Recently, learned image compression methods have shown superior performance compared to the traditional hand-crafted image codecs including BPG. One of the fundamental research directions in learned image compression is to develop entropy models that accurately estimate the probability distribution of the quantized latent representation. Like other vision tasks, most of the recent learned entropy models are based on convolutional neural networks (CNNs). However, CNNs have a limitation in modeling dependencies between distant regions due to their nature of local connectivity, which can be a significant bottleneck in image compression where reducing spatial redundancy is a key point. To address this issue, we propose a novel entropy model called Information Transformer (Informer) that exploits both local and global information in a content-dependent manner using an attention mechanism. Our experiments demonstrate that Informer improves rate-distortion performance over the state-of-the-art methods on the Kodak and Tecnick datasets without the quadratic computational complexity problem.
Transformer-based models, such as the Vision Transformer (ViT), can outperform onvolutional Neural Networks (CNNs) in some vision tasks when there is sufficient training data. However, (CNNs) have a strong and useful inductive bias for vision tasks (i.e. translation equivariance and locality). In this work, we developed a novel model architecture that we call a Mobile fish landmark detection network (MFLD-net). We have made this model using convolution operations based on ViT (i.e. Patch embeddings, Multi-Layer Perceptrons). MFLD-net can achieve competitive or better results in low data regimes while being lightweight and therefore suitable for embedded and mobile devices. Furthermore, we show that MFLD-net can achieve keypoint (landmark) estimation accuracies on-par or even better than some of the state-of-the-art (CNNs) on a fish image dataset. Additionally, unlike ViT, MFLD-net does not need a pre-trained model and can generalise well when trained on a small dataset. We provide quantitative and qualitative results that demonstrate the model's generalisation capabilities. This work will provide a foundation for future efforts in developing mobile, but efficient fish monitoring systems and devices.
In computer vision, human pose synthesis and transfer deal with probabilistic image generation of a person in a previously unseen pose from an already available observation of that person. Though researchers have recently proposed several methods to achieve this task, most of these techniques derive the target pose directly from the desired target image on a specific dataset, making the underlying process challenging to apply in real-world scenarios as the generation of the target image is the actual aim. In this paper, we first present the shortcomings of current pose transfer algorithms and then propose a novel text-based pose transfer technique to address those issues. We divide the problem into three independent stages: (a) text to pose representation, (b) pose refinement, and (c) pose rendering. To the best of our knowledge, this is one of the first attempts to develop a text-based pose transfer framework where we also introduce a new dataset DF-PASS, by adding descriptive pose annotations for the images of the DeepFashion dataset. The proposed method generates promising results with significant qualitative and quantitative scores in our experiments.
Deep neural networks used for image classification often use convolutional filters to extract distinguishing features before passing them to a linear classifier. Most interpretability literature focuses on providing semantic meaning to convolutional filters to explain a model's reasoning process and confirm its use of relevant information from the input domain. Fully connected layers can be studied by decomposing their weight matrices using a singular value decomposition, in effect studying the correlations between the rows in each matrix to discover the dynamics of the map. In this work we define a singular value decomposition for the weight tensor of a convolutional layer, which provides an analogous understanding of the correlations between filters, exposing the dynamics of the convolutional map. We validate our definition using recent results in random matrix theory. By applying the decomposition across the linear layers of an image classification network we suggest a framework against which interpretability methods might be applied using hypergraphs to model class separation. Rather than looking to the activations to explain the network, we use the singular vectors with the greatest corresponding singular values for each linear layer to identify those features most important to the network. We illustrate our approach with examples and introduce the DeepDataProfiler library, the analysis tool used for this study.
In computer vision, fine-tuning is the de-facto approach to leverage pre-trained vision models to perform downstream tasks. However, deploying it in practice is quite challenging, due to adopting parameter inefficient global update and heavily relying on high-quality downstream data. Recently, prompt-based learning, which adds a task-relevant prompt to adapt the downstream tasks to pre-trained models, has drastically boosted the performance of many natural language downstream tasks. In this work, we extend this notable transfer ability benefited from prompt into vision models as an alternative to fine-tuning. To this end, we propose parameter-efficient Prompt tuning (Pro-tuning) to adapt frozen vision models to various downstream vision tasks. The key to Pro-tuning is prompt-based tuning, i.e., learning task-specific vision prompts for downstream input images with the pre-trained model frozen. By only training a few additional parameters, it can work on diverse CNN-based and Transformer-based architectures. Extensive experiments evidence that Pro-tuning outperforms fine-tuning in a broad range of vision tasks and scenarios, including image classification (generic objects, class imbalance, image corruption, adversarial robustness, and out-of-distribution generalization), and dense prediction tasks such as object detection and semantic segmentation.
In this paper, a unified transformation method in learned image compression(LIC) is proposed from the perspective of modulation. Firstly, the quantization in LIC is considered as a generalized channel with additive uniform noise. Moreover, the LIC is interpreted as a particular communication system according to the consistency in structures and optimization objectives. Thus, the technology of communication systems can be applied to guide the design of modules in LIC. Furthermore, a unified transform method based on signal modulation (TSM) is defined. In the view of TSM, the existing transformation methods are mathematically reduced to a linear modulation. A series of transformation methods, e.g. TPM and TJM, are obtained by extending to nonlinear modulation. The experimental results on various datasets and backbone architectures verify that the effectiveness and robustness of the proposed method. More importantly, it further confirms the feasibility of guiding LIC design from a communication perspective. For example, when backbone architecture is hyperprior combining context model, our method achieves 3.52$\%$ BD-rate reduction over GDN on Kodak dataset without increasing complexity.
Existing deep learning-based full-reference IQA (FR-IQA) models usually predict the image quality in a deterministic way by explicitly comparing the features, gauging how severely distorted an image is by how far the corresponding feature lies from the space of the reference images. Herein, we look at this problem from a different viewpoint and propose to model the quality degradation in perceptual space from a statistical distribution perspective. As such, the quality is measured based upon the Wasserstein distance in the deep feature domain. More specifically, the 1DWasserstein distance at each stage of the pre-trained VGG network is measured, based on which the final quality score is performed. The deep Wasserstein distance (DeepWSD) performed on features from neural networks enjoys better interpretability of the quality contamination caused by various types of distortions and presents an advanced quality prediction capability. Extensive experiments and theoretical analysis show the superiority of the proposed DeepWSD in terms of both quality prediction and optimization.
Recently, large pretrained models (e.g., BERT, StyleGAN, CLIP) have shown great knowledge transfer and generalization capability on various downstream tasks within their domains. Inspired by these efforts, in this paper we propose a unified model for open-domain image editing focusing on color and tone adjustment of open-domain images while keeping their original content and structure. Our model learns a unified editing space that is more semantic, intuitive, and easy to manipulate than the operation space (e.g., contrast, brightness, color curve) used in many existing photo editing softwares. Our model belongs to the image-to-image translation framework which consists of an image encoder and decoder, and is trained on pairs of before- and after-images to produce multimodal outputs. We show that by inverting image pairs into latent codes of the learned editing space, our model can be leveraged for various downstream editing tasks such as language-guided image editing, personalized editing, editing-style clustering, retrieval, etc. We extensively study the unique properties of the editing space in experiments and demonstrate superior performance on the aforementioned tasks.
Reconstructing a 3D shape based on a single sketch image is challenging due to the large domain gap between a sparse, irregular sketch and a regular, dense 3D shape. Existing works try to employ the global feature extracted from sketch to directly predict the 3D coordinates, but they usually suffer from losing fine details that are not faithful to the input sketch. Through analyzing the 3D-to-2D projection process, we notice that the density map that characterizes the distribution of 2D point clouds (i.e., the probability of points projected at each location of the projection plane) can be used as a proxy to facilitate the reconstruction process. To this end, we first translate a sketch via an image translation network to a more informative 2D representation that can be used to generate a density map. Next, a 3D point cloud is reconstructed via a two-stage probabilistic sampling process: first recovering the 2D points (i.e., the x and y coordinates) by sampling the density map; and then predicting the depth (i.e., the z coordinate) by sampling the depth values at the ray determined by each 2D point. Extensive experiments are conducted, and both quantitative and qualitative results show that our proposed approach significantly outperforms other baseline methods.
Convolutional Neural Networks (CNN) have provided new and accurate methods for processing digital images and videos. Yet, training CNNs is extremely demanding in terms of computational resources. Also, for specific applications, the standard use of transfer learning also tends to require far more resources than what may be needed. Furthermore, the final systems tend to operate as black boxes that are difficult to interpret. The current thesis considers the problem of detecting faces from the AOLME video dataset. The AOLME dataset consists of a large video collection of group interactions that are recorded in unconstrained classroom environments. For the thesis, still image frames were extracted at every minute from 18 24-minute videos. Then, each video frame was divided into 9x5 blocks with 50x50 pixels each. For each of the 19440 blocks, the percentage of face pixels was set as ground truth. Face detection was then defined as a regression problem for determining the face pixel percentage for each block. For testing different methods, 12 videos were used for training and validation. The remaining 6 videos were used for testing. The thesis examines the impact of using the instantaneous phase for the AOLME block-based face detection application. For comparison, the thesis compares the use of the Frequency Modulation image based on the instantaneous phase, the use of the instantaneous amplitude, and the original gray scale image. To generate the FM and AM inputs, the thesis uses dominant component analysis that aims to decrease the training overhead while maintaining interpretability.