A Solution to Co-occurrence Bias: Attributes Disentanglement via Mutual Information Minimization for Pedestrian Attribute Recognition
Recent studies on pedestrian attribute recognition progress with either explicit or implicit modeling of the co-occurrence among attributes. Considering that this known a prior is highly variable and unforeseeable regarding the specific scenarios, we show that current methods can actually suffer in generalizing such fitted attributes interdependencies onto scenes or identities off the dataset distribution, resulting in the underlined bias of attributes co-occurrence. To render models robust in realistic scenes, we propose the attributes-disentangled feature learning to ensure the recognition of an attribute not inferring on the existence of others, and which is sequentially formulated as a problem of mutual information minimization. Rooting from it, practical strategies are devised to efficiently decouple attributes, which substantially improve the baseline and establish state-of-the-art performance on realistic datasets like PETAzs and RAPzs. Code is released on https://github.com/SDret/A-Solution-to-Co-occurence-Bias-in-Pedestrian-Attribute-Recognition.
Code (2)
Tasks
AttributeDisentanglementPedestrian Attribute RecognitionSimilar Papers 제목 키워드 기반
Unsupervised Discovery, Control, and Disentanglement of Semantic Attributes with Applications to Anomaly Detection
Our work focuses on unsupervised and generative methods that address the following goals: (a) learning unsupervised generative representations that discover latent factors controlling image semantic attributes, (b) study…
Anomaly DetectionAttributeDisentanglementImage Generation+3Evaluation of Latent Space Disentanglement in the Presence of Interdependent Attributes
Controllable music generation with deep generative models has become increasingly reliant on disentanglement learning techniques. However, current disentanglement metrics, such as mutual information gap (MIG), are often …
DisentanglementMusic GenerationDisentangled Representation Learning via Modular Compositional Bias
Recent disentangled representation learning (DRL) methods heavily rely on factor specific strategies-either learning objectives for attributes or model architectures for objects-to embed inductive biases. Such divergent …
Representation LearningDiscover the Unknown Biased Attribute of an Image Classifier
Recent works find that AI algorithms learn biases from data. Therefore, it is urgent and vital to identify biases in AI algorithms. However, the previous bias identification pipeline overly relies on human experts to con…
AttributeDisentanglementCAD-VAE: Leveraging Correlation-Aware Latents for Comprehensive Fair Disentanglement
While deep generative models have significantly advanced representation learning, they may inherit or amplify biases and fairness issues by encoding sensitive attributes alongside predictive features. Enforcing strict in…
DisentanglementFairnessRepresentation Learning