- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes SPARC, a framework for compositional zero-shot learning (CZSL) that reduces object-induced shortcuts while preserving useful object context. It introduces a complementary-evidence feedback adapter to refine visual representations, along with object-discounted loss, hierarchical margins, and inference-time score correction to mitigate object bias. Experiments on three CZSL benchmarks demonstrate competitive performance in both closed-world and open-world settings, supported by ablation studies.
Critical strengths
- The paper identifies a relevant challenge in compositional zero-shot learning, where models may exploit frequently observed attribute-object associations rather than learning sufficient visual evidence for attributes. The distinction between useful object context and harmful object-induced shortcuts provides a reasonable motivation for improving compositional generalization.
- The proposed framework addresses object influence at three different stages through complementary-evidence feedback, object-relative training objectives, and image-dependent score rectification.
- The experiments demonstrate competitive results on three standard CZSL benchmarks under closed-world and open-world settings.
Critical weaknesses
- The methodological novelty of SPARC appears limited, as it mainly combines established techniques such as attention-based feature adaptation, residual projection, auxiliary losses, and score calibration. Similar ideas have been explored in existing CZSL methods, including CPF (ICCV 2025) for object-conditioned attribute learning, ProLT (AAAI 2024) for distribution-prior adjustment, and Mutual Balancing (Pattern Recognition 2024) for balancing attribute-object components.
- Although the paper aims to mitigate object-induced shortcuts, the experiments mainly focus on recognition accuracy without directly measuring shortcut reduction. It remains unclear whether the improvements stem from better attribute grounding or generic feature enhancement and score calibration. The authors should include controlled analyses of predictions for the same object with different attributes, as well as evaluations under varying attribute-object co-occurrence biases, to better validate the effectiveness of shortcut mitigation.
- The semantic validity of the proposed object-related and complementary supports remains questionable. Low object similarity does not necessarily indicate informative attribute evidence, as it may instead arise from background clutter, occlusion, or noise, particularly in challenging datasets such as MIT-States and C-GQA. It would be better to provide attention map visualizations to verify whether the proposed decomposition effectively distinguishes object-related regions from meaningful attribute cues.
Questions for authors
Please see the Weaknesses.