As neural networks grow in size and complexity, inference speeds decline. To combat this, one of the most effective compression techniques -- channel pruning -- removes channels from weights. However, for multi-branch segments of a model, channel removal can introduce inference-time memory copies. In turn, these copies increase inference latency -- so much so that the pruned model can be slower than the unpruned model. As a workaround, pruners conventionally constrain certain channels to be pruned together. This fully eliminates memory copies but, as we show, significantly impairs accuracy. We now have a dilemma: Remove constraints but increase latency, or add constraints and impair accuracy. In response, our insight is to reorder channels at export time, (1) reducing latency by reducing memory copies and (2) improving accuracy by removing constraints. Using this insight, we design a generic algorithm UPSCALE to prune models with any pruning pattern. By removing constraints from existing pruners, we improve ImageNet accuracy for post-training pruned models by 2.1 points on average -- benefiting DenseNet (+16.9), EfficientNetV2 (+7.9), and ResNet (+6.2). Furthermore, by reordering channels, UPSCALE improves inference speeds by up to 2x over a baseline export.

Advances in image-based dietary assessment methods have allowed nutrition professionals and researchers to improve the accuracy of dietary assessment, where images of food consumed are captured using smartphones or wearable devices. These images are then analyzed using computer vision methods to estimate energy and nutrition content of the foods. Food image segmentation, which determines the regions in an image where foods are located, plays an important role in this process. Current methods are data dependent and thus cannot generalize well for different food types. To address this problem, we propose a class-agnostic food image segmentation method. Our method uses a pair of eating scene images, one before starting eating and one after eating is completed. Using information from both the before and after eating images, we can segment food images by finding the salient missing objects without any prior information about the food class. We model a paradigm of top-down saliency that guides the attention of the human visual system based on a task to find the salient missing objects in a pair of images. Our method is validated on food images collected from a dietary study that showed promising results.

Face obscuration is needed by law enforcement and mass media outlets to guarantee privacy. Sharing sensitive content where obscuration or redaction techniques have failed to completely remove all identifiable traces can lead to many legal and social issues. Hence, we need to be able to systematically measure the face obscuration performance of a given technique. In this paper we propose to measure the effectiveness of eight obscuration techniques. We do so by attacking the redacted faces in three scenarios: obscured face identification, verification, and reconstruction. Threat modeling is also considered to provide a vulnerability analysis for each studied obscuration technique. Based on our evaluation, we show that the k-same based methods are the most effective.

It is well known that dietary habits have a significant influence on health. While many studies have been conducted to understand this relationship, little is known about the relationship between eating environments and health. Yet researchers and health agencies around the world have recognized the eating environment as a promising context for improving diet and health. In this paper, we propose an image clustering method to automatically extract the eating environments from eating occasion images captured during a community dwelling dietary study. Specifically, we are interested in learning how many different environments an individual consumes food in. Our method clusters images by extracting features at both global and local scales using a deep neural network. The variation in the number of clusters and images captured by different individual makes this a very challenging problem. Experimental results show that our method performs significantly better compared to several existing clustering approaches.

Recent advances in convolutional neural networks (CNN) have achieved remarkable results in locating objects in images. In these networks, the training procedure usually requires providing bounding boxes or the maximum number of expected objects. In this paper, we address the task of estimating object locations without annotated bounding boxes which are typically hand-drawn and time consuming to label. We propose a loss function that can be used in any fully convolutional network (FCN) to estimate object locations. This loss function is a modification of the average Hausdorff distance between two unordered sets of points. The proposed method has no notion of bounding boxes, region proposals, or sliding windows. We evaluate our method with three datasets designed to locate people's heads, pupil centers and plant centers. We outperform state-of-the-art generic object detectors and methods fine-tuned for pupil tracking.

The recent advancements in image processing and computer vision allow realistic photo manipulations. In order to avoid the distribution of fake imagery, the image forensics community is working towards the development of image authenticity verification tools. Methods based on shadow analysis are particularly reliable since they are part of the physical integrity of the scene, thus detecting forgeries is possible whenever inconsistencies are found (e.g., shadows not coherent with the light direction). An attacker can easily delete inconsistent shadows and replace them with correctly cast shadows in order to fool forensics detectors based on physical analysis. In this paper, we propose a method to detect shadow removal done with state-of-the-art tools. The proposed method is based on a conditional generative adversarial network (cGAN) specifically trained for shadow removal detection.

In recent years, the number of images shared online has continuously grown. The forensics community has kept the pace by developing techniques to both reliably extract information from these images, but also to remove it. In particular, the latest developments in image anonymization methods exposes an attack vector when used by skilled ill-intentioned image producers that may want to elude prosecution. We present an approach to detect whether or not an image has undergone a laundering process, i.e., it has been tampered with so that its unique characterizing features have been changed to avoid detection. We focus on the photo response non uniformity (PRNU) noise unique to every imaging sensor, and we consider that an image has been "laundered" when we detect the absence of PRNU from an image. We propose a per image preprocessing pipeline that generates information-rich features later used as input of fine-tuned convolutional neural networks (CNNs). We study the performance of the proposed approach using various CNN architectures and blind anonymization techniques and show its effectiveness under several training and testing scenarios. Our results also show that CNN models trained with the proposed feature are capable of generalizing over unseen devices and are robust against non-geometric transformations.

In recent months a machine learning based free software tool has made it easy to create believable face swaps in videos that leaves few traces of manipulation, in what are known as "deepfake" videos. Scenarios where these realistic fake videos are used to create political distress, blackmail someone or fake terrorism events are easily envisioned. This paper proposes a temporal-aware pipeline to automatically detect deepfake videos. Our system uses a convolutional neural network (CNN) to extract frame-level features. These features are then used to train a recurrent neural network (RNN) that learns to classify if a video has been subject to manipulation or not. We evaluate our method against a large set of deepfake videos collected from multiple video websites. We show how our system can achieve competitive results in this task while using a simple architecture.

Among the image forensic issues investigated in the last few years, great attention has been devoted to blind camera model attribution. This refers to the problem of detecting which camera model has been used to acquire an image by only exploiting pixel information. Solving this problem has great impact on image integrity assessment as well as on authenticity verification. Recent advancements that use convolutional neural networks (CNNs) in the media forensic field have enabled camera model attribution methods to work well even on small image patches. These improvements are also important for determining forgery localization. Some patches of an image may not contain enough information related to the camera model (e.g., saturated patches). In this paper, we propose a CNN-based solution to estimate the camera model attribution reliability of a given image patch. We show that we can estimate a reliabilitymap indicating which portions of the image contain reliable camera traces. Testing using a well known dataset confirms that by using this information, it is possible to increase small patch camera model attribution accuracy by more than 8% on a single patch.

Pedestrian detection is a fundamental task for many applications including autonomous vehicles and surveillance systems. In a mobile or networked environment bandwidth is limited and adaptive datarate streaming is used. Video compression can introduce significant quality degradation that impacts the accuracy of video analytics. In this paper, we examine the problem of a changing video data-rate and examine how it affects the performance of video analytics, in particular pedestrian detection, using a two-stage quality-adaptive convolutional neural network system. Our experimental results demonstrate that when adaptive data-rate streaming is used, our proposed quality-adaptive approach reduces the miss rate by 20% compared to the baseline detector.

Detecting the camera model used to shoot a picture enables to solve a wide series of forensic problems, from copyright infringement to ownership attribution. For this reason, the forensic community has developed a set of camera model identification algorithms that exploit characteristic traces left on acquired images by the processing pipelines specific of each camera model. In this letter, we investigate a novel approach to solve camera model identification problem. Specifically, we propose a data-driven algorithm based on convolutional neural networks, which learns features characterizing each camera model directly from the acquired pictures. Results on a well-known dataset of 18 camera models show that: 1) the proposed method outperforms up-to-date state-of-the-art algorithms on classification of 64 × 64 color image patches; 2) features learned by the proposed network generalize to camera models never used for training.