Search

The fusion of AI and fashion design has emerged as a promising research area. However, the lack of extensive, interrelated data on clothing and try-on stages has hindered the full potential of AI in this domain. Addressing this, we present the Fashion-Diffusion dataset, a product of multiple years' rigorous effort. This dataset, the first of its kind, comprises over a million high-quality fashion images, paired with detailed text descriptions. Sourced from a diverse range of geographical locations and cultural backgrounds, the dataset encapsulates global fashion trends. The images have been meticulously annotated with fine-grained attributes related to clothing and humans, simplifying the fashion design process into a Text-to-Image (T2I) task. The Fashion-Diffusion dataset not only provides high-quality text-image pairs and diverse human-garment pairs but also serves as a large-scale resource about humans, thereby facilitating research in T2I generation. Moreover, to foster standardization in the T2I-based fashion design field, we propose a new benchmark comprising multiple datasets for evaluating the performance of fashion design models. This work represents a significant leap forward in the realm of AI-driven fashion design, setting a new standard for future research in this field.

Despite significant progress in the field, it is still challenging to create personalized visual representations that align closely with the desires and preferences of individual users. This process requires users to articulate their ideas in words that are both comprehensible to the models and accurately capture their vision, posing difficulties for many users. In this paper, we tackle this challenge by leveraging historical user interactions with the system to enhance user prompts. We propose a novel approach that involves rewriting user prompts based on a newly collected large-scale text-to-image dataset with over 300k prompts from 3115 users. Our rewriting model enhances the expressiveness and alignment of user prompts with their intended visual outputs. Experimental results demonstrate the superiority of our methods over baseline approaches, as evidenced in our new offline evaluation method and online tests. Our code and dataset are available at https://github.com/zzjchen/Tailored-Visions., Comment: Accepted at CVPR 2024

With the rapid development of wearable cameras, a massive collection of egocentric video for first-person visual perception becomes available. Using egocentric videos to predict first-person activity faces many challenges, including limited field of view, occlusions, and unstable motions. Observing that sensor data from wearable devices facilitates human activity recognition, multi-modal activity recognition is attracting increasing attention. However, the deficiency of related dataset hinders the development of multi-modal deep learning for egocentric activity recognition. Nowadays, deep learning in real world has led to a focus on continual learning that often suffers from catastrophic forgetting. But the catastrophic forgetting problem for egocentric activity recognition, especially in the context of multiple modalities, remains unexplored due to unavailability of dataset. In order to assist this research, we present a multi-modal egocentric activity dataset for continual learning named UESTC-MMEA-CL, which is collected by self-developed glasses integrating a first-person camera and wearable sensors. It contains synchronized data of videos, accelerometers, and gyroscopes, for 32 types of daily activities, performed by 10 participants. Its class types and scale are compared with other publicly available datasets. The statistical analysis of the sensor data is given to show the auxiliary effects for different behaviors. And results of egocentric activity recognition are reported when using separately, and jointly, three modalities: RGB, acceleration, and gyroscope, on a base network architecture. To explore the catastrophic forgetting in continual learning tasks, four baseline methods are extensively evaluated with different multi-modal combinations. We hope the UESTC-MMEA-CL can promote future studies on continual learning for first-person activity recognition in wearable applications., Comment: IEEE Transactions on Multimedia

Deep discriminative models (DDMs), e.g. deep regression forests and deep decision forests, have been extensively studied recently to solve problems such as facial age estimation, head pose estimation, etc.. Due to a shortage of well-labeled data that does not have noise and imbalanced distribution problems, learning DDMs is always challenging. Existing methods usually tackle these challenges through learning more discriminative features or re-weighting samples. We argue that learning DDMs gradually, from easy to hard, is more reasonable, for two reasons. First, this is more consistent with the cognitive process of human beings. Second, noisy as well as underrepresented examples can be distinguished by virtue of previously learned knowledge. Thus, we resort to a gradual learning strategy -- self-paced learning (SPL). Then, a natural question arises: can SPL lead DDMs to achieve more robust and less biased solutions? To answer this question, this paper proposes a new SPL method: easy and underrepresented examples first, for learning DDMs. This tackles the fundamental ranking and selection problem in SPL from a new perspective: fairness. Our idea is fundamental and can be easily combined with a variety of DDMs. Extensive experimental results on three computer vision tasks, i.e., facial age estimation, head pose estimation, and gaze estimation, show our new method gains considerable performance improvement in both accuracy and fairness. Source code is available at https://github.com/learninginvision/SPU., Comment: The article is submitted to TNNLS, and is under review

The goal of few-shot classification is to classify new categories with few labeled examples within each class. Nowadays, the excellent performance in handling few-shot classification problems is shown by metric-based meta-learning methods. However, it is very hard for previous methods to discriminate the fine-grained sub-categories in the embedding space without fine-grained labels. This may lead to unsatisfactory generalization to fine-grained subcategories, and thus affects model interpretation. To tackle this problem, we introduce the contrastive loss into few-shot classification for learning latent fine-grained structure in the embedding space. Furthermore, to overcome the drawbacks of random image transformation used in current contrastive learning in producing noisy and inaccurate image pairs (i.e., views), we develop a learning-to-learn algorithm to automatically generate different views of the same image. Extensive experiments on standard few-shot learning benchmarks demonstrate the superiority of our method., Comment: 8 pages, 4 figures

Multi-view clustering is an important research topic due to its capability to utilize complementary information from multiple views. However, there are few methods to consider the negative impact caused by certain views with unclear clustering structures, resulting in poor multi-view clustering performance. To address this drawback, we propose self-supervised discriminative feature learning for deep multi-view clustering (SDMVC). Concretely, deep autoencoders are applied to learn embedded features for each view independently. To leverage the multi-view complementary information, we concatenate all views' embedded features to form the global features, which can overcome the negative impact of some views' unclear clustering structures. In a self-supervised manner, pseudo-labels are obtained to build a unified target distribution to perform multi-view discriminative feature learning. During this process, global discriminative information can be mined to supervise all views to learn more discriminative features, which in turn are used to update the target distribution. Besides, this unified target distribution can make SDMVC learn consistent cluster assignments, which accomplishes the clustering consistency of multiple views while preserving their features' diversity. Experiments on various types of multi-view datasets show that SDMVC achieves state-of-the-art performance.

Disentanglement, a critical concern in interpretable machine learning, has also garnered significant attention from the computer vision community. Many existing GAN-based class disentanglement (unsupervised) approaches, such as InfoGAN and its variants, primarily aim to maximize the mutual information (MI) between the generated image and its latent codes. However, this focus may lead to a tendency for the network to generate highly similar images when presented with the same latent class factor, potentially resulting in mode collapse or mode dropping. To alleviate this problem, we propose \texttt{CoDeGAN} (Contrastive Disentanglement for Generative Adversarial Networks), where we relax similarity constraints for disentanglement from the image domain to the feature domain. This modification not only enhances the stability of GAN training but also improves their disentangling capabilities. Moreover, we integrate self-supervised pre-training into CoDeGAN to learn semantic representations, significantly facilitating unsupervised disentanglement. Extensive experimental results demonstrate the superiority of our method over state-of-the-art approaches across multiple benchmarks. The code is available at https://github.com/learninginvision/CoDeGAN.

Deep discriminative models (e.g. deep regression forests, deep neural decision forests) have achieved remarkable success recently to solve problems such as facial age estimation and head pose estimation. Most existing methods pursue robust and unbiased solutions either through learning discriminative features, or reweighting samples. We argue what is more desirable is learning gradually to discriminate like our human beings, and hence we resort to self-paced learning (SPL). Then, a natural question arises: can self-paced regime lead deep discriminative models to achieve more robust and less biased solutions? To this end, this paper proposes a new deep discriminative model--self-paced deep regression forests with consideration on underrepresented examples (SPUDRFs). It tackles the fundamental ranking and selecting problem in SPL from a new perspective: fairness. This paradigm is fundamental and could be easily combined with a variety of deep discriminative models (DDMs). Extensive experiments on two computer vision tasks, i.e., facial age estimation and head pose estimation, demonstrate the efficacy of SPUDRFs, where state-of-the-art performances are achieved., Comment: ECCV 2020

Facial age estimation is an important and challenging problem in computer vision. Existing approaches usually employ deep neural networks (DNNs) to fit the mapping from facial features to age, even though there exist some noisy and confusing samples. We argue that it is more desirable to distinguish noisy and confusing facial images from regular ones, and alleviate the interference arising from them. To this end, we propose self-paced deep regression forests (SP-DRFs) -- a gradual learning DNNs framework for age estimation. As the model is learned gradually, from simplicity to complexity, it tends to emphasize more on reliable samples and avoid bad local minima. Moreover, the proposed capped-likelihood function helps to exclude noisy samples in training, rendering our SP-DRFs significantly more robust. We demonstrate the efficacy of SP-DRFs on Morph II and FG-NET datasets, where our model achieves state-of-the-art performance., Comment: 7 pages, 5 figures, 2 tables

We study the problem of multimodal generative modelling of images based on generative adversarial networks (GANs). Despite the success of existing methods, they often ignore the underlying structure of vision data or its multimodal generation characteristics. To address this problem, we introduce the Dirichlet prior for multimodal image generation, which leads to a new Latent Dirichlet Allocation based GAN (LDAGAN). In detail, for the generative process modelling, LDAGAN defines a generative mode for each sample, determining which generative sub-process it belongs to. For the adversarial training, LDAGAN derives a variational expectation-maximization (VEM) algorithm to estimate model parameters. Experimental results on real-world datasets have demonstrated the outstanding performance of LDAGAN over other existing GANs.