Visual artifacts remain a persistent challenge in diffusion models, even with training on massive datasets. Current solutions primarily rely on supervised detectors, yet lack understanding of why these artifacts occur in the first place. In our analysis, we identify three distinct phases in the diffusion generative process: Profiling, Mutation, and Refinement. Artifacts typically emerge during the Mutation phase, where certain regions exhibit anomalous score dynamics over time, causing abrupt disruptions in the normal evolution pattern. This temporal nature explains why existing methods focusing only on spatial uncertainty of the final output fail at effective artifact localization. Based on these insights, we propose ASCED (Abnormal Score Correction for Enhancing Diffusion), that detects artifacts by monitoring abnormal score dynamics during the diffusion process, with a trajectory-aware on-the-fly mitigation strategy that appropriate generation of noise in the detected areas. Unlike most existing methods that apply post hoc corrections, e.g., by applying a noising-denoising scheme after generation, our mitigation strategy operates seamlessly within the existing diffusion process. Extensive experiments demonstrate that our proposed approach effectively reduces artifacts across diverse domains, matching or surpassing existing supervised methods without additional training. Project page: YuCao16.github.io/ASCED.

Recent advances in generative models have sparked research on improving model fairness with AI-generated data. However, existing methods often face limitations in the diversity and quality of synthetic data, leading to compromised fairness and overall model accuracy. Moreover, many approaches rely on the availability of demographic group labels, which are often costly to annotate. This paper proposes AIM-Fair, aiming to overcome these limitations and harness the potential of cutting-edge generative models in promoting algorithmic fairness. We investigate a fine-tuning paradigm starting from a biased model initially trained on real-world data without demographic annotations. This model is then fine-tuned using unbiased synthetic data generated by a state-of-the-art diffusion model to improve its fairness. Two key challenges are identified in this fine-tuning paradigm, 1) the low quality of synthetic data, which can still happen even with advanced generative models, and 2) the domain and bias gap between real and synthetic data. To address the limitation of synthetic data quality, we propose Contextual Synthetic Data Generation (CSDG) to generate data using a text-to-image diffusion model (T2I) with prompts generated by a context-aware LLM, ensuring both data diversity and control of bias in synthetic data. To resolve domain and bias shifts, we introduce a novel selective fine-tuning scheme in which only model parameters more sensitive to bias and less sensitive to domain shift are updated. Experiments on CelebA and UTKFace datasets show that our AIM-Fair improves model fairness while maintaining utility, outperforming both fully and partially fine-tuned approaches to model fairness. The code is available at https://github.com/zengqunzhao/AIM-Fair.

Current facial expression recognition (FER) models are often designed in a supervised learning manner and thus are constrained by the lack of large-scale facial expression images with high-quality annotations. Consequently, these models often fail to generalize well, performing poorly on unseen images in inference. Vision-language-based zero-shot models demonstrate a promising potential for addressing such challenges. However, these models lack task-specific knowledge and therefore are not optimized for the nuances of recognizing facial expressions. To bridge this gap, this work proposes a novel method, Exp-CLIP, to enhance zero-shot FER by transferring the task knowledge from large language models (LLMs). Specifically, based on the pre-trained vision-language encoders, we incorporate a projection head designed to map the initial joint vision-language space into a space that captures representations of facial actions. To train this projection head for subsequent zero-shot predictions, we propose to align the projected visual representations with task-specific semantic meanings derived from the LLM encoder, and the text instruction-based strategy is employed to customize the LLM knowledge. Given unlabelled facial data and efficient training of the projection head, Exp-CLIP achieves superior zero-shot results to the CLIP models and several other large vision-language models (LVLMs) on seven in-the-wild FER datasets. The code is available at https://github.com/zengqunzhao/Exp-CLIP.

This paper presents an efficiently robust facial expression recognition (FER) network, named EfficientFace, which holds much fewer parameters but more robust to the FER in the wild. Firstly, to improve the robustness of the lightweight network, a local-feature extractor and a channel-spatial modulator are designed, in which the depthwise convolution is employed. As a result, the network is aware of local and global-salient facial features. Then, considering the fact that most emotions occur as combinations, mixtures, or compounds of the basic emotions, we introduce a simple but efficient label distribution learning (LDL) method as a novel training strategy. Experiments conducted on realistic occlusion and pose variation datasets demonstrate that the proposed EfficientFace is robust under occlusion and pose variation conditions. Moreover, the proposed method achieves state-of-the-art results on RAF-DB, CAER-S, and AffectNet-7 datasets with accuracies of 88.36%, 85.87%, and 63.70%, respectively, and a comparable result on the AffectNet-8 dataset with an accuracy of 59.89%. The code is public available at https://github.com/zengqunzhao/EfficientFace.

This paper proposes a dynamic facial expression recognition transformer (Former-DFER) for the in-the-wild scenario. Specifically, the proposed Former-DFER mainly consists of a convolutional spatial transformer (CS-Former) and a temporal transformer (T-Former). The CS-Former consists of five convolution blocks and N spatial encoders, which is designed to guide the network to learn occlusion and pose-robust facial features from the spatial perspective. And the temporal transformer consists of M temporal encoders, which is designed to allow the network to learn contextual facial features from the temporal perspective. The heatmaps of the leaned facial features demonstrate that the proposed Former-DFER is capable of handling the issues such as occlusion, non-frontal pose, and head motion. And the visualization of the feature distribution shows that the proposed method can learn more discriminative facial features. Moreover, our Former-DFER also achieves state-of-the-art results on the DFEW and AFEW benchmarks.

Facial expression recognition (FER) in the wild received broad concerns in which occlusion and pose variation are two key issues. This paper proposed a global multi-scale and local attention network (MA-Net) for FER in the wild. Specifically, the proposed network consists of three main components: a feature pre-extractor, a multi-scale module, and a local attention module. The feature pre-extractor is utilized to pre-extract middle-level features, the multi-scale module to fuse features with different receptive fields, which reduces the susceptibility of deeper convolution towards occlusion and variant pose, while the local attention module can guide the network to focus on local salient features, which releases the interference of occlusion and non-frontal pose problems on FER in the wild. Extensive experiments demonstrate that the proposed MA-Net achieves the state-of-the-art results on several in-the-wild FER benchmarks: CAER-S, AffectNet-7, AffectNet-8, RAFDB, and SFEW with accuracies of 88.42%, 64.53%, 60.29%, 88.40%, and 59.40% respectively. The codes and training logs are publicly available at https://github.com/zengqunzhao/MA-Net.