Hui Li

Hui Li, Mingjie Sun, Jimin Xiao et al.

Referring Expression Segmentation (RES), which is aimed at localizing and segmenting the target according to the given language expression, has drawn increasing attention. Existing methods jointly consider the localization and segmentation steps, which rely on the fused visual and linguistic features for both steps. We argue that the conflict between the purpose of identifying an object and generating a mask limits the RES performance. To solve this problem, we propose a parallel position-kernel-segmentation pipeline to better isolate and then interact the localization and segmentation steps. In our pipeline, linguistic information will not directly contaminate the visual feature for segmentation. Specifically, the localization step localizes the target object in the image based on the referring expression, and then the visual kernel obtained from the localization step guides the segmentation step. This pipeline also enables us to train RES in a weakly-supervised way, where the pixel-level segmentation labels are replaced by click annotations on center and corner points. The position head is fully-supervised and trained with the click annotations as supervision, and the segmentation head is trained with weakly-supervised segmentation losses. To validate our framework on a weakly-supervised setting, we annotated three RES benchmark datasets (RefCOCO, RefCOCO+ and RefCOCOg) with click annotations.Our method is simple but surprisingly effective, outperforming all previous state-of-the-art RES methods on fully- and weakly-supervised settings by a large margin. The benchmark code and datasets will be released.

Hui Li, Zidong Guo, Seon-Min Rhee et al.

Accurate facial landmarks are essential prerequisites for many tasks related to human faces. In this paper, an accurate facial landmark detector is proposed based on cascaded transformers. We formulate facial landmark detection as a coordinate regression task such that the model can be trained end-to-end. With self-attention in transformers, our model can inherently exploit the structured relationships between landmarks, which would benefit landmark detection under challenging conditions such as large pose and occlusion. During cascaded refinement, our model is able to extract the most relevant image features around the target landmark for coordinate prediction, based on deformable attention mechanism, thus bringing more accurate alignment. In addition, we propose a novel decoder that refines image features and landmark positions simultaneously. With few parameter increasing, the detection performance improves further. Our model achieves new state-of-the-art performance on several standard facial landmark detection benchmarks, and shows good generalization ability in cross-dataset evaluation.

Caiyuan Zheng, Hui Li, Seon-Min Rhee et al.

Scene text recognition (STR) attracts much attention over the years because of its wide application. Most methods train STR model in a fully supervised manner which requires large amounts of labeled data. Although synthetic data contributes a lot to STR, it suffers from the real-tosynthetic domain gap that restricts model performance. In this work, we aim to boost STR models by leveraging both synthetic data and the numerous real unlabeled images, exempting human annotation cost thoroughly. A robust consistency regularization based semi-supervised framework is proposed for STR, which can effectively solve the instability issue due to domain inconsistency between synthetic and real images. A character-level consistency regularization is designed to mitigate the misalignment between characters in sequence recognition. Extensive experiments on standard text recognition benchmarks demonstrate the effectiveness of the proposed method. It can steadily improve existing STR models, and boost an STR model to achieve new state-of-the-art results. To our best knowledge, this is the first consistency regularization based framework that applies successfully to STR.

Hui Li, Xuyang Yao, Wuyuan Xie et al.

Deep high dynamic range (HDR) imaging as an image translation issue has achieved great performance without explicit optical flow alignment. However, challenges remain over content association ambiguities especially caused by saturation and large-scale movements. To address the ghosting issue and enhance the details in saturated regions, we propose a scale-aware two-stage high dynamic range imaging framework (STHDR) to generate high-quality ghost-free HDR image. The scale-aware technique and two-stage fusion strategy can progressively and effectively improve the HDR composition performance. Specifically, our framework consists of feature alignment and two-stage fusion. In feature alignment, we propose a spatial correct module (SCM) to better exploit useful information among non-aligned features to avoid ghosting and saturation. In the first stage of feature fusion, we obtain a preliminary fusion result with little ghosting. In the second stage, we conflate the results of the first stage with aligned features to further reduce residual artifacts and thus improve the overall quality. Extensive experimental results on the typical test dataset validate the effectiveness of the proposed STHDR in terms of speed and quality.

Hui Li, Pengfei Yang, Juanyang Chen et al.

Knowledge distillation as an efficient knowledge transfer technique, has achieved remarkable success in unimodal scenarios. However, in cross-modal settings, conventional distillation methods encounter significant challenges due to data and statistical heterogeneities, failing to leverage the complementary prior knowledge embedded in cross-modal teacher models. This paper empirically reveals two critical issues in existing approaches: distillation path selection and knowledge drift. To address these limitations, we propose MST-Distill, a novel cross-modal knowledge distillation framework featuring a mixture of specialized teachers. Our approach employs a diverse ensemble of teacher models across both cross-modal and multimodal configurations, integrated with an instance-level routing network that facilitates adaptive and dynamic distillation. This architecture effectively transcends the constraints of traditional methods that rely on monotonous and static teacher models. Additionally, we introduce a plug-in masking module, independently trained to suppress modality-specific discrepancies and reconstruct teacher representations, thereby mitigating knowledge drift and enhancing transfer effectiveness. Extensive experiments across five diverse multimodal datasets, spanning visual, audio, and text, demonstrate that our method significantly outperforms existing state-of-the-art knowledge distillation methods in cross-modal distillation tasks. The source code is available at https://github.com/Gray-OREO/MST-Distill.

Wenliang Qian, Yang Xu, Wangmeng Zuo et al.

Generative Adversarial Networks (GANs) are an unsupervised generative model that learns data distribution through adversarial training. However, recent experiments indicated that GANs are difficult to train due to the requirement of optimization in the high dimensional parameter space and the zero gradient problem. In this work, we propose a Self Sparse Generative Adversarial Network (Self-Sparse GAN) that reduces the parameter space and alleviates the zero gradient problem. In the Self-Sparse GAN, we design a Self-Adaptive Sparse Transform Module (SASTM) comprising the sparsity decomposition and feature-map recombination, which can be applied on multi-channel feature maps to obtain sparse feature maps. The key idea of Self-Sparse GAN is to add the SASTM following every deconvolution layer in the generator, which can adaptively reduce the parameter space by utilizing the sparsity in multi-channel feature maps. We theoretically prove that the SASTM can not only reduce the search space of the convolution kernel weight of the generator but also alleviate the zero gradient problem by maintaining meaningful features in the Batch Normalization layer and driving the weight of deconvolution layers away from being negative. The experimental results show that our method achieves the best FID scores for image generation compared with WGAN-GP on MNIST, Fashion-MNIST, CIFAR-10, STL-10, mini-ImageNet, CELEBA-HQ, and LSUN bedrooms, and the relative decrease of FID is 4.76% ~ 21.84%.