Recently, several Vision Transformer (ViT) based methods have been proposed for Fine-Grained Visual Classification (FGVC).These methods significantly surpass existing CNN-based ones, demonstrating the effectiveness of ViT in FGVC tasks.However, there are some limitations when applying ViT directly to FGVC.First, ViT needs to split images into patches and calculate the attention of every pair, which may result in heavy redundant calculation and unsatisfying performance when handling fine-grained images with complex background and small objects.Second, a standard ViT only utilizes the class token in the final layer for classification, which is not enough to extract comprehensive fine-grained information. To address these issues, we propose a novel ViT based fine-grained object discriminator for FGVC tasks, ViT-FOD for short. Specifically, besides a ViT backbone, it further introduces three novel components, i.e, Attention Patch Combination (APC), Critical Regions Filter (CRF), and Complementary Tokens Integration (CTI). Thereinto, APC pieces informative patches from two images to generate a new image so that the redundant calculation can be reduced. CRF emphasizes tokens corresponding to discriminative regions to generate a new class token for subtle feature learning. To extract comprehensive information, CTI integrates complementary information captured by class tokens in different ViT layers. We conduct comprehensive experiments on widely used datasets and the results demonstrate that ViT-FOD is able to achieve state-of-the-art performance.
Face identification (FI) is ubiquitous and drives many high-stake decisions made by law enforcement. State-of-the-art FI approaches compare two images by taking the cosine similarity between their image embeddings. Yet, such an approach suffers from poor out-of-distribution (OOD) generalization to new types of images (e.g., when a query face is masked, cropped, or rotated) not included in the training set or the gallery. Here, we propose a re-ranking approach that compares two faces using the Earth Mover's Distance on the deep, spatial features of image patches. Our extra comparison stage explicitly examines image similarity at a fine-grained level (e.g., eyes to eyes) and is more robust to OOD perturbations and occlusions than traditional FI. Interestingly, without finetuning feature extractors, our method consistently improves the accuracy on all tested OOD queries: masked, cropped, rotated, and adversarial while obtaining similar results on in-distribution images.
In this paper, we propose an effective and efficient method for Human-Gaze-Target (HGT) detection, i.e., gaze following. Current approaches decouple the HGT detection task into separate branches of salient object detection and human gaze prediction, employing a two-stage framework where human head locations must first be detected and then be fed into the next gaze target prediction sub-network. In contrast, we redefine the HGT detection task as detecting human head locations and their gaze targets, simultaneously. By this way, our method, named Human-Gaze-Target detection TRansformer or HGTTR, streamlines the HGT detection pipeline by eliminating all other additional components. HGTTR reasons about the relations of salient objects and human gaze from the global image context. Moreover, unlike existing two-stage methods that require human head locations as input and can predict only one human's gaze target at a time, HGTTR can directly predict the locations of all people and their gaze targets at one time in an end-to-end manner. The effectiveness and robustness of our proposed method are verified with extensive experiments on the two standard benchmark datasets, GazeFollowing and VideoAttentionTarget. Without bells and whistles, HGTTR outperforms existing state-of-the-art methods by large margins (6.4 mAP gain on GazeFollowing and 10.3 mAP gain on VideoAttentionTarget) with a much simpler architecture.
Several research groups have shown that Generative Adversarial Networks (GANs) can generate photo-realistic images in recent years. Using the GANs, a map is created between a latent code and a photo-realistic image. This process can also be reversed: given a photo as input, it is possible to obtain the corresponding latent code. In this paper, we will show how the inversion process can be easily exploited to interpret the latent space and control the output of StyleGAN2, a GAN architecture capable of generating photo-realistic faces. From a biological perspective, facial features such as nose size depend on important genetic factors, and we explore the latent spaces that correspond to such biological features, including masculinity and eye colour. We show the results obtained by applying the proposed method to a set of photos extracted from the CelebA-HQ database. We quantify some of these measures by utilizing two landmarking protocols, and evaluate their robustness through statistical analysis. Finally we correlate these measures with the input parameters used to perturb the latent spaces along those interpretable directions. Our results contribute towards building the groundwork of using such GAN architecture in forensics to generate photo-realistic faces that satisfy certain biological attributes.
Recently, neural networks purely based on attention were shown to address image understanding tasks such as image classification. However, these visual transformers are pre-trained with hundreds of millions of images using an expensive infrastructure, thereby limiting their adoption by the larger community. In this work, with an adequate training scheme, we produce a competitive convolution-free transformer by training on Imagenet only. We train it on a single computer in less than 3 days. Our reference vision transformer (86M parameters) achieves top-1 accuracy of 83.1% (single-crop evaluation) on ImageNet with no external data. We share our code and models to accelerate community advances on this line of research. Additionally, we introduce a teacher-student strategy specific to transformers. It relies on a distillation token ensuring that the student learns from the teacher through attention. We show the interest of this token-based distillation, especially when using a convnet as a teacher. This leads us to report results competitive with convnets for both Imagenet (where we obtain up to 84.4% accuracy) and when transferring to other tasks.
Collaborative machine learning settings like federated learning can be susceptible to adversarial interference and attacks. One class of such attacks is termed model inversion attacks, characterised by the adversary reverse-engineering the model to extract representations and thus disclose the training data. Prior implementations of this attack typically only rely on the captured data (i.e. the shared gradients) and do not exploit the data the adversary themselves control as part of the training consortium. In this work, we propose a novel model inversion framework that builds on the foundations of gradient-based model inversion attacks, but additionally relies on matching the features and the style of the reconstructed image to data that is controlled by an adversary. Our technique outperforms existing gradient-based approaches both qualitatively and quantitatively, while still maintaining the same honest-but-curious threat model, allowing the adversary to obtain enhanced reconstructions while remaining concealed.
In this work, we address the problem of estimating the so-called "Social Distancing" given a single uncalibrated image in unconstrained scenarios. Our approach proposes a semi-automatic solution to approximate the homography matrix between the scene ground and image plane. With the estimated homography, we then leverage an off-the-shelf pose detector to detect body poses on the image and to reason upon their inter-personal distances using the length of their body-parts. Inter-personal distances are further locally inspected to detect possible violations of the social distancing rules. We validate our proposed method quantitatively and qualitatively against baselines on \rev{public domain} dataset\rev{s} for which we provided groundtruth on inter-personal distances. Besides, we demonstrate the application of our method deployed in \rev{a} real testing scenario where statistics on the inter-personal distances are currently used to improve the safety in a critical environment.
Food is not only a basic human necessity but also a key factor driving a society's health and economic well-being. As a result, the cooking domain is a popular use-case to demonstrate decision-support (AI) capabilities in service of benefits like precision health with tools ranging from information retrieval interfaces to task-oriented chatbots. An AI here should understand concepts in the food domain (e.g., recipes, ingredients), be tolerant to failures encountered while cooking (e.g., browning of butter), handle allergy-based substitutions, and work with multiple data modalities (e.g. text and images). However, the recipes today are handled as textual documents which makes it difficult for machines to read, reason and handle ambiguity. This demands a need for better representation of the recipes, overcoming the ambiguity and sparseness that exists in the current textual documents. In this paper, we discuss the construction of a machine-understandable rich recipe representation (R3), in the form of plans, from the recipes available in natural language. R3 is infused with additional knowledge such as information about allergens and images of ingredients, possible failures and tips for each atomic cooking step. To show the benefits of R3, we also present TREAT, a tool for recipe retrieval which uses R3 to perform multi-modal reasoning on the recipe's content (plan objects - ingredients and cooking tools), food preparation process (plan actions and time), and media type (image, text). R3 leads to improved retrieval efficiency and new capabilities that were hither-to not possible in textual representation.
This is a tutorial and survey paper on Generative Adversarial Network (GAN), adversarial autoencoders, and their variants. We start with explaining adversarial learning and the vanilla GAN. Then, we explain the conditional GAN and DCGAN. The mode collapse problem is introduced and various methods, including minibatch GAN, unrolled GAN, BourGAN, mixture GAN, D2GAN, and Wasserstein GAN, are introduced for resolving this problem. Then, maximum likelihood estimation in GAN are explained along with f-GAN, adversarial variational Bayes, and Bayesian GAN. Then, we cover feature matching in GAN, InfoGAN, GRAN, LSGAN, energy-based GAN, CatGAN, MMD GAN, LapGAN, progressive GAN, triple GAN, LAG, GMAN, AdaGAN, CoGAN, inverse GAN, BiGAN, ALI, SAGAN, Few-shot GAN, SinGAN, and interpolation and evaluation of GAN. Then, we introduce some applications of GAN such as image-to-image translation (including PatchGAN, CycleGAN, DeepFaceDrawing, simulated GAN, interactive GAN), text-to-image translation (including StackGAN), and mixing image characteristics (including FineGAN and MixNMatch). Finally, we explain the autoencoders based on adversarial learning including adversarial autoencoder, PixelGAN, and implicit autoencoder.
Recently, zero-shot image classification by vision-language pre-training has demonstrated incredible achievements, that the model can classify arbitrary category without seeing additional annotated images of that category. However, it is still unclear how to make the zero-shot recognition working well on broader vision problems, such as object detection and semantic segmentation. In this paper, we target for zero-shot semantic segmentation, by building it on an off-the-shelf pre-trained vision-language model, i.e., CLIP. It is difficult because semantic segmentation and the CLIP model perform on different visual granularity, that semantic segmentation processes on pixels while CLIP performs on images. To remedy the discrepancy on processing granularity, we refuse the use of the prevalent one-stage FCN based framework, and advocate a two-stage semantic segmentation framework, with the first stage extracting generalizable mask proposals and the second stage leveraging an image based CLIP model to perform zero-shot classification on the masked image crops which are generated in the first stage. Our experimental results show that this simple framework surpasses previous state-of-the-arts by a large margin: +29.5 hIoU on the Pascal VOC 2012 dataset, and +8.9 hIoU on the COCO Stuff dataset. With its simplicity and strong performance, we hope this framework to serve as a baseline to facilitate the future research.