalance issue for multi-label classification. PLM is versatile: it can be applied to most objective functions and it can be used alongside other strategies for class imbalance. Our method achieves strong performance when compared to existing methods on both multi-label (MultiMNIST and MSCOCO) and single-label (imbalanced CIFAR-10 and CIFAR-100) image classification datasets.