In this work, we explore a scalable way for building a general representation model toward unlimited modalities. We release ONE-PEACE, a highly extensible model with 4B parameters that can seamlessly align and integrate representations across vision, audio, and language modalities. The architecture of ONE-PEACE comprises modality adapters, shared self-attention layers, and modality FFNs. This design allows for the easy extension of new modalities by adding adapters and FFNs, while also enabling multi-modal fusion through self-attention layers. To pretrain ONE-PEACE, we develop two modality-agnostic pretraining tasks, cross-modal aligning contrast and intra-modal denoising contrast, which align the semantic space of different modalities and capture fine-grained details within modalities concurrently. With the scaling-friendly architecture and pretraining tasks, ONE-PEACE has the potential to expand to unlimited modalities. Without using any vision or language pretrained model for initialization, ONE-PEACE achieves leading results on a wide range of uni-modal and multi-modal tasks, including image classification (ImageNet), semantic segmentation (ADE20K), audio-text retrieval (AudioCaps, Clotho), audio classification (ESC-50, FSD50K, VGGSound), audio question answering (AVQA), image-text retrieval (MSCOCO, Flickr30K), and visual grounding (RefCOCO/+/g). Code is available at https://github.com/OFA-Sys/ONE-PEACE.
In the application of Multiple Instance Learning (MIL) methods for Whole Slide Image (WSI) classification, attention mechanisms often focus on a subset of discriminative instances, which are closely linked to overfitting. To mitigate overfitting, we present Attention-Challenging MIL (ACMIL). ACMIL combines two techniques based on separate analyses for attention value concentration. Firstly, UMAP of instance features reveals various patterns among discriminative instances, with existing attention mechanisms capturing only some of them. To remedy this, we introduce Multiple Branch Attention (MBA) to capture more discriminative instances using multiple attention branches. Secondly, the examination of the cumulative value of Top-K attention scores indicates that a tiny number of instances dominate the majority of attention. In response, we present Stochastic Top-K Instance Masking (STKIM), which masks out a portion of instances with Top-K attention values and allocates their attention values to the remaining instances. The extensive experimental results on three WSI datasets with two pre-trained backbones reveal that our ACMIL outperforms state-of-the-art methods. Additionally, through heatmap visualization and UMAP visualization, this paper extensively illustrates ACMIL's effectiveness in suppressing attention value concentration and overcoming the overfitting challenge. The source code is available at \url{https://github.com/dazhangyu123/ACMIL}.
Deep neural networks (DNNs) have been shown to perform well on exclusive, multi-class classification tasks. However, when different classes have similar visual features, it becomes challenging for human annotators to differentiate them. This scenario necessitates the use of composite class labels. In this paper, we propose a novel framework called Hyper-Evidential Neural Network (HENN) that explicitly models predictive uncertainty due to composite class labels in training data in the context of the belief theory called Subjective Logic (SL). By placing a grouped Dirichlet distribution on the class probabilities, we treat predictions of a neural network as parameters of hyper-subjective opinions and learn the network that collects both single and composite evidence leading to these hyper-opinions by a deterministic DNN from data. We introduce a new uncertainty type called vagueness originally designed for hyper-opinions in SL to quantify composite classification uncertainty for DNNs. Our results demonstrate that HENN outperforms its state-of-the-art counterparts based on four image datasets. The code and datasets are available at: https://github.com/Hugo101/HyperEvidentialNN.
In this paper, we propose novel generative models for creating adversarial examples, slightly perturbed images resembling natural images but maliciously crafted to fool pre-trained models. We present trainable deep neural networks for transforming images to adversarial perturbations. Our proposed models can produce image-agnostic and image-dependent perturbations for both targeted and non-targeted attacks. We also demonstrate that similar architectures can achieve impressive results in fooling classification and semantic segmentation models, obviating the need for hand-crafting attack methods for each task. Using extensive experiments on challenging high-resolution datasets such as ImageNet and Cityscapes, we show that our perturbations achieve high fooling rates with small perturbation norms. Moreover, our attacks are considerably faster than current iterative methods at inference time.
Data representation in non-Euclidean spaces has proven effective for capturing hierarchical and complex relationships in real-world datasets. Hyperbolic spaces, in particular, provide efficient embeddings for hierarchical structures. This paper introduces the Hyperbolic Vision Transformer (HVT), a novel extension of the Vision Transformer (ViT) that integrates hyperbolic geometry. While traditional ViTs operate in Euclidean space, our method enhances the self-attention mechanism by leveraging hyperbolic distance and M\"obius transformations. This enables more effective modeling of hierarchical and relational dependencies in image data. We present rigorous mathematical formulations, showing how hyperbolic geometry can be incorporated into attention layers, feed-forward networks, and optimization. We offer improved performance for image classification using the ImageNet dataset.
Pre-trained multi-modal Vision-Language Models like CLIP are widely used off-the-shelf for a variety of applications. In this paper, we show that the common practice of individually exploiting the text or image encoders of these powerful multi-modal models is highly suboptimal for intra-modal tasks like image-to-image retrieval. We argue that this is inherently due to the CLIP-style inter-modal contrastive loss that does not enforce any intra-modal constraints, leading to what we call intra-modal misalignment. To demonstrate this, we leverage two optimization-based modality inversion techniques that map representations from their input modality to the complementary one without any need for auxiliary data or additional trained adapters. We empirically show that, in the intra-modal tasks of image-to-image and text-to-text retrieval, approaching these tasks inter-modally significantly improves performance with respect to intra-modal baselines on more than fifteen datasets. Additionally, we demonstrate that approaching a native inter-modal task (e.g. zero-shot image classification) intra-modally decreases performance, further validating our findings. Finally, we show that incorporating an intra-modal term in the pre-training objective or narrowing the modality gap between the text and image feature embedding spaces helps reduce the intra-modal misalignment. The code is publicly available at: https://github.com/miccunifi/Cross-the-Gap.
This paper presents a new Vision Transformer (ViT) architecture Multi-Scale Vision Longformer, which significantly enhances the ViT of \cite{dosovitskiy2020image} for encoding high-resolution images using two techniques. The first is the multi-scale model structure, which provides image encodings at multiple scales with manageable computational cost. The second is the attention mechanism of vision Longformer, which is a variant of Longformer \cite{beltagy2020longformer}, originally developed for natural language processing, and achieves a linear complexity w.r.t. the number of input tokens. A comprehensive empirical study shows that the new ViT significantly outperforms several strong baselines, including the existing ViT models and their ResNet counterparts, and the Pyramid Vision Transformer from a concurrent work \cite{wang2021pyramid}, on a range of vision tasks, including image classification, object detection, and segmentation. The models and source code are released at \url{https://github.com/microsoft/vision-longformer}.
Single image super-resolution (SISR) is the process of obtaining one high-resolution version of a low-resolution image by increasing the number of pixels per unit area. This method has been actively investigated by the research community, due to the wide variety of real-world problems where it can be applied, from aerial and satellite imaging to compressed image and video enhancement. Despite the improvements achieved by deep learning in the field, the vast majority of the used networks are based on traditional convolutions, with the solutions focusing on going deeper and/or wider, and innovations coming from jointly employing successful concepts from other fields. In this work, we decided to step up from the traditional convolutions and adopt the concept of capsules. Since their overwhelming results both in image classification and segmentation problems, we question how suitable they are for SISR. We also verify that different solutions share most of their configurations, and argue that this trend leads to fewer explorations of network varieties. During our experiments, we check various strategies to improve results, ranging from new and different loss functions to changes in the capsule layers. Our network achieved good results with fewer convolutional-based layers, showing that capsules might be a concept worth applying in the image super-resolution problem.
Perhaps surprisingly sewerage infrastructure is one of the most costly infrastructures in modern society. Sewer pipes are manually inspected to determine whether the pipes are defective. However, this process is limited by the number of qualified inspectors and the time it takes to inspect a pipe. Automatization of this process is therefore of high interest. So far, the success of computer vision approaches for sewer defect classification has been limited when compared to the success in other fields mainly due to the lack of public datasets. To this end, in this work we present a large novel and publicly available multi-label classification dataset for image-based sewer defect classification called Sewer-ML. The Sewer-ML dataset consists of 1.3 million images annotated by professional sewer inspectors from three different utility companies across nine years. Together with the dataset, we also present a benchmark algorithm and a novel metric for assessing performance. The benchmark algorithm is a result of evaluating 12 state-of-the-art algorithms, six from the sewer defect classification domain and six from the multi-label classification domain, and combining the best performing algorithms. The novel metric is a class-importance weighted F2 score, $\text{F}2_{\text{CIW}}$, reflecting the economic impact of each class, used together with the normal pipe F1 score, $\text{F}1_{\text{Normal}}$. The benchmark algorithm achieves an $\text{F}2_{\text{CIW}}$ score of 55.11% and $\text{F}1_{\text{Normal}}$ score of 90.94%, leaving ample room for improvement on the Sewer-ML dataset. The code, models, and dataset are available at the project page https://vap.aau.dk/sewer-ml/
Deep neural networks produce state-of-the-art results when trained on a large number of labeled examples but tend to overfit when small amounts of labeled examples are used for training. Creating a large number of labeled examples requires considerable resources, time, and effort. If labeling new data is not feasible, so-called semi-supervised learning can achieve better generalisation than purely supervised learning by employing unlabeled instances as well as labeled ones. The work presented in this paper is motivated by the observation that transfer learning provides the opportunity to potentially further improve performance by exploiting models pretrained on a similar domain. More specifically, we explore the use of transfer learning when performing semi-supervised learning using self-learning. The main contribution is an empirical evaluation of transfer learning using different combinations of similarity metric learning methods and label propagation algorithms in semi-supervised learning. We find that transfer learning always substantially improves the model's accuracy when few labeled examples are available, regardless of the type of loss used for training the neural network. This finding is obtained by performing extensive experiments on the SVHN, CIFAR10, and Plant Village image classification datasets and applying pretrained weights from Imagenet for transfer learning.
Multi-Label Image Classification (MLIC) approaches usually exploit label correlations to achieve good performance. However, emphasizing correlation like co-occurrence may overlook discriminative features of the target itself and lead to model overfitting, thus undermining the performance. In this study, we propose a generic framework named Parallel Self-Distillation (PSD) for boosting MLIC models. PSD decomposes the original MLIC task into several simpler MLIC sub-tasks via two elaborated complementary task decomposition strategies named Co-occurrence Graph Partition (CGP) and Dis-occurrence Graph Partition (DGP). Then, the MLIC models of fewer categories are trained with these sub-tasks in parallel for respectively learning the joint patterns and the category-specific patterns of labels. Finally, knowledge distillation is leveraged to learn a compact global ensemble of full categories with these learned patterns for reconciling the label correlation exploitation and model overfitting. Extensive results on MS-COCO and NUS-WIDE datasets demonstrate that our framework can be easily plugged into many MLIC approaches and improve performances of recent state-of-the-art approaches. The explainable visual study also further validates that our method is able to learn both the category-specific and co-occurring features. The source code is released at https://github.com/Robbie-Xu/CPSD.
In real medical data, training samples typically show long-tailed distributions with multiple labels. Class distribution of the medical data has a long-tailed shape, in which the incidence of different diseases is quite varied, and at the same time, it is not unusual for images taken from symptomatic patients to be multi-label diseases. Therefore, in this paper, we concurrently address these two issues by putting forth a robust asymmetric loss on the polynomial function. Since our loss tackles both long-tailed and multi-label classification problems simultaneously, it leads to a complex design of the loss function with a large number of hyper-parameters. Although a model can be highly fine-tuned due to a large number of hyper-parameters, it is difficult to optimize all hyper-parameters at the same time, and there might be a risk of overfitting a model. Therefore, we regularize the loss function using the Hill loss approach, which is beneficial to be less sensitive against the numerous hyper-parameters so that it reduces the risk of overfitting the model. For this reason, the proposed loss is a generic method that can be applied to most medical image classification tasks and does not make the training process more time-consuming. We demonstrate that the proposed robust asymmetric loss performs favorably against the long-tailed with multi-label medical image classification in addition to the various long-tailed single-label datasets. Notably, our method achieves Top-5 results on the CXR-LT dataset of the ICCV CVAMD 2023 competition. We opensource our implementation of the robust asymmetric loss in the public repository: https://github.com/kalelpark/RAL.
The performance of deep neural networks for image recognition tasks such as predicting a smiling face is known to degrade with under-represented classes of sensitive attributes. We address this problem by introducing fairness-aware regularization losses based on batch estimates of Demographic Parity, Equalized Odds, and a novel Intersection-over-Union measure. The experiments performed on facial and medical images from CelebA, UTKFace, and the SIIM-ISIC melanoma classification challenge show the effectiveness of our proposed fairness losses for bias mitigation as they improve model fairness while maintaining high classification performance. To the best of our knowledge, our work is the first attempt to incorporate these types of losses in an end-to-end training scheme for mitigating biases of visual attribute predictors. Our code is available at https://github.com/nish03/FVAP.
We propose a metadata-aware self-supervised learning~(SSL)~framework useful for fine-grained classification and ecological mapping of bird species around the world. Our framework unifies two SSL strategies: Contrastive Learning~(CL) and Masked Image Modeling~(MIM), while also enriching the embedding space with metadata available with ground-level imagery of birds. We separately train uni-modal and cross-modal ViT on a novel cross-view global bird species dataset containing ground-level imagery, metadata (location, time), and corresponding satellite imagery. We demonstrate that our models learn fine-grained and geographically conditioned features of birds, by evaluating on two downstream tasks: fine-grained visual classification~(FGVC) and cross-modal retrieval. Pre-trained models learned using our framework achieve SotA performance on FGVC of iNAT-2021 birds and in transfer learning settings for CUB-200-2011 and NABirds datasets. Moreover, the impressive cross-modal retrieval performance of our model enables the creation of species distribution maps across any geographic region. The dataset and source code will be released at https://github.com/mvrl/BirdSAT}.
Data embeddings with CLIP and ImageBind provide powerful features for the analysis of multimedia and/or multimodal data. We assess their performance here for classification using a Gaussian Mixture models (GMMs) based layer as an alternative to the standard Softmax layer. GMMs based classifiers have recently been shown to have interesting performances as part of deep learning pipelines trained end-to-end. Our first contribution is to investigate GMM based classification performance taking advantage of the embedded spaces CLIP and ImageBind. Our second contribution is in proposing our own GMM based classifier with a lower parameters count than previously proposed. Our findings are, that in most cases, on these tested embedded spaces, one gaussian component in the GMMs is often enough for capturing each class, and we hypothesize that this may be due to the contrastive loss used for training these embedded spaces that naturally concentrates features together for each class. We also observed that ImageBind often provides better performance than CLIP for classification of image datasets even when these embedded spaces are compressed using PCA.
Autonomous agents interacting with the real world need to learn new concepts efficiently and reliably. This requires learning in a low-data regime, which is a highly challenging problem. We address this task by introducing a fast optimization-based meta-learning method for few-shot classification. It consists of an embedding network, providing a general representation of the image, and a base learner module. The latter learns a linear classifier during the inference through an unrolled optimization procedure. We design an inner learning objective composed of (i) a robust classification loss on the support set and (ii) an entropy loss, allowing transductive learning from unlabeled query samples. By employing an efficient initialization module and a Steepest Descent based optimization algorithm, our base learner predicts a powerful classifier within only a few iterations. Further, our strategy enables important aspects of the base learner objective to be learned during meta-training. To the best of our knowledge, this work is the first to integrate both induction and transduction into the base learner in an optimization-based meta-learning framework. We perform a comprehensive experimental analysis, demonstrating the speed and effectiveness of our approach on four few-shot classification datasets. The Code is available at \href{https://github.com/4rdhendu/FIML}{\textcolor{blue}{https://github.com/4rdhendu/FIML}}.
In the time-series analysis, the time series motifs and the order patterns in time series can reveal general temporal patterns and dynamic features. Triadic Motif Field (TMF) is a simple and effective time-series image encoding method based on triadic time series motifs. Electrocardiography (ECG) signals are time-series data widely used to diagnose various cardiac anomalies. The TMF images contain the features characterizing the normal and Atrial Fibrillation (AF) ECG signals. Considering the quasi-periodic characteristics of ECG signals, the dynamic features can be extracted from the TMF images with the transfer learning pre-trained convolutional neural network (CNN) models. With the extracted features, the simple classifiers, such as the Multi-Layer Perceptron (MLP), the logistic regression, and the random forest, can be applied for accurate anomaly detection. With the test dataset of the PhysioNet Challenge 2017 database, the TMF classification model with the VGG16 transfer learning model and MLP classifier demonstrates the best performance with the 95.50% ROC-AUC and 88.43% F1 score in the AF classification. Besides, the TMF classification model can identify AF patients in the test dataset with high precision. The feature vectors extracted from the TMF images show clear patient-wise clustering with the t-distributed Stochastic Neighbor Embedding technique. Above all, the TMF classification model has very good clinical interpretability. The patterns revealed by symmetrized Gradient-weighted Class Activation Mapping have a clear clinical interpretation at the beat and rhythm levels.
The problem of adversarial defenses for image classification, where the goal is to robustify a classifier against adversarial examples, is considered. Inspired by the hypothesis that these examples lie beyond the natural image manifold, a novel aDversarIal defenSe with local impliCit functiOns (DISCO) is proposed to remove adversarial perturbations by localized manifold projections. DISCO consumes an adversarial image and a query pixel location and outputs a clean RGB value at the location. It is implemented with an encoder and a local implicit module, where the former produces per-pixel deep features and the latter uses the features in the neighborhood of query pixel for predicting the clean RGB value. Extensive experiments demonstrate that both DISCO and its cascade version outperform prior defenses, regardless of whether the defense is known to the attacker. DISCO is also shown to be data and parameter efficient and to mount defenses that transfers across datasets, classifiers and attacks.
In this paper, we describe the system for generating textual descriptions of short video clips using recurrent neural networks (RNN), which we used while participating in the Large Scale Movie Description Challenge 2015 in ICCV 2015. Our work builds on static image captioning systems with RNN based language models and extends this framework to videos utilizing both static image features and video-specific features. In addition, we study the usefulness of visual content classifiers as a source of additional information for caption generation. With experimental results we show that utilizing keyframe based features, dense trajectory video features and content classifier outputs together gives better performance than any one of them individually.
Pixel intensity is a widely used feature for clustering and segmentation algorithms, the resulting segmentation using only intensity values might suffer from noises and lack of spatial context information. Wavelet transform is often used for image denoising and classification. We proposed a novel method to incorporate Wavelet features in segmentation and clustering algorithms. The conventional K-means, Fuzzy c-means (FCM), and Active contour without edges (ACWE) algorithms were modified to adapt Wavelet features, leading to robust clustering/segmentation algorithms. A weighting parameter to control the weight of low-frequency sub-band information was also introduced. The new algorithms showed the capability to converge to different segmentation results based on the frequency information derived from the Wavelet sub-bands.