Despite significant research on lightweight deep neural networks (DNNs) designed for edge devices, the current face detectors do not fully meet the requirements for "intelligent" CMOS image sensors (iCISs) integrated with embedded DNNs. These sensors are essential in various practical applications, such as energy-efficient mobile phones and surveillance systems with always-on capabilities. One noteworthy limitation is the absence of suitable face detectors for the always-on scenario, a crucial aspect of image sensor-level applications. These detectors must operate directly with sensor RAW data before the image signal processor (ISP) takes over. This gap poses a significant challenge in achieving optimal performance in such scenarios. Further research and development are necessary to bridge this gap and fully leverage the potential of iCIS applications. In this study, we aim to bridge the gap by exploring extremely low-bit lightweight face detectors, focusing on the always-on face detection scenario for mobile image sensor applications. To achieve this, our proposed model utilizes sensor-aware synthetic RAW inputs, simulating always-on face detection processed "before" the ISP chain. Our approach employs ternary (-1, 0, 1) weights for potential implementations in image sensors, resulting in a relatively simple network architecture with shallow layers and extremely low-bitwidth. Our method demonstrates reasonable face detection performance and excellent efficiency in simulation studies, offering promising possibilities for practical always-on face detectors in real-world applications.
Diffusion models have recently shown remarkable success in high-quality image generation. Sometimes, however, a pre-trained diffusion model exhibits partial misalignment in the sense that the model can generate good images, but it sometimes outputs undesirable images. If so, we simply need to prevent the generation of the bad images, and we call this task censoring. In this work, we present censored generation with a pre-trained diffusion model using a reward model trained on minimal human feedback. We show that censoring can be accomplished with extreme human feedback efficiency and that labels generated with a mere few minutes of human feedback are sufficient. Code available at: https://github.com/tetrzim/diffusion-human-feedback.
We study the mean estimation problem under communication and local differential privacy constraints. While previous work has proposed \emph{order}-optimal algorithms for the same problem (i.e., asymptotically optimal as we spend more bits), \emph{exact} optimality (in the non-asymptotic setting) still has not been achieved. In this work, we take a step towards characterizing the \emph{exact}-optimal approach in the presence of shared randomness (a random variable shared between the server and the user) and identify several necessary conditions for \emph{exact} optimality. We prove that one of the necessary conditions is to utilize a rotationally symmetric shared random codebook. Based on this, we propose a randomization mechanism where the codebook is a randomly rotated simplex -- satisfying the necessary properties of the \emph{exact}-optimal codebook. The proposed mechanism is based on a $k$-closest encoding which we prove to be \emph{exact}-optimal for the randomly rotated simplex codebook.
The role of mobile cameras increased dramatically over the past few years, leading to more and more research in automatic image quality enhancement and RAW photo processing. In this Mobile AI challenge, the target was to develop an efficient end-to-end AI-based image signal processing (ISP) pipeline replacing the standard mobile ISPs that can run on modern smartphone GPUs using TensorFlow Lite. The participants were provided with a large-scale Fujifilm UltraISP dataset consisting of thousands of paired photos captured with a normal mobile camera sensor and a professional 102MP medium-format FujiFilm GFX100 camera. The runtime of the resulting models was evaluated on the Snapdragon's 8 Gen 1 GPU that provides excellent acceleration results for the majority of common deep learning ops. The proposed solutions are compatible with all recent mobile GPUs, being able to process Full HD photos in less than 20-50 milliseconds while achieving high fidelity results. A detailed description of all models developed in this challenge is provided in this paper.
The deep learning-based ISP models for mobile cameras produce high-quality images comparable to the professional DSLR camera. However, many of them are computationally expensive, which may not be appropriate for mobile environments. Also, the recent mobile cameras adopt non-Bayer CFAs (e.g., Quad Bayer, Nona Bayer, and QxQ Bayer) to improve image quality; however, most deep learning-based ISP models mainly focus on standard Bayer CFA. In this work, we propose PyNET-QxQ based on PyNET, a light-weighted ISP explicitly designed for the QxQ CFA pattern. The number of parameters of PyNET-QxQ is less than 2.5% of PyNET. We also introduce a novel knowledge distillation technique, progressive distillation, to train the compressed network effectively. Finally, experiments with QxQ images (obtained by an actual QxQ camera sensor, under development) demonstrate the outstanding performance of PyNET-QxQ despite significant parameter reductions.
The tremendous recent progress in analyzing the training dynamics of overparameterized neural networks has primarily focused on wide networks and therefore does not sufficiently address the role of depth in deep learning. In this work, we present the first trainability guarantee of infinitely deep but narrow neural networks. We study the infinite-depth limit of a multilayer perceptron (MLP) with a specific initialization and establish a trainability guarantee using the NTK theory. We then extend the analysis to an infinitely deep convolutional neural network (CNN) and perform brief experiments
Unstructured pruning reduces a significant amount of weights of neural networks. However, unstructured pruning provides a sparse network with the same network architecture as the original network. On the other hand, structured pruning provides an efficient network architecture by removing channels, but the parameter reduction is not significant. In this paper, we consider transferring knowledge from unstructured pruning to a network with efficient architecture (with fewer channels). In particular, we apply the knowledge distillation (KD), where the teacher network is a sparse network (obtained from unstructured pruning), and the student network has an efficient architecture. We observe that learning from the pruned teacher is more effective than learning from the unpruned teacher. We further achieve the promising experimental results that unstructured pruning can improve the performance of knowledge distillation in general.
Neural network (NN) compression has become essential to enable deploying over-parameterized NN models on resource-constrained devices. As a simple and easy-to-implement method, pruning is one of the most established NN compression techniques. Although it is a mature method with more than 30 years of history, there is still a lack of good understanding and systematic analysis of why pruning works well even with aggressive compression ratios. In this work, we answer this question by studying NN compression from an information-theoretic approach and show that rate distortion theory suggests pruning to achieve the theoretical limits of NN compression. Our derivation also provides an end-to-end compression pipeline involving a novel pruning strategy. That is, in addition to pruning the model, we also find a minimum-length binary representation of it via entropy coding. Our method consistently outperforms the existing pruning strategies and reduces the pruned model's size by 2.5 times. We evaluate the efficacy of our strategy on MNIST, CIFAR-10 and ImageNet datasets using 5 distinct architectures.
Generative adversarial networks (GAN) are a widely used class of deep generative models, but their minimax training dynamics are not understood very well. In this work, we show that GANs with a 2-layer infinite-width generator and a 2-layer finite-width discriminator trained with stochastic gradient ascent-descent have no spurious stationary points. We then show that when the width of the generator is finite but wide, there are no spurious stationary points within a ball whose radius becomes arbitrarily large (to cover the entire parameter space) as the width goes to infinity.