Abstract: Image-to-image (I2I) translation has matured in recent years and is able to generate high-quality realistic images. However, despite current success, it still faces important challenges when applied to small domains. Existing methods use transfer learning for I2I translation, but they still require the learning of millions of parameters from scratch. This drawback severely limits its application on small domains. In this paper, we propose a new transfer learning for I2I translation (TransferI2I). We decouple our learning process into the image generation step and the I2I translation step. In the first step we propose two novel techniques: source-target initialization and self-initialization of the adaptor layer. The former finetunes the pretrained generative model (e.g., StyleGAN) on source and target data. The latter allows to initialize all non-pretrained network parameters without the need of any data. These techniques provide a better initialization for the I2I translation step. In addition, we introduce an auxiliary GAN that further facilitates the training of deep I2I systems even from small datasets. In extensive experiments on three datasets, (Animal faces, Birds, and Foods), we show that we outperform existing methods and that mFID improves on several datasets with over 25 points.

Abstract: In this work, we study the suitability of high dynamic range, wide color gamut (HDR/WCG) objective quality metrics to assess the perceived deterioration of compressed images encoded using the hybrid log-gamma (HLG) method, which is the standard for HDR television. Several image quality metrics have been developed to deal specifically with HDR content, although in previous work we showed that the best results (i.e., better matches to the opinion of human expert observers) are obtained by an HDR metric that consists simply in applying a given standard dynamic range metric, called visual information fidelity (VIF), directly to HLG-encoded images. However, all these HDR metrics ignore the chroma components for their calculations, that is, they consider only the luminance channel. For this reason, in the current work, we conduct subjective evaluation experiments in a professional setting using compressed HDR/WCG images encoded with HLG and analyze the ability of the best HDR metric to detect perceivable distortions in the chroma components, as well as the suitability of popular color metrics (including ΔITPR , which supports parameters for HLG) to correlate with the opinion scores. Our first contribution is to show that there is a need to consider the chroma components in HDR metrics, as there are color distortions that subjects perceive but that the best HDR metric fails to detect. Our second contribution is the surprising result that VIF, which utilizes only the luminance channel, correlates much better with the subjective evaluation scores than the metrics investigated that do consider the color components.

Abstract: Learning continually from non-stationary data streams is a long-standing goal and a challenging problem in machine learning. Recently, we have witnessed a renewed and fast-growing interest in continual learning, especially within the deep learning community. However, algorithmic solutions are often difficult to re-implement, evaluate and port across different settings, where even results on standard benchmarks are hard to reproduce. In this work, we propose Avalanche, an open-source end-to-end library for continual learning research based on PyTorch. Avalanche is designed to provide a shared and collaborative codebase for fast prototyping, training, and reproducible evaluation of continual learning algorithms.

Abstract: In the film industry, the same movie is expected to be watched on displays of vastly different sizes, from cinema screens to mobile phones. But visual induction, the perceptual phenomenon by which the appearance of a scene region is affected by its surroundings, will be different for the same image shown on two displays of different dimensions. This phenomenon presents a practical challenge for the preservation of the artistic intentions of filmmakers, because it can lead to shifts in image appearance between viewing destinations. In this work, we show that a neural field model based on the efficient representation principle is able to predict induction effects and how, by regularizing its associated energy functional, the model is still able to represent induction but is now invertible. From this finding, we propose a method to preprocess an image in a screen–size dependent way so that its perception, in terms of visual induction, may remain constant across displays of different size. The potential of the method is demonstrated through psychophysical experiments on synthetic images and qualitative examples on natural images.

Abstract: We present EgoACO, a deep neural architecture for video action recognition that learns to pool action-context-object descriptors from frame level features by leveraging the verb-noun structure of action labels in egocentric video datasets. The core component of EgoACO is class activation pooling (CAP), a differentiable pooling operation that combines ideas from bilinear pooling for fine-grained recognition and from feature learning for discriminative localization. CAP uses self-attention with a dictionary of learnable weights to pool from the most relevant feature regions. Through CAP, EgoACO learns to decode object and scene context descriptors from video frame features. For temporal modeling in EgoACO, we design a recurrent version of class activation pooling termed Long Short-Term Attention (LSTA). LSTA extends convolutional gated LSTM with built-in spatial attention and a re-designed output gate. Action, object and context descriptors are fused by a multi-head prediction that accounts for the inter-dependencies between noun-verb-action structured labels in egocentric video datasets. EgoACO features built-in visual explanations, helping learning and interpretation. Results on the two largest egocentric action recognition datasets currently available, EPIC-KITCHENS and EGTEA, show that by explicitly decoding action-context-object descriptors, EgoACO achieves state-of-the-art recognition performance.

Abstract: Modern computer vision requires processing large amounts of data, both while training the model and/or during inference, once the model is deployed. Scenarios where images are captured and processed in physically separated locations are increasingly common (e.g. autonomous vehicles, cloud computing). In addition, many devices suffer from limited resources to store or transmit data (e.g. storage space, channel capacity). In these scenarios, lossy image compression plays a crucial role to effectively increase the number of images collected under such constraints. However, lossy compression entails some undesired degradation of the data that may harm the performance of the downstream analysis task at hand, since important semantic information may be lost in the process. Moreover, we may only have compressed images at training time but are able to use original images at inference time, or vice versa, and in such a case, the downstream model suffers from covariate shift. In this paper, we analyze this phenomenon, with a special focus on vision-based perception for autonomous driving as a paradigmatic scenario. We see that loss of semantic information and covariate shift do indeed exist, resulting in a drop in performance that depends on the compression rate. In order to address the problem, we propose dataset restoration, based on image restoration with generative adversarial networks (GANs). Our method is agnostic to both the particular image compression method and the downstream task; and has the advantage of not adding additional cost to the deployed models, which is particularly important in resource-limited devices. The presented experiments focus on semantic segmentation as a challenging use case, cover a broad range of compression rates and diverse datasets, and show how our method is able to significantly alleviate the negative effects of compression on the downstream visual task.

Abstract: A signed distance function (SDF) as the 3D shape description is one of the most effective approaches to represent 3D geometry for rendering and reconstruction. Our work is inspired by the state-of-the-art method DeepSDF [17] that learns and analyzes the 3D shape as the iso-surface of its shell and this method has shown promising results especially in the 3D shape reconstruction and compression domain. In this paper, we consider the degeneration problem of reconstruction coming from the capacity decrease of the DeepSDF model, which approximates the SDF with a neural network and a single latent code. We propose Local Geometry Code Learning (LGCL), a model that improves the original DeepSDF results by learning from a local shape geometry of the full 3D shape. We add an extra graph neural network to split the single transmittable latent code into a set of local latent codes distributed on the 3D shape. Mentioned latent codes are used to approximate the SDF in their local regions, which will alleviate the complexity of the approximation compared to the original DeepSDF. Furthermore, we introduce a new geometric loss function to facilitate the training of these local latent codes. Note that other local shape adjusting methods use the 3D voxel representation, which in turn is a problem highly difficult to solve or even is insolvable. In contrast, our architecture is based on graph processing implicitly and performs the learning regression process directly in the latent code space, thus make the proposed architecture more flexible and also simple for realization. Our experiments on 3D shape reconstruction demonstrate that our LGCL method can keep more details with a significantly smaller size of the SDF decoder and outperforms considerably the original DeepSDF method under the most important quantitative metrics.