Analyzing complex scenes with Deep Neural Networks is a challenging task, particularly when images contain multiple objects that partially occlude each other. Existing approaches to image analysis mostly process objects independently and do not take into account the relative occlusion of nearby objects. In this paper, we propose a deep network for multi-object instance segmentation that is robust to occlusion and can be trained from bounding box supervision only. Our work builds on Compositional Networks, which learn a generative model of neural feature activations to locate occluders and to classify objects based on their non-occluded parts. We extend their generative model to include multiple objects and introduce a framework for efficient inference in challenging occlusion scenarios. In particular, we obtain feed-forward predictions of the object classes and their instance and occluder segmentations. We introduce an Occlusion Reasoning Module (ORM) that locates erroneous segmentations and estimates the occlusion order to correct them. The improved segmentation masks are, in turn, integrated into the network in a top-down manner to improve the image classification. Our experiments on the KITTI INStance dataset (KINS) and a synthetic occlusion dataset demonstrate the effectiveness and robustness of our model at multi-object instance segmentation under occlusion. Code is publically available at https://github.com/XD7479/Multi-Object-Occlusion.
In this article, we introduce a novel variant of the Tsetlin machine (TM) that randomly drops clauses, the key learning elements of a TM. In effect, TM with drop clause ignores a random selection of the clauses in each epoch, selected according to a predefined probability. In this way, additional stochasticity is introduced in the learning phase of TM. To explore the effects drop clause has on accuracy, training time, interpretability and robustness, we conduct extensive experiments on nine benchmark datasets in natural language processing~(NLP) (IMDb, R8, R52, MR and TREC) and image classification (MNIST, Fashion MNIST, CIFAR-10 and CIFAR-100). Our proposed model outperforms baseline machine learning algorithms by a wide margin and achieves competitive performance in comparison with recent deep learning model such as BERT and AlexNET-DFA. In brief, we observe up to +10% increase in accuracy and 2x to 4x faster learning compared with standard TM. We further employ the Convolutional TM to document interpretable results on the CIFAR datasets, visualizing how the heatmaps produced by the TM become more interpretable with drop clause. We also evaluate how drop clause affects learning robustness by introducing corruptions and alterations in the image/language test data. Our results show that drop clause makes TM more robust towards such changes.
Contrastive learning has been proved to be a promising technique for image-level representation learning from unlabeled data. Many existing works have demonstrated improved results by applying contrastive learning in classification and object detection tasks for either natural images or medical images. However, its application to medical image segmentation tasks has been limited. In this work, we use lung segmentation in chest X-rays as a case study and propose a contrastive learning framework with temporal correlated medical images, named CL-TCI, to learn superior encoders for initializing the segmentation network. We adapt CL-TCI from two state-of-the-art contrastive learning methods-MoCo and SimCLR. Experiment results on three chest X-ray datasets show that under two different segmentation backbones, U-Net and Deeplab-V3, CL-TCI can outperform all baselines that do not incorporate any temporal correlation in both semi-supervised learning setting and transfer learning setting with limited annotation. This suggests that information among temporal correlated medical images can indeed improve contrastive learning performance. Between the two variations of CL-TCI, CL-TCI adapted from MoCo outperforms CL-TCI adapted from SimCLR in most settings, indicating that more contrastive samples can benefit the learning process and help the network learn high-quality representations.
In this work, we present a novel matrix-encoding method that is particularly convenient for neural networks to make predictions in a privacy-preserving manner using homomorphic encryption. Based on this encoding method, we implement a convolutional neural network for handwritten image classification over encryption. For two matrices $A$ and $B$ to perform homomorphic multiplication, the main idea behind it, in a simple version, is to encrypt matrix $A$ and the transpose of matrix $B$ into two ciphertexts respectively. With additional operations, the homomorphic matrix multiplication can be calculated over encrypted matrices efficiently. For the convolution operation, we in advance span each convolution kernel to a matrix space of the same size as the input image so as to generate several ciphertexts, each of which is later used together with the ciphertext encrypting input images for calculating some of the final convolution results. We accumulate all these intermediate results and thus complete the convolution operation. In a public cloud with 40 vCPUs, our convolutional neural network implementation on the MNIST testing dataset takes $\sim$ 287 seconds to compute ten likelihoods of 32 encrypted images of size $28 \times 28$ simultaneously. The data owner only needs to upload one ciphertext ($\sim 19.8$ MB) encrypting these 32 images to the public cloud.
In recent years, the success of large-scale vision-language models (VLMs) such as CLIP has led to their increased usage in various computer vision tasks. These models enable zero-shot inference through carefully crafted instructional text prompts without task-specific supervision. However, the potential of VLMs for generalization tasks in remote sensing (RS) has not been fully realized. To address this research gap, we propose a novel image-conditioned prompt learning strategy called the Visual Attention Parameterized Prompts Learning Network (APPLeNet). APPLeNet emphasizes the importance of multi-scale feature learning in RS scene classification and disentangles visual style and content primitives for domain generalization tasks. To achieve this, APPLeNet combines visual content features obtained from different layers of the vision encoder and style properties obtained from feature statistics of domain-specific batches. An attention-driven injection module is further introduced to generate visual tokens from this information. We also introduce an anti-correlation regularizer to ensure discrimination among the token embeddings, as this visual information is combined with the textual tokens. To validate APPLeNet, we curated four available RS benchmarks and introduced experimental protocols and datasets for three domain generalization tasks. Our results consistently outperform the relevant literature and code is available at https://github.com/mainaksingha01/APPLeNet
Humans can develop internal world models that encode common sense knowledge, telling them how the world works and predicting the consequences of their actions. This concept has emerged as a promising direction for establishing general-purpose machine-learning models in recent preliminary works, e.g., for visual representation learning. In this paper, we present CheXWorld, the first effort towards a self-supervised world model for radiographic images. Specifically, our work develops a unified framework that simultaneously models three aspects of medical knowledge essential for qualified radiologists, including 1) local anatomical structures describing the fine-grained characteristics of local tissues (e.g., architectures, shapes, and textures); 2) global anatomical layouts describing the global organization of the human body (e.g., layouts of organs and skeletons); and 3) domain variations that encourage CheXWorld to model the transitions across different appearance domains of radiographs (e.g., varying clarity, contrast, and exposure caused by collecting radiographs from different hospitals, devices, or patients). Empirically, we design tailored qualitative and quantitative analyses, revealing that CheXWorld successfully captures these three dimensions of medical knowledge. Furthermore, transfer learning experiments across eight medical image classification and segmentation benchmarks showcase that CheXWorld significantly outperforms existing SSL methods and large-scale medical foundation models. Code & pre-trained models are available at https://github.com/LeapLabTHU/CheXWorld.
Web image datasets curated online inherently contain ambiguous in-distribution (ID) instances and out-of-distribution (OOD) instances, which we collectively call non-conforming (NC) instances. In many recent approaches for mitigating the negative effects of NC instances, the core implicit assumption is that the NC instances can be found via entropy maximization. For "entropy" to be well-defined, we are interpreting the output prediction vector of an instance as the parameter vector of a multinomial random variable, with respect to some trained model with a softmax output layer. Hence, entropy maximization is based on the idealized assumption that NC instances have predictions that are "almost" uniformly distributed. However, in real-world web image datasets, there are numerous NC instances whose predictions are far from being uniformly distributed. To tackle the limitation of entropy maximization, we propose $(\alpha, \beta)$-generalized KL divergence, $\mathcal{D}_{\text{KL}}^{\alpha, \beta}(p\|q)$, which can be used to identify significantly more NC instances. Theoretical properties of $\mathcal{D}_{\text{KL}}^{\alpha, \beta}(p\|q)$ are proven, and we also show empirically that a simple use of $\mathcal{D}_{\text{KL}}^{\alpha, \beta}(p\|q)$ outperforms all baselines on the NC instance identification task. Building upon $(\alpha,\beta)$-generalized KL divergence, we also introduce a new iterative training framework, GenKL, that identifies and relabels NC instances. When evaluated on three web image datasets, Clothing1M, Food101/Food101N, and mini WebVision 1.0, we achieved new state-of-the-art classification accuracies: $81.34\%$, $85.73\%$ and $78.99\%$/$92.54\%$ (top-1/top-5), respectively.
Coronavirus disease (COVID-19) is a contagious infection caused by severe acute respiratory syndrome coronavirus-2 (SARS-COV-2) and it has infected and killed millions of people across the globe. In the absence of specific drugs or vaccines for the treatment of COVID-19 and the limitation of prevailing diagnostic techniques, there is a requirement for some alternate automatic screening systems that can be used by the physicians to quickly identify and isolate the infected patients. A chest X-ray (CXR) image can be used as an alternative modality to detect and diagnose the COVID-19. In this study, we present an automatic COVID-19 diagnostic and severity prediction (COVIDX) system that uses deep feature maps from CXR images to diagnose COVID-19 and its severity prediction. The proposed system uses a three-phase classification approach (healthy vs unhealthy, COVID-19 vs Pneumonia, and COVID-19 severity) using different shallow supervised classification algorithms. We evaluated COVIDX not only through 10-fold cross2 validation and by using an external validation dataset but also in real settings by involving an experienced radiologist. In all the evaluation settings, COVIDX outperforms all the existing stateof-the-art methods designed for this purpose. We made COVIDX easily accessible through a cloud-based webserver and python code available at https://sites.google.com/view/wajidarshad/software and https://github.com/wajidarshad/covidx, respectively.
Modern deep learning methods have achieved great success in machine learning and computer vision fields by learning a set of pre-defined datasets. Howerver, these methods perform unsatisfactorily when applied into real-world situations. The reason of this phenomenon is that learning new tasks leads the trained model quickly forget the knowledge of old tasks, which is referred to as catastrophic forgetting. Current state-of-the-art incremental learning methods tackle catastrophic forgetting problem in traditional classification networks and ignore the problem existing in embedding networks, which are the basic networks for image retrieval, face recognition, zero-shot learning, etc. Different from traditional incremental classification networks, the semantic gap between the embedding spaces of two adjacent tasks is the main challenge for embedding networks under incremental learning setting. Thus, we propose a novel class-incremental method for embedding network, named as zero-shot translation class-incremental method (ZSTCI), which leverages zero-shot translation to estimate and compensate the semantic gap without any exemplars. Then, we try to learn a unified representation for two adjacent tasks in sequential learning process, which captures the relationships of previous classes and current classes precisely. In addition, ZSTCI can easily be combined with existing regularization-based incremental learning methods to further improve performance of embedding networks. We conduct extensive experiments on CUB-200-2011 and CIFAR100, and the experiment results prove the effectiveness of our method. The code of our method has been released.
Temporal information is essential to learning effective policies with Reinforcement Learning (RL). However, current state-of-the-art RL algorithms either assume that such information is given as part of the state space or, when learning from pixels, use the simple heuristic of frame-stacking to implicitly capture temporal information present in the image observations. This heuristic is in contrast to the current paradigm in video classification architectures, which utilize explicit encodings of temporal information through methods such as optical flow and two-stream architectures to achieve state-of-the-art performance. Inspired by leading video classification architectures, we introduce the Flow of Latents for Reinforcement Learning (Flare), a network architecture for RL that explicitly encodes temporal information through latent vector differences. We show that Flare (i) recovers optimal performance in state-based RL without explicit access to the state velocity, solely with positional state information, (ii) achieves state-of-the-art performance on pixel-based challenging continuous control tasks within the DeepMind control benchmark suite, namely quadruped walk, hopper hop, finger turn hard, pendulum swing, and walker run, and is the most sample efficient model-free pixel-based RL algorithm, outperforming the prior model-free state-of-the-art by 1.9X and 1.5X on the 500k and 1M step benchmarks, respectively, and (iv), when augmented over rainbow DQN, outperforms this state-of-the-art level baseline on 5 of 8 challenging Atari games at 100M time step benchmark.
Connected decision boundaries are useful in several tasks like image segmentation, clustering, alpha-shape or defining a region in nD-space. However, the machine learning literature lacks methods for generating connected decision boundaries using neural networks. Thresholding an invex function, a generalization of a convex function, generates such decision boundaries. This paper presents two methods for constructing invex functions using neural networks. The first approach is based on constraining a neural network with Gradient Clipped-Gradient Penality (GCGP), where we clip and penalise the gradients. In contrast, the second one is based on the relationship of the invex function to the composition of invertible and convex functions. We employ connectedness as a basic interpretation method and create connected region-based classifiers. We show that multiple connected set based classifiers can approximate any classification function. In the experiments section, we use our methods for classification tasks using an ensemble of 1-vs-all models as well as using a single multiclass model on small-scale datasets. The experiments show that connected set-based classifiers do not pose any disadvantage over ordinary neural network classifiers, but rather, enhance their interpretability. We also did an extensive study on the properties of invex function and connected sets for interpretability and network morphism with experiments on toy and real-world data sets. Our study suggests that invex function is fundamental to understanding and applying locality and connectedness of input space which is useful for various downstream tasks.
One fascinating aspect of pre-trained vision-language models~(VLMs) learning under language supervision is their impressive zero-shot generalization capability. However, this ability is hindered by distribution shifts between the training and testing data. Previous test time adaptation~(TTA) methods for VLMs in zero-shot classification rely on minimizing the entropy of model outputs, tending to be stuck in incorrect model predictions. In this work, we propose TTA with feedback to rectify the model output and prevent the model from becoming blindly confident. Specifically, a CLIP model is adopted as the reward model during TTA and provides feedback for the VLM. Given a single test sample, the VLM is forced to maximize the CLIP reward between the input and sampled results from the VLM output distribution. The proposed \textit{reinforcement learning with CLIP feedback~(RLCF)} framework is highly flexible and universal. Beyond the classification task, with task-specific sampling strategies and a proper reward baseline choice, RLCF can be easily extended to not only discrimination tasks like retrieval but also generalization tasks like image captioning, improving the zero-shot generalization capacity of VLMs. According to the characteristics of these VL tasks, we build different fully TTA pipelines with RLCF to improve the zero-shot generalization ability of various VLMs. Extensive experiments along with promising empirical results demonstrate the effectiveness of RLCF. The code is available at https://github.com/mzhaoshuai/RLCF.
Current status quo in machine learning is to use static datasets of real images for training, which often come from long-tailed distributions. With the recent advances in generative models, researchers have started augmenting these static datasets with synthetic data, reporting moderate performance improvements on classification tasks. We hypothesize that these performance gains are limited by the lack of feedback from the classifier to the generative model, which would promote the usefulness of the generated samples to improve the classifier's performance. In this work, we introduce a framework for augmenting static datasets with useful synthetic samples, which leverages one-shot feedback from the classifier to drive the sampling of the generative model. In order for the framework to be effective, we find that the samples must be close to the support of the real data of the task at hand, and be sufficiently diverse. We validate three feedback criteria on a long-tailed dataset (ImageNet-LT) as well as a group-imbalanced dataset (NICO++). On ImageNet-LT, we achieve state-of-the-art results, with over 4 percent improvement on underrepresented classes while being twice efficient in terms of the number of generated synthetic samples. NICO++ also enjoys marked boosts of over 5 percent in worst group accuracy. With these results, our framework paves the path towards effectively leveraging state-of-the-art text-to-image models as data sources that can be queried to improve downstream applications.
We introduce a new setting of Novel Class Discovery in Semantic Segmentation (NCDSS), which aims at segmenting unlabeled images containing new classes given prior knowledge from a labeled set of disjoint classes. In contrast to existing approaches that look at novel class discovery in image classification, we focus on the more challenging semantic segmentation. In NCDSS, we need to distinguish the objects and background, and to handle the existence of multiple classes within an image, which increases the difficulty in using the unlabeled data. To tackle this new setting, we leverage the labeled base data and a saliency model to coarsely cluster novel classes for model training in our basic framework. Additionally, we propose the Entropy-based Uncertainty Modeling and Self-training (EUMS) framework to overcome noisy pseudo-labels, further improving the model performance on the novel classes. Our EUMS utilizes an entropy ranking technique and a dynamic reassignment to distill clean labels, thereby making full use of the noisy data via self-supervised learning. We build the NCDSS benchmark on the PASCAL-5$^i$ dataset and COCO-20$^i$ dataset. Extensive experiments demonstrate the feasibility of the basic framework (achieving an average mIoU of 49.81% on PASCAL-5$^i$) and the effectiveness of EUMS framework (outperforming the basic framework by 9.28% mIoU on PASCAL-5$^i$).
Density-based and classification-based methods have ruled unsupervised anomaly detection in recent years, while reconstruction-based methods are rarely mentioned for the poor reconstruction ability and low performance. However, the latter requires no costly extra training samples for the unsupervised training that is more practical, so this paper focuses on improving this kind of method and proposes a novel Omni-frequency Channel-selection Reconstruction (OCR-GAN) network to handle anomaly detection task in a perspective of frequency. Concretely, we propose a Frequency Decoupling (FD) module to decouple the input image into different frequency components and model the reconstruction process as a combination of parallel omni-frequency image restorations, as we observe a significant difference in the frequency distribution of normal and abnormal images. Given the correlation among multiple frequencies, we further propose a Channel Selection (CS) module that performs frequency interaction among different encoders by adaptively selecting different channels. Abundant experiments demonstrate the effectiveness and superiority of our approach over different kinds of methods, e.g., achieving a new state-of-the-art 98.3 detection AUC on the MVTec AD dataset without extra training data that markedly surpasses the reconstruction-based baseline by +38.1 and the current SOTA method by +0.3. Source code is available at https://github.com/zhangzjn/OCR-GAN.
Deep learning models often require large amounts of data for training, leading to increased costs. It is particularly challenging in medical imaging, i.e., gathering distributed data for centralized training, and meanwhile, obtaining quality labels remains a tedious job. Many methods have been proposed to address this issue in various training paradigms, e.g., continual learning, active learning, and federated learning, which indeed demonstrate certain forms of the data valuation process. However, existing methods are either overly intuitive or limited to common clean/toy datasets in the experiments. In this work, we present two data valuation metrics based on Synaptic Intelligence and gradient norms, respectively, to study the redundancy in real-world image data. Novel online and offline data selection algorithms are then proposed via clustering and grouping based on the examined data values. Our online approach effectively evaluates data utilizing layerwise model parameter updates and gradients in each epoch and can accelerate model training with fewer epochs and a subset (e.g., 19%-59%) of data while maintaining equivalent levels of accuracy in a variety of datasets. It also extends to the offline coreset construction, producing subsets of only 18%-30% of the original. The codes for the proposed adaptive data selection and coreset computation are available (https://github.com/ZhenyuTANG2023/data_selection).
Object detection is a task that performs position identification and label classification of objects in images or videos. The information obtained through this process plays an essential role in various tasks in the field of computer vision. In object detection, the data utilized for training and validation typically originate from public datasets that are well-balanced in terms of the number of objects ascribed to each class in an image. However, in real-world scenarios, handling datasets with much greater class imbalance, i.e., very different numbers of objects for each class , is much more common, and this imbalance may reduce the performance of object detection when predicting unseen test images. In our study, thus, we propose a method that evenly distributes the classes in an image for training and validation, solving the class imbalance problem in object detection. Our proposed method aims to maintain a uniform class distribution through multi-label stratification. We tested our proposed method not only on public datasets that typically exhibit balanced class distribution but also on custom datasets that may have imbalanced class distribution. We found that our proposed method was more effective on datasets containing severe imbalance and less data. Our findings indicate that the proposed method can be effectively used on datasets with substantially imbalanced class distribution.
Language Identification (LID) systems are used to classify the spoken language from a given audio sample and are typically the first step for many spoken language processing tasks, such as Automatic Speech Recognition (ASR) systems. Without automatic language detection, speech utterances cannot be parsed correctly and grammar rules cannot be applied, causing subsequent speech recognition steps to fail. We propose a LID system that solves the problem in the image domain, rather than the audio domain. We use a hybrid Convolutional Recurrent Neural Network (CRNN) that operates on spectrogram images of the provided audio snippets. In extensive experiments we show, that our model is applicable to a range of noisy scenarios and can easily be extended to previously unknown languages, while maintaining its classification accuracy. We release our code and a large scale training set for LID systems to the community.
Hashing produces compact representations for documents, to perform tasks like classification or retrieval based on these short codes. When hashing is supervised, the codes are trained using labels on the training data. This paper first shows that the evaluation protocols used in the literature for supervised hashing are not satisfactory: we show that a trivial solution that encodes the output of a classifier significantly outperforms existing supervised or semi-supervised methods, while using much shorter codes. We then propose two alternative protocols for supervised hashing: one based on retrieval on a disjoint set of classes, and another based on transfer learning to new classes. We provide two baseline methods for image-related tasks to assess the performance of (semi-)supervised hashing: without coding and with unsupervised codes. These baselines give a lower- and upper-bound on the performance of a supervised hashing scheme.
Previous work has modeled the compositionality of words by creating character-level models of meaning, reducing problems of sparsity for rare words. However, in many writing systems compositionality has an effect even on the character-level: the meaning of a character is derived by the sum of its parts. In this paper, we model this effect by creating embeddings for characters based on their visual characteristics, creating an image for the character and running it through a convolutional neural network to produce a visual character embedding. Experiments on a text classification task demonstrate that such model allows for better processing of instances with rare characters in languages such as Chinese, Japanese, and Korean. Additionally, qualitative analyses demonstrate that our proposed model learns to focus on the parts of characters that carry semantic content, resulting in embeddings that are coherent in visual space.