Object-Aware Domain Generalization for Object Detection

• URL: http://arxiv.org/abs/2312.12133v1
• Date: Tue, 19 Dec 2023 13:11:35 GMT
• Title: Object-Aware Domain Generalization for Object Detection
• Authors: Wooju Lee, Dasol Hong, Hyungtae Lim, and Hyun Myung
• Abstract summary: We propose an object-aware domain generalization (OA-DG) method for single-domain generalization in object detection. Our method consists of data augmentation and training strategy, which are called OA-Mix and OA-Loss, respectively. Our proposed method outperforms state-of-the-art works on standard benchmarks.
• Score: 10.28961895672321
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Single-domain generalization (S-DG) aims to generalize a model to unseen environments with a single-source domain. However, most S-DG approaches have been conducted in the field of classification. When these approaches are applied to object detection, the semantic features of some objects can be damaged, which can lead to imprecise object localization and misclassification. To address these problems, we propose an object-aware domain generalization (OA-DG) method for single-domain generalization in object detection. Our method consists of data augmentation and training strategy, which are called OA-Mix and OA-Loss, respectively. OA-Mix generates multi-domain data with multi-level transformation and object-aware mixing strategy. OA-Loss enables models to learn domain-invariant representations for objects and backgrounds from the original and OA-Mixed images. Our proposed method outperforms state-of-the-art works on standard benchmarks. Our code is available at https://github.com/WoojuLee24/OA-DG.

Related papers

• Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts [56.57141696245328]
  In open-world scenarios, where both novel classes and domains may exist, an ideal segmentation model should detect anomaly classes for safety. Existing methods often struggle to distinguish between domain-level and semantic-level distribution shifts.
  arXiv  Detail & Related papers  (2024-11-06T11:03:02Z)
• Attention-based Class-Conditioned Alignment for Multi-Source Domain Adaptation of Object Detectors [11.616494893839757]
  Domain adaptation methods for object detection (OD) strive to mitigate the impact of distribution shifts by promoting feature alignment across source and target domains. Most state-of-the-art MSDA methods for OD perform feature alignment in a class-agnostic manner. We propose an attention-based class-conditioned alignment method for MSDA that aligns instances of each object category across domains.
  arXiv  Detail & Related papers  (2024-03-14T23:31:41Z)
• CLIP the Gap: A Single Domain Generalization Approach for Object Detection [60.20931827772482]
  Single Domain Generalization tackles the problem of training a model on a single source domain so that it generalizes to any unseen target domain. We propose to leverage a pre-trained vision-language model to introduce semantic domain concepts via textual prompts. We achieve this via a semantic augmentation strategy acting on the features extracted by the detector backbone, as well as a text-based classification loss.
  arXiv  Detail & Related papers  (2023-01-13T12:01:18Z)
• Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection [79.89082006155135]
  Unsupervised Domain Adaptation (UDA) is an effective approach to tackle the issue of domain shift. UDA methods try to align the source and target representations to improve the generalization on the target domain. The Source-Free Adaptation Domain (SFDA) setting aims to alleviate these concerns by adapting a source-trained model for the target domain without requiring access to the source data.
  arXiv  Detail & Related papers  (2022-03-29T17:50:43Z)
• Compound Domain Generalization via Meta-Knowledge Encoding [55.22920476224671]
  We introduce Style-induced Domain-specific Normalization (SDNorm) to re-normalize the multi-modal underlying distributions. We harness the prototype representations, the centroids of classes, to perform relational modeling in the embedding space. Experiments on four standard Domain Generalization benchmarks reveal that COMEN exceeds the state-of-the-art performance without the need of domain supervision.
  arXiv  Detail & Related papers  (2022-03-24T11:54:59Z)
• Domain Generalisation for Object Detection under Covariate and Concept Shift [10.32461766065764]
  Domain generalisation aims to promote the learning of domain-invariant features while suppressing domain-specific features. An approach to domain generalisation for object detection is proposed, the first such approach applicable to any object detection architecture.
  arXiv  Detail & Related papers  (2022-03-10T11:14:18Z)
• Weakly Supervised Object Localization as Domain Adaption [19.854125742336688]
  Weakly supervised object localization (WSOL) focuses on localizing objects only with the supervision of image-level classification masks. Most previous WSOL methods follow the classification activation map (CAM) that localizes objects based on the classification structure with the multi-instance learning (MIL) mechanism. This work provides a novel perspective that models WSOL as a domain adaption (DA) task, where the score estimator trained on the source/image domain is tested on the target/pixel domain to locate objects.
  arXiv  Detail & Related papers  (2022-03-03T13:50:22Z)
• META: Mimicking Embedding via oThers' Aggregation for Generalizable Person Re-identification [68.39849081353704]
  Domain generalizable (DG) person re-identification (ReID) aims to test across unseen domains without access to the target domain data at training time. This paper presents a new approach called Mimicking Embedding via oThers' Aggregation (META) for DG ReID.
  arXiv  Detail & Related papers  (2021-12-16T08:06:50Z)
• Inferring Latent Domains for Unsupervised Deep Domain Adaptation [54.963823285456925]
  Unsupervised Domain Adaptation (UDA) refers to the problem of learning a model in a target domain where labeled data are not available. This paper introduces a novel deep architecture which addresses the problem of UDA by automatically discovering latent domains in visual datasets. We evaluate our approach on publicly available benchmarks, showing that it outperforms state-of-the-art domain adaptation methods.
  arXiv  Detail & Related papers  (2021-03-25T14:33:33Z)
• Cross-Domain Structure Preserving Projection for Heterogeneous Domain Adaptation [23.18781318003242]
  Heterogeneous Domain Adaptation (HDA) addresses the transfer learning problems where data from source and target domains are of different modalities. Traditional domain adaptation algorithms assume that the representations of source and target samples reside in the same feature space. We propose a novel Cross-Domain Structure Preserving Projection (CDSPP) algorithm for HDA.
  arXiv  Detail & Related papers  (2020-04-26T16:22:28Z)

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.