Search

This study addresses the challenge of self-supervised learning for 3D mesh analysis. It presents an new approach that uses random walks as a form of data augmentation to generate diverse representations of mesh surfaces. Furthermore, it employs a combination of contrastive and clustering losses. The contrastive learning framework maximizes similarity between augmented instances of the same mesh while minimizing similarity between different meshes. We integrate this with a clustering loss, enhancing class distinction across training epochs and mitigating training variance. Our model's effectiveness is evaluated using mean Average Precision (mAP) scores and a supervised SVM linear classifier on extracted features, demonstrating its potential for various downstream tasks such as object classification and shape retrieval.

The paper proposes a novel evaluation metric for automatic medical report generation from X-ray images, VLScore. It aims to overcome the limitations of existing evaluation methods, which either focus solely on textual similarities, ignoring clinical aspects, or concentrate only on a single clinical aspect, the pathology, neglecting all other factors. The key idea of our metric is to measure the similarity between radiology reports while considering the corresponding image. We demonstrate the benefit of our metric through evaluation on a dataset where radiologists marked errors in pairs of reports, showing notable alignment with radiologists' judgments. In addition, we provide a new dataset for evaluating metrics. This dataset includes well-designed perturbations that distinguish between significant modifications (e.g., removal of a diagnosis) and insignificant ones. It highlights the weaknesses in current evaluation metrics and provides a clear framework for analysis.

Medical report generation from X-ray images is a challenging task, particularly in an unpaired setting where paired image-report data is unavailable for training. To address this challenge, we propose a novel model that leverages the available information in two distinct datasets, one comprising reports and the other consisting of images. The core idea of our model revolves around the notion that combining auto-encoding report generation with multi-modal (report-image) alignment can offer a solution. However, the challenge persists regarding how to achieve this alignment when pair correspondence is absent. Our proposed solution involves the use of auxiliary tasks, particularly contrastive learning and classification, to position related images and reports in close proximity to each other. This approach differs from previous methods that rely on pre-processing steps, such as using external information stored in a knowledge graph. Our model, named MedRAT, surpasses previous state-of-the-art methods, demonstrating the feasibility of generating comprehensive medical reports without the need for paired data or external tools.

Generating medical reports for X-ray images presents a significant challenge, particularly in unpaired scenarios where access to paired image-report data for training is unavailable. Previous works have typically learned a joint embedding space for images and reports, necessitating a specific labeling schema for both. We introduce an innovative approach that eliminates the need for consistent labeling schemas, thereby enhancing data accessibility and enabling the use of incompatible datasets. This approach is based on cycle-consistent mapping functions that transform image embeddings into report embeddings, coupled with report auto-encoding for medical report generation. Our model and objectives consider intricate local details and the overarching semantic context within images and reports. This approach facilitates the learning of effective mapping functions, resulting in the generation of coherent reports. It outperforms state-of-the-art results in unpaired chest X-ray report generation, demonstrating improvements in both language and clinical metrics.

Bundle adjustment is the common way to solve localization and mapping. It is an iterative process in which a system of non-linear equations is solved using two optimization methods, weighted by a damping factor. In the classic approach, the latter is chosen heuristically by the Levenberg-Marquardt algorithm on each iteration. This might take many iterations, making the process computationally expensive, which might be harmful to real-time applications. We propose to replace this heuristic by viewing the problem in a holistic manner, as a game, and formulating it as a reinforcement-learning task. We set an environment which solves the non-linear equations and train an agent to choose the damping factor in a learned manner. We demonstrate that our approach considerably reduces the number of iterations required to reach the bundle adjustment's convergence, on both synthetic and real-life scenarios. We show that this reduction benefits the classic approach and can be integrated with other bundle adjustment acceleration methods.

Accurately detecting objects in the environment is a key challenge for autonomous vehicles. However, obtaining annotated data for detection is expensive and time-consuming. We introduce PatchContrast, a novel self-supervised point cloud pre-training framework for 3D object detection. We propose to utilize two levels of abstraction to learn discriminative representation from unlabeled data: proposal-level and patch-level. The proposal-level aims at localizing objects in relation to their surroundings, whereas the patch-level adds information about the internal connections between the object's components, hence distinguishing between different objects based on their individual components. We demonstrate how these levels can be integrated into self-supervised pre-training for various backbones to enhance the downstream 3D detection task. We show that our method outperforms existing state-of-the-art models on three commonly-used 3D detection datasets.

Anomaly detection aims at identifying images that deviate significantly from the norm. We focus on algorithms that embed the normal training examples in space and when given a test image, detect anomalies based on the features distance to the k-nearest training neighbors. We propose a new operator that takes into account the varying structure & importance of the features in the embedding space. Interestingly, this is done by taking into account not only the nearest neighbors, but also the neighbors of these neighbors (k-NNN). We show that by simply replacing the nearest neighbor component in existing algorithms by our k-NNN operator, while leaving the rest of the algorithms untouched, each algorithms own results are improved. This is the case both for common homogeneous datasets, such as flowers or nuts of a specific type, as well as for more diverse datasets

Medical imaging analysis plays a critical role in the diagnosis and treatment of various medical conditions. This paper focuses on chest X-ray images and their corresponding radiological reports. It presents a new model that learns a joint X-ray image & report representation. The model is based on a novel alignment scheme between the visual data and the text, which takes into account both local and global information. Furthermore, the model integrates domain-specific information of two types -- lateral images and the consistent visual structure of chest images. Our representation is shown to benefit three types of retrieval tasks: text-image retrieval, class-based retrieval, and phrase-grounding.

Controllable image captioning models generate human-like image descriptions, enabling some kind of control over the generated captions. This paper focuses on controlling the caption length, i.e. a short and concise description or a long and detailed one. Since existing image captioning datasets contain mostly short captions, generating long captions is challenging. To address the shortage of long training examples, we propose to enrich the dataset with varying-length self-generated captions. These, however, might be of varying quality and are thus unsuitable for conventional training. We introduce a novel training strategy that selects the data points to be used at different times during the training. Our method dramatically improves the length-control abilities, while exhibiting SoTA performance in terms of caption quality. Our approach is general and is shown to be applicable also to paragraph generation.

Archaeology is an intriguing domain for computer vision. It suffers not only from shortage in (labeled) data, but also from highly-challenging data, which is often extremely abraded and damaged. This paper proposes a novel semi-supervised model for classification and retrieval of images of archaeological artifacts. This model utilizes unique data that exists in the domain -- manual drawings made by special artists. These are used during training to implicitly transfer the domain knowledge from the drawings to their corresponding images, improving their classification results. We show that while learning how to classify, our model also learns how to generate drawings of the artifacts, an important documentation task, which is currently performed manually. Last but not least, we collected a new dataset of stamp-seals of the Southern Levant. Our code and dataset are publicly available., Comment: 8 pages, 9 figures

3D object detection within large 3D scenes is challenging not only due to the sparsity and irregularity of 3D point clouds, but also due to both the extreme foreground-background scene imbalance and class imbalance. A common approach is to add ground-truth objects from other scenes. Differently, we propose to modify the scenes by removing elements (voxels), rather than adding ones. Our approach selects the "meaningful" voxels, in a manner that addresses both types of dataset imbalance. The approach is general and can be applied to any voxel-based detector, yet the meaningfulness of a voxel is network-dependent. Our voxel selection is shown to improve the performance of several prominent 3D detection methods., Comment: CVPR 2023

A polygonal mesh is the most-commonly used representation of surfaces in computer graphics. Therefore, it is not surprising that a number of mesh classification networks have recently been proposed. However, while adversarial attacks are wildly researched in 2D, the field of adversarial meshes is under explored. This paper proposes a novel, unified, and general adversarial attack, which leads to misclassification of several state-of-the-art mesh classification neural networks. Our attack approach is black-box, i.e. it has access only to the network's predictions, but not to the network's full architecture or gradients. The key idea is to train a network to imitate a given classification network. This is done by utilizing random walks along the mesh surface, which gather geometric information. These walks provide insight onto the regions of the mesh that are important for the correct prediction of the given classification network. These mesh regions are then modified more than other regions in order to attack the network in a manner that is barely visible to the naked eye.

Point clouds are gaining prominence as a method for representing 3D shapes, but their irregular structure poses a challenge for deep learning methods. In this paper we propose CloudWalker, a novel method for learning 3D shapes using random walks. Previous works attempt to adapt Convolutional Neural Networks (CNNs) or impose a grid or mesh structure to 3D point clouds. This work presents a different approach for representing and learning the shape from a given point set. The key idea is to impose structure on the point set by multiple random walks through the cloud for exploring different regions of the 3D object. Then we learn a per-point and per-walk representation and aggregate multiple walk predictions at inference. Our approach achieves state-of-the-art results for two 3D shape analysis tasks: classification and retrieval.

Mesh representation by random walks has been shown to benefit deep learning. Randomness is indeed a powerful concept. However, it comes with a price: some walks might wander around non-characteristic regions of the mesh, which might be harmful to shape analysis, especially when only a few walks are utilized. We propose a novel walk-attention mechanism that leverages the fact that multiple walks are used. The key idea is that the walks may provide each other with information regarding the meaningful (attentive) features of the mesh. We utilize this mutual information to extract a single descriptor of the mesh. This differs from common attention mechanisms that use attention to improve the representation of each individual descriptor. Our approach achieves SOTA results for two basic 3D shape analysis tasks: classification and retrieval. Even a handful of walks along a mesh suffice for learning., Comment: 8 pages, 5 figures

This work focuses on object goal visual navigation, aiming at finding the location of an object from a given class, where in each step the agent is provided with an egocentric RGB image of the scene. We propose to learn the agent's policy using a reinforcement learning algorithm. Our key contribution is a novel attention probability model for visual navigation tasks. This attention encodes semantic information about observed objects, as well as spatial information about their place. This combination of the "what" and the "where" allows the agent to navigate toward the sought-after object effectively. The attention model is shown to improve the agent's policy and to achieve state-of-the-art results on commonly-used datasets.

Most attempts to represent 3D shapes for deep learning have focused on volumetric grids, multi-view images and point clouds. In this paper we look at the most popular representation of 3D shapes in computer graphics - a triangular mesh - and ask how it can be utilized within deep learning. The few attempts to answer this question propose to adapt convolutions & pooling to suit Convolutional Neural Networks (CNNs). This paper proposes a very different approach, termed MeshWalker, to learn the shape directly from a given mesh. The key idea is to represent the mesh by random walks along the surface, which "explore" the mesh's geometry and topology. Each walk is organized as a list of vertices, which in some manner imposes regularity on the mesh. The walk is fed into a Recurrent Neural Network (RNN) that "remembers" the history of the walk. We show that our approach achieves state-of-the-art results for two fundamental shape analysis tasks: shape classification and semantic segmentation. Furthermore, even a very small number of examples suffices for learning. This is highly important, since large datasets of meshes are difficult to acquire.

Visual illusions may be explained by the likelihood of patches in real-world images, as argued by input-driven paradigms in Neuro-Science. However, neither the data nor the tools existed in the past to extensively support these explanations. The era of big data opens a new opportunity to study input-driven approaches. We introduce a tool that computes the likelihood of patches, given a large dataset to learn from. Given this tool, we present a model that supports the approach and explains lightness and color visual illusions in a unified manner. Furthermore, our model generates visual illusions in natural images, by applying the same tool, reversely.

This paper proposes a novel approach to performing image-to-image translation between unpaired domains. Rather than relying on a cycle constraint, our method takes advantage of collaboration between various GANs. This results in a multi-modal method, in which multiple optional and diverse images are produced for a given image. Our model addresses some of the shortcomings of classical GANs: (1) It is able to remove large objects, such as glasses. (2) Since it does not need to support the cycle constraint, no irrelevant traces of the input are left on the generated image. (3) It manages to translate between domains that require large shape modifications. Our results are shown to outperform those generated by state-of-the-art methods for several challenging applications on commonly-used datasets, both qualitatively and quantitatively.

This paper deals with the prediction of the memorability of a given image. We start by proposing an algorithm that reaches human-level performance on the LaMem dataset - the only large scale benchmark for memorability prediction. The suggested algorithm is based on three observations we make regarding convolutional neural networks (CNNs) that affect memorability prediction. Having reached human-level performance we were humbled, and asked ourselves whether indeed we have resolved memorability prediction - and answered this question in the negative. We studied a few factors and made some recommendations that should be taken into account when designing the next benchmark.

Puzzle solving is a difficult problem in its own right, even when the pieces are all square and build up a natural image. But what if these ideal conditions do not hold? One such application domain is archaeology, where restoring an artifact from its fragments is highly important. From the point of view of computer vision, archaeological puzzle solving is very challenging, due to three additional difficulties: the fragments are of general shape; they are abraded, especially at the boundaries (where the strongest cues for matching should exist); and the domain of valid transformations between the pieces is continuous. The key contribution of this paper is a fully-automatic and general algorithm that addresses puzzle solving in this intriguing domain. We show that our state-of-the-art approach manages to correctly reassemble dozens of broken artifacts and frescoes.

This paper addresses the problem of viewpoint estimation of an object in a given image. It presents five key insights that should be taken into consideration when designing a CNN that solves the problem. Based on these insights, the paper proposes a network in which (i) The architecture jointly solves detection, classification, and viewpoint estimation. (ii) New types of data are added and trained on. (iii) A novel loss function, which takes into account both the geometry of the problem and the new types of data, is propose. Our network improves the state-of-the-art results for this problem by 9.8%., Comment: 17 pages, ECCV2018 submission