Multi-view Adversarial Discriminator: Mine the Non-causal Factors for Object Detection in Unseen Domains

• URL: http://arxiv.org/abs/2304.02950v1
• Date: Thu, 6 Apr 2023 09:20:28 GMT
• Title: Multi-view Adversarial Discriminator: Mine the Non-causal Factors for Object Detection in Unseen Domains
• Authors: Mingjun Xu, Lingyun Qin, Weijie Chen, Shiliang Pu, Lei Zhang
• Abstract summary: We present an idea to remove non-causal factors from common features by multi-view adversarial training on source domains. We propose a Multi-view Adversarial Discriminator (MAD) based domain generalization model. Our MAD obtains state-of-the-art performance on six benchmarks.
• Score: 36.4342793435982
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Domain shift degrades the performance of object detection models in practical applications. To alleviate the influence of domain shift, plenty of previous work try to decouple and learn the domain-invariant (common) features from source domains via domain adversarial learning (DAL). However, inspired by causal mechanisms, we find that previous methods ignore the implicit insignificant non-causal factors hidden in the common features. This is mainly due to the single-view nature of DAL. In this work, we present an idea to remove non-causal factors from common features by multi-view adversarial training on source domains, because we observe that such insignificant non-causal factors may still be significant in other latent spaces (views) due to the multi-mode structure of data. To summarize, we propose a Multi-view Adversarial Discriminator (MAD) based domain generalization model, consisting of a Spurious Correlations Generator (SCG) that increases the diversity of source domain by random augmentation and a Multi-View Domain Classifier (MVDC) that maps features to multiple latent spaces, such that the non-causal factors are removed and the domain-invariant features are purified. Extensive experiments on six benchmarks show our MAD obtains state-of-the-art performance.

Related papers

• Causal Prototype-inspired Contrast Adaptation for Unsupervised Domain Adaptive Semantic Segmentation of High-resolution Remote Sensing Imagery [8.3316355693186]
  We propose a prototype-inspired contrast adaptation (CPCA) method to explore the invariant causal mechanisms between different HRSIs domains and their semantic labels. It disentangles causal features and bias features from the source and target domain images through a causal feature disentanglement module. To further de-correlate causal and bias features, a causal intervention module is introduced to intervene on the bias features to generate counterfactual unbiased samples.
  arXiv  Detail & Related papers  (2024-03-06T13:39:18Z)
• DIGIC: Domain Generalizable Imitation Learning by Causal Discovery [69.13526582209165]
  Causality has been combined with machine learning to produce robust representations for domain generalization. We make a different attempt by leveraging the demonstration data distribution to discover causal features for a domain generalizable policy. We design a novel framework, called DIGIC, to identify the causal features by finding the direct cause of the expert action from the demonstration data distribution.
  arXiv  Detail & Related papers  (2024-02-29T07:09:01Z)
• Domain Generalization via Causal Adjustment for Cross-Domain Sentiment Analysis [59.73582306457387]
  We focus on the problem of domain generalization for cross-domain sentiment analysis. We propose a backdoor adjustment-based causal model to disentangle the domain-specific and domain-invariant representations. A series of experiments show the great performance and robustness of our model.
  arXiv  Detail & Related papers  (2024-02-22T13:26:56Z)
• Multi-Domain Causal Representation Learning via Weak Distributional Invariances [27.72497122405241]
  Causal representation learning has emerged as the center of action in causal machine learning research. We show that autoencoders that incorporate such invariances can provably identify the stable set of latents from the rest across different settings.
  arXiv  Detail & Related papers  (2023-10-04T14:41:41Z)
• Rethinking Domain Generalization for Face Anti-spoofing: Separability and Alignment [35.67771212285966]
  This work studies the generalization issue of face anti-spoofing (FAS) models on domain gaps, such as image resolution, blurriness and sensor variations. We formulate this FAS strategy of separability and alignment (SA-FAS) as a problem of invariant risk minimization (IRM) We demonstrate the effectiveness of SA-FAS on challenging cross-domain FAS datasets and establish state-of-the-art performance.
  arXiv  Detail & Related papers  (2023-03-23T20:34:27Z)
• Robust Domain Adaptive Object Detection with Unified Multi-Granularity Alignment [59.831917206058435]
  Domain adaptive detection aims to improve the generalization of detectors on target domain. Recent approaches achieve domain adaption through feature alignment in different granularities via adversarial learning. We introduce a unified multi-granularity alignment (MGA)-based detection framework for domain-invariant feature learning.
  arXiv  Detail & Related papers  (2023-01-01T08:38:07Z)
• Contrastive ACE: Domain Generalization Through Alignment of Causal Mechanisms [34.99779761100095]
  Domain generalization aims to learn knowledge invariant across different distributions. We consider the causal invariance of the average causal effect of the features to the labels.
  arXiv  Detail & Related papers  (2021-06-02T04:01:22Z)
• Learning Domain Invariant Representations for Generalizable Person Re-Identification [71.35292121563491]
  Generalizable person Re-Identification (ReID) has attracted growing attention in recent computer vision community. We introduce causality into person ReID and propose a novel generalizable framework, named Domain Invariant Representations for generalizable person Re-Identification (DIR-ReID)
  arXiv  Detail & Related papers  (2021-03-29T18:59:48Z)
• Heuristic Domain Adaptation [105.59792285047536]
  Heuristic Domain Adaptation Network (HDAN) explicitly learns the domain-invariant and domain-specific representations. Heuristic Domain Adaptation Network (HDAN) has exceeded state-of-the-art on unsupervised DA, multi-source DA and semi-supervised DA.
  arXiv  Detail & Related papers  (2020-11-30T04:21:35Z)
• Adaptively-Accumulated Knowledge Transfer for Partial Domain Adaptation [66.74638960925854]
  Partial domain adaptation (PDA) deals with a realistic and challenging problem when the source domain label space substitutes the target domain. We propose an Adaptively-Accumulated Knowledge Transfer framework (A$2$KT) to align the relevant categories across two domains.
  arXiv  Detail & Related papers  (2020-08-27T00:53:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.