Anomaly Detection and Segmentation (AD&S) is crucial for industrial quality control. While existing methods excel in generating anomaly scores for each pixel, practical applications require producing a binary segmentation to identify anomalies. Due to the absence of labeled anomalies in many real scenarios, standard practices binarize these maps based on some statistics derived from a validation set containing only nominal samples, resulting in poor segmentation performance. This paper addresses this problem by proposing a test time training strategy to improve the segmentation performance. Indeed, at test time, we can extract rich features directly from anomalous samples to train a classifier that can discriminate defects effectively. Our general approach can work downstream to any AD&S method that provides an anomaly score map as output, even in multimodal settings. We demonstrate the effectiveness of our approach over baselines through extensive experimentation and evaluation on MVTec AD and MVTec 3D-AD.
The paper explores the industrial multimodal Anomaly Detection (AD) task, which exploits point clouds and RGB images to localize anomalies. We introduce a novel light and fast framework that learns to map features from one modality to the other on nominal samples. At test time, anomalies are detected by pinpointing inconsistencies between observed and mapped features. Extensive experiments show that our approach achieves state-of-the-art detection and segmentation performance in both the standard and few-shot settings on the MVTec 3D-AD dataset while achieving faster inference and occupying less memory than previous multimodal AD methods. Moreover, we propose a layer-pruning technique to improve memory and time efficiency with a marginal sacrifice in performance.
While text-conditional 3D object generation and manipulation have seen rapid progress, the evaluation of coherence between generated 3D shapes and input textual descriptions lacks a clear benchmark. The reason is twofold: a) the low quality of the textual descriptions in the only publicly available dataset of text-shape pairs; b) the limited effectiveness of the metrics used to quantitatively assess such coherence. In this paper, we propose a comprehensive solution that addresses both weaknesses. Firstly, we employ large language models to automatically refine textual descriptions associated with shapes. Secondly, we propose a quantitative metric to assess text-to-shape coherence, through cross-attention mechanisms. To validate our approach, we conduct a user study and compare quantitatively our metric with existing ones. The refined dataset, the new metric and a set of text-shape pairs validated by the user study comprise a novel, fine-grained benchmark that we publicly release to foster research on text-to-shape coherence of text-conditioned 3D generative models. Benchmark available at https://cvlab-unibo.github.io/CrossCoherence-Web/.
In semantic image synthesis, the state of the art is dominated by methods that use spatially-adaptive normalization layers, which allow for excellent visual generation quality and editing versatility. Granted their efficacy, recent research efforts have focused toward finer-grained local style control and multi-modal generation. By construction though, such layers tend to overlook global image statistics leading to unconvincing local style editing and causing global inconsistencies such as color or illumination distribution shifts. Also, the semantic layout is required for mapping styles in the generator, putting a strict alignment constraint over the features. In response, we designed a novel architecture where cross-attention layers are used in place of de-normalization ones for conditioning the image generation. Our model inherits the advantages of both solutions, retaining state-of-the-art reconstruction quality, as well as improved global and local style transfer. Code and models available at https://github.com/TFonta/CA2SIS.
Deep generative models have shown impressive results in generating realistic images of faces. GANs managed to generate high-quality, high-fidelity images when conditioned on semantic masks, but they still lack the ability to diversify their output. Diffusion models partially solve this problem and are able to generate diverse samples given the same condition. In this paper, we propose a multi-conditioning approach for diffusion models via cross-attention exploiting both attributes and semantic masks to generate high-quality and controllable face images. We also studied the impact of applying perceptual-focused loss weighting into the latent space instead of the pixel space. Our method extends the previous approaches by introducing conditioning on more than one set of features, guaranteeing a more fine-grained control over the generated face images. We evaluate our approach on the CelebA-HQ dataset, and we show that it can generate realistic and diverse samples while allowing for fine-grained control over multiple attributes and semantic regions. Additionally, we perform an ablation study to evaluate the impact of different conditioning strategies on the quality and diversity of the generated images.
In this paper, we propose to exploit the side-tuning framework for multimodal document classification. Side-tuning is a methodology for network adaptation recently introduced to solve some of the problems related to previous approaches. Thanks to this technique it is actually possible to overcome model rigidity and catastrophic forgetting of transfer learning by fine-tuning. The proposed solution uses off-the-shelf deep learning architectures leveraging the side-tuning framework to combine a base model with a tandem of two side networks. We show that side-tuning can be successfully employed also when different data sources are considered, e.g. text and images in document classification. The experimental results show that this approach pushes further the limit for document classification accuracy with respect to the state of the art.
Although one of the most popular practices in photography since the end of the 19th century, an increase in scholarly interest in family photo albums dates back to the early 1980s. Such collections of photos may reveal sociological and historical insights regarding specific cultures and times. They are, however, in most cases scattered among private homes and only available on paper or photographic film, thus making their analysis by academics such as historians, social-cultural anthropologists and cultural theorists very cumbersome. In this paper, we analyze the IMAGO dataset including photos belonging to family albums assembled at the University of Bologna's Rimini campus since 2004. Following a deep learning-based approach, the IMAGO dataset has offered the opportunity of experimenting with photos taken between year 1845 and year 2009, with the goals of assessing the dates and the socio-historical contexts of the images, without use of any other sources of information. Exceeding our initial expectations, such analysis has revealed its merit not only in terms of the performance of the approach adopted in this work, but also in terms of the foreseeable implications and use for the benefit of socio-historical research. To the best of our knowledge, this is the first work that moves along this path in literature.
Person re-identification is best known as the problem of associating a single person that is observed from one or more disjoint cameras. The existing literature has mainly addressed such an issue, neglecting the fact that people usually move in groups, like in crowded scenarios. We believe that the additional information carried by neighboring individuals provides a relevant visual context that can be exploited to obtain a more robust match of single persons within the group. Despite this, re-identifying groups of people compound the common single person re-identification problems by introducing changes in the relative position of persons within the group and severe self-occlusions. In this paper, we propose a solution for group re-identification that grounds on transferring knowledge from single person re-identification to group re-identification by exploiting sparse dictionary learning. First, a dictionary of sparse atoms is learned using patches extracted from single person images. Then, the learned dictionary is exploited to obtain a sparsity-driven residual group representation, which is finally matched to perform the re-identification. Extensive experiments on the i-LIDS groups and two newly collected datasets show that the proposed solution outperforms state-of-the-art approaches.
Human motion and behaviour in crowded spaces is influenced by several factors, such as the dynamics of other moving agents in the scene, as well as the static elements that might be perceived as points of attraction or obstacles. In this work, we present a new model for human trajectory prediction which is able to take advantage of both human-human and human-space interactions. The future trajectory of humans, are generated by observing their past positions and interactions with the surroundings. To this end, we propose a "context-aware" recurrent neural network LSTM model, which can learn and predict human motion in crowded spaces such as a sidewalk, a museum or a shopping mall. We evaluate our model on a public pedestrian datasets, and we contribute a new challenging dataset that collects videos of humans that navigate in a (real) crowded space such as a big museum. Results show that our approach can predict human trajectories better when compared to previous state-of-the-art forecasting models.
In this paper we introduce a method to overcome one of the main challenges of person re-identification in multi-camera networks, namely cross-view appearance changes. The proposed solution addresses the extreme variability of person appearance in different camera views by exploiting multiple feature representations. For each feature, Kernel Canonical Correlation Analysis (KCCA) with different kernels is exploited to learn several projection spaces in which the appearance correlation between samples of the same person observed from different cameras is maximized. An iterative logistic regression is finally used to select and weigh the contributions of each feature projections and perform the matching between the two views. Experimental evaluation shows that the proposed solution obtains comparable performance on VIPeR and PRID 450s datasets and improves on PRID and CUHK01 datasets with respect to the state of the art.