The out-of-distribution (OOD) problem generally arises when neural networks encounter data that significantly deviates from the training data distribution, \ie, in-distribution (InD). In this paper, we study the OOD problem from a neuron activation view. We first formulate neuron activation states by considering both the neuron output and its influence on model decisions. Then, we propose the concept of \textit{neuron activation coverage} (NAC), which characterizes the neuron behaviors under InD and OOD data. Leveraging our NAC, we show that 1) InD and OOD inputs can be naturally separated based on the neuron behavior, which significantly eases the OOD detection problem and achieves a record-breaking performance of 0.03% FPR95 on ResNet-50, outperforming the previous best method by 20.67%; 2) a positive correlation between NAC and model generalization ability consistently holds across architectures and datasets, which enables a NAC-based criterion for evaluating model robustness. By comparison with the traditional validation criterion, we show that NAC-based criterion not only can select more robust models, but also has a stronger correlation with OOD test performance.
Recent years have witnessed an exponential increase in the demand for face video compression, and the success of artificial intelligence has expanded the boundaries beyond traditional hybrid video coding. Generative coding approaches have been identified as promising alternatives with reasonable perceptual rate-distortion trade-offs, leveraging the statistical priors of face videos. However, the great diversity of distortion types in spatial and temporal domains, ranging from the traditional hybrid coding frameworks to generative models, present grand challenges in compressed face video quality assessment (VQA). In this paper, we introduce the large-scale Compressed Face Video Quality Assessment (CFVQA) database, which is the first attempt to systematically understand the perceptual quality and diversified compression distortions in face videos. The database contains 3,240 compressed face video clips in multiple compression levels, which are derived from 135 source videos with diversified content using six representative video codecs, including two traditional methods based on hybrid coding frameworks, two end-to-end methods, and two generative methods. In addition, a FAce VideO IntegeRity (FAVOR) index for face video compression was developed to measure the perceptual quality, considering the distinct content characteristics and temporal priors of the face videos. Experimental results exhibit its superior performance on the proposed CFVQA dataset. The benchmark is now made publicly available at: https://github.com/Yixuan423/Compressed-Face-Videos-Quality-Assessment.
The emergence of digital avatars has raised an exponential increase in the demand for human point clouds with realistic and intricate details. The compression of such data becomes challenging with overwhelming data amounts comprising millions of points. Herein, we leverage the human geometric prior in geometry redundancy removal of point clouds, greatly promoting the compression performance. More specifically, the prior provides topological constraints as geometry initialization, allowing adaptive adjustments with a compact parameter set that could be represented with only a few bits. Therefore, we can envisage high-resolution human point clouds as a combination of geometric priors and structural deviations. The priors could first be derived with an aligned point cloud, and subsequently the difference of features is compressed into a compact latent code. The proposed framework can operate in a play-and-plug fashion with existing learning based point cloud compression methods. Extensive experimental results show that our approach significantly improves the compression performance without deteriorating the quality, demonstrating its promise in a variety of applications.
By integrating certain optimization solvers with deep neural networks, deep unfolding network (DUN) with good interpretability and high performance has attracted growing attention in compressive sensing (CS). However, existing DUNs often improve the visual quality at the price of a large number of parameters and have the problem of feature information loss during iteration. In this paper, we propose an Optimization-inspired Cross-attention Transformer (OCT) module as an iterative process, leading to a lightweight OCT-based Unfolding Framework (OCTUF) for image CS. Specifically, we design a novel Dual Cross Attention (Dual-CA) sub-module, which consists of an Inertia-Supplied Cross Attention (ISCA) block and a Projection-Guided Cross Attention (PGCA) block. ISCA block introduces multi-channel inertia forces and increases the memory effect by a cross attention mechanism between adjacent iterations. And, PGCA block achieves an enhanced information interaction, which introduces the inertia force into the gradient descent step through a cross attention block. Extensive CS experiments manifest that our OCTUF achieves superior performance compared to state-of-the-art methods while training lower complexity. Codes are available at https://github.com/songjiechong/OCTUF.
ML-powered code generation aims to assist developers to write code in a more productive manner, by intelligently generating code blocks based on natural language prompts. Recently, large pretrained deep learning models have substantially pushed the boundary of code generation and achieved impressive performance. Despite their great power, the huge number of model parameters poses a significant threat to adapting them in a regular software development environment, where a developer might use a standard laptop or mid-size server to develop her code. Such large models incur significant resource usage (in terms of memory, latency, and dollars) as well as carbon footprint. Model compression is a promising approach to address these challenges. Several techniques are proposed to compress large pretrained models typically used for vision or textual data. Out of many available compression techniques, we identified that quantization is mostly applicable for code generation task as it does not require significant retraining cost. As quantization represents model parameters with lower-bit integer (e.g., int8), the model size and runtime latency would both benefit from such int representation. We extensively study the impact of quantized model on code generation tasks across different dimension: (i) resource usage and carbon footprint, (ii) accuracy, and (iii) robustness. To this end, through systematic experiments we find a recipe of quantization technique that could run even a $6$B model in a regular laptop without significant accuracy or robustness degradation. We further found the recipe is readily applicable to code summarization task as well.
Nowadays, forgery faces pose pressing security concerns over fake news, fraud, impersonation, etc. Despite the demonstrated success in intra-domain face forgery detection, existing detection methods lack generalization capability and tend to suffer from dramatic performance drops when deployed to unforeseen domains. To mitigate this issue, this paper designs a more general fake face detection model based on the vision transformer(ViT) architecture. In the training phase, the pretrained ViT weights are freezed, and only the Low-Rank Adaptation(LoRA) modules are updated. Additionally, the Single Center Loss(SCL) is applied to supervise the training process, further improving the generalization capability of the model. The proposed method achieves state-of-the-arts detection performances in both cross-manipulation and cross-dataset evaluations.
Mapping images to deep feature space for comparisons has been wildly adopted in recent learning-based full-reference image quality assessment (FR-IQA) models. Analogous to the classical classification task, the ideal mapping space for quality regression should possess both inter-class separability and intra-class compactness. The inter-class separability that focuses on the discrimination of images with different quality levels has been highly emphasized in existing models. However, the intra-class compactness that maintains small objective quality variance of images with the same or indistinguishable quality escapes the research attention, potentially leading to the perception-biased measures. In this paper, we reveal that such bias is mainly caused by the unsuitable subspace that the features are projected and compared in. To account for this, we develop the Debiased Mapping based quality Measure (DMM), which relies on the orthonormal bases of deep learning features formed by singular value decomposition (SVD). The SVD in deep learning feature domain, which overwhelmingly separates the quality variations with singular values and projection bases, facilitates the quality inference with dedicatedly designed distance measure. Experiments on different IQA databases demonstrate the mapping method is able to mitigate the perception bias efficiently, and the superior performance on quality prediction verifies the effectiveness of our method. The implementation will be publicly available.
In this paper, we propose a novel framework for Interactive Face Video Coding (IFVC), which allows humans to interact with the intrinsic visual representations instead of the signals. The proposed solution enjoys several distinct advantages, including ultra-compact representation, low delay interaction, and vivid expression and headpose animation. In particular, we propose the Internal Dimension Increase (IDI) based representation, greatly enhancing the fidelity and flexibility in rendering the appearance while maintaining reasonable representation cost. By leveraging strong statistical regularities, the visual signals can be effectively projected into controllable semantics in the three dimensional space (e.g., mouth motion, eye blinking, head rotation and head translation), which are compressed and transmitted. The editable bitstream, which naturally supports the interactivity at the semantic level, can synthesize the face frames via the strong inference ability of the deep generative model. Experimental results have demonstrated the performance superiority and application prospects of our proposed IFVC scheme. In particular, the proposed scheme not only outperforms the state-of-the-art video coding standard Versatile Video Coding (VVC) and the latest generative compression schemes in terms of rate-distortion performance for face videos, but also enables the interactive coding without introducing additional manipulation processes. Furthermore, the proposed framework is expected to shed lights on the future design of the digital human communication in the metaverse.
Real-time intelligence applications in Internet of Things (IoT) environment depend on timely data communication. However, it is challenging to transmit and analyse massive data of various modalities. Recently proposed task-oriented communication methods based on deep learning have showed its superiority in communication efficiency. In this paper, we propose a cooperative task-oriented communication method for the transmission of multi-modal data from multiple end devices to a central server. In particular, we use the transmission result of data of one modality, which is with lower rate, to control the transmission of other modalities with higher rate in order to reduce the amount of transmitted date. We take the human activity recognition (HAR) task in a smart home environment and design the semantic-oriented transceivers for the transmission of monitoring videos of different rooms and acceleration data of the monitored human. The numerical results demonstrate that by using the transmission control based on the obtained results of the received acceleration data, the transmission is reduced to 2% of that without transmission control while preserving the performance on the HAR task.