In recent years, deep neural networks have been successful in both industry and academia, especially for computer vision tasks. The great success of deep learning is mainly due to its scalability to encode large-scale data and to maneuver billions of model parameters. However, it is a challenge to deploy these cumbersome deep models on devices with limited resources, e.g., mobile phones and embedded devices, not only because of the high computational complexity but also the large storage requirements. To this end, a variety of model compression and acceleration techniques have been developed. As a representative type of model compression and acceleration, knowledge distillation effectively learns a small student model from a large teacher model. It has received rapid increasing attention from the community. This paper provides a comprehensive survey of knowledge distillation from the perspectives of knowledge categories, training schemes, teacher-student architecture, distillation algorithms, performance comparison and applications. Furthermore, challenges in knowledge distillation are briefly reviewed and comments on future research are discussed and forwarded.

Knowledge Distillation: A Survey

Automatic machine-based Facial Expression Analysis (FEA) has made substantial progress in the past few decades driven by its importance for applications in psychology, security, health, entertainment, and human–computer interaction. The vast majority of completed FEA studies are based on nonoccluded faces collected in a controlled laboratory environment. Automatic expression recognition tolerant to partial occlusion remains less understood, particularly in real-world scenarios. In recent years, efforts investigating techniques to handle partial occlusion for FEA have seen an increase. The context is right for a comprehensive perspective of these developments and the state of the art from this perspective. This survey provides such a comprehensive review of recent advances in dataset creation, algorithm development, and investigations of the effects of occlusion critical for robust performance in FEA systems. It outlines existing challenges in overcoming partial occlusion and discusses possible opportunities in advancing the technology. To the best of our knowledge, it is the first FEA survey dedicated to occlusion and aimed at promoting better-informed and benchmarked future work.

Facial Expression Analysis under Partial Occlusion: A Survey

http://spiral.imperial.ac.uk/bitstream/10044/1/32322/2/300w.pdf

300 Faces In-The-Wild Challenge

Automatic machine-based Facial Expression Analysis (FEA) has made substantial progress in the past few decades driven by its importance for applications in psychology, security, health, entertainment and human computer interaction. The vast majority of completed FEA studies are based on non-occluded faces collected in a controlled laboratory environment. Automatic expression recognition tolerant to partial occlusion remains less understood, particularly in real-world scenarios. In recent years, efforts investigating techniques to handle partial occlusion for FEA have seen an increase. The context is right for a comprehensive perspective of these developments and the state of the art from this perspective. This survey provides such a comprehensive review of recent advances in dataset creation, algorithm development, and investigations of the effects of occlusion critical for robust performance in FEA systems. It outlines existing challenges in overcoming partial occlusion and discusses possible opportunities in advancing the technology. To the best of our knowledge, it is the first FEA survey dedicated to occlusion and aimed at promoting better informed and benchmarked future work.

Recently, neural networks purely based on attention were shown to address image understanding tasks such as image classification. However, these visual transformers are pre-trained with hundreds of millions of images using an expensive infrastructure, thereby limiting their adoption. 
In this work, we produce a competitive convolution-free transformer by training on Imagenet only. We train them on a single computer in less than 3 days. Our reference vision transformer (86M parameters) achieves top-1 accuracy of 83.1% (single-crop evaluation) on ImageNet with no external data. 
More importantly, we introduce a teacher-student strategy specific to transformers. It relies on a distillation token ensuring that the student learns from the teacher through attention. We show the interest of this token-based distillation, especially when using a convnet as a teacher. This leads us to report results competitive with convnets for both Imagenet (where we obtain up to 85.2% accuracy) and when transferring to other tasks. We share our code and models.

Training data-efficient image transformers & distillation through attention

Standard Knowledge Distillation (KD) approaches distill the knowledge of a cumbersome teacher model into the parameters of a student model with a pre-defined architecture. However, the knowledge of a neural network, which is represented by the network's output distribution conditioned on its input, depends not only on its parameters but also on its architecture. Hence, a more generalized approach for KD is to distill the teacher's knowledge into both the parameters and architecture of the student. To achieve this, we present a new \textit{Architecture-aware Knowledge Distillation (AKD)} approach that finds student models (pearls for the teacher) that are best for distilling the given teacher model. In particular, we leverage Neural Architecture Search (NAS), equipped with our KD-guided reward, to search for the best student architectures for a given teacher. Experimental results show our proposed AKD consistently outperforms the conventional NAS plus KD approach, and achieves state-of-the-art results on the ImageNet classification task under various latency settings. Furthermore, the best AKD student architecture for the ImageNet classification task also transfers well to other tasks such as million level face recognition and ensemble learning.

/pdf/search-to-distill-pearls-are-everywhere-but-not-the-eyes-2rqfhgy77l.pdf

Search to Distill: Pearls Are Everywhere but Not the Eyes

Recent text-to-image generation models like DreamBooth have made remarkable progress in generating highly customized images of a target subject, by fine-tuning an ``expert model'' for a given subject from a few examples. However, this process is expensive, since a new expert model must be learned for each subject. In this paper, we present SuTI, a Subject-driven Text-to-Image generator that replaces subject-specific fine tuning with in-context learning. Given a few demonstrations of a new subject, SuTI can instantly generate novel renditions of the subject in different scenes, without any subject-specific optimization. SuTI is powered by apprenticeship learning, where a single apprentice model is learned from data generated by a massive number of subject-specific expert models. Specifically, we mine millions of image clusters from the Internet, each centered around a specific visual subject. We adopt these clusters to train a massive number of expert models, each specializing in a different subject. The apprentice model SuTI then learns to imitate the behavior of these fine-tuned experts. SuTI can generate high-quality and customized subject-specific images 20x faster than optimization-based SoTA methods. On the challenging DreamBench and DreamBench-v2, our human evaluation shows that SuTI significantly outperforms existing models like InstructPix2Pix, Textual Inversion, Imagic, Prompt2Prompt, Re-Imagen and DreamBooth, especially on the subject and text alignment aspects.

pdf/subject-driven-text-to-image-generation-via-apprenticeship-2s252h2s.pdf

Subject-driven Text-to-Image Generation via Apprenticeship Learning

This paper proposes a method for generating images of customized objects specified by users. The method is based on a general framework that bypasses the lengthy optimization required by previous approaches, which often employ a per-object optimization paradigm. Our framework adopts an encoder to capture high-level identifiable semantics of objects, producing an object-specific embedding with only a single feed-forward pass. The acquired object embedding is then passed to a text-to-image synthesis model for subsequent generation. To effectively blend a object-aware embedding space into a well developed text-to-image model under the same generation context, we investigate different network designs and training strategies, and propose a simple yet effective regularized joint training scheme with an object identity preservation loss. Additionally, we propose a caption generation scheme that become a critical piece in fostering object specific embedding faithfully reflected into the generation process, while keeping control and editing abilities. Once trained, the network is able to produce diverse content and styles, conditioned on both texts and objects. We demonstrate through experiments that our proposed method is able to synthesize images with compelling output quality, appearance diversity, and object fidelity, without the need of test-time optimization. Systematic studies are also conducted to analyze our models, providing insights for future work.

Taming Encoder for Zero Fine-tuning Image Customization with Text-to-Image Diffusion Models

The problem of face alignment has been intensively studied in the past years. A large number of novel methods have been proposed and reported very good performance on benchmark dataset such as 300W. However, the differences in the experimental setting and evaluation metric, missing details in the description of the methods make it hard to reproduce the results reported and evaluate the relative merits. For instance, most recent face alignment methods are built on top of face detection but from different face detectors. In this paper, we carry out a rigorous evaluation of these methods by making the following contributions: 1) we proposes a new evaluation metric for face alignment on a set of images, i.e., area under error distribution curve within a threshold, AUC$_\alpha$, given the fact that the traditional evaluation measure (mean error) is very sensitive to big alignment error. 2) we extend the 300W database with more practical face detections to make fair comparison possible. 3) we carry out face alignment sensitivity analysis w.r.t. face detection, on both synthetic and real data, using both off-the-shelf and re-retrained models. 4) we study factors that are particularly important to achieve good performance and provide suggestions for practical applications. Most of the conclusions drawn from our comparative analysis cannot be inferred from the original publications.

An Empirical Study of Recent Face Alignment Methods

Recently, a series of works in computer vision have shown promising results on various image and video understanding tasks using self-attention. However, due to the quadratic computational and memory complexities of self-attention, these works either apply attention only to low-resolution feature maps in later stages of a deep network or restrict the receptive field of attention in each layer to a small local region. To overcome these limitations, this work introduces a new global self-attention module, referred to as the GSA module, which is efficient enough to serve as the backbone component of a deep network. This module consists of two parallel layers: a content attention layer that attends to pixels based only on their content and a positional attention layer that attends to pixels based on their spatial locations. The output of this module is the sum of the outputs of the two layers. Based on the proposed GSA module, we introduce new standalone global attention-based deep networks that use GSA modules instead of convolutions to model pixel interactions. Due to the global extent of the proposed GSA module, a GSA network has the ability to model long-range pixel interactions throughout the network. Our experimental results show that GSA networks outperform the corresponding convolution-based networks significantly on the CIFAR-100 and ImageNet datasets while using less number of parameters and computations. The proposed GSA networks also outperform various existing attention-based networks on the ImageNet dataset.

/pdf/global-self-attention-networks-for-image-recognition-3zyc81pisj.pdf

Global Self-Attention Networks for Image Recognition

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Xuhui Jia

Author Tools

Chat about Author