Crossmodal Knowledge Distillation with WordNet-Relaxed Text Embeddings for Robust Image Classification

• URL: http://arxiv.org/abs/2503.24017v1
• Date: Mon, 31 Mar 2025 12:41:26 GMT
• Title: Crossmodal Knowledge Distillation with WordNet-Relaxed Text Embeddings for Robust Image Classification
• Authors: Chenqi Guo, Mengshuo Rong, Qianli Feng, Rongfan Feng, Yinglong Ma,
• Abstract summary: Crossmodal knowledge distillation aims to enhance a unimodal student using a multimodal teacher model.<n>We propose a framework that integrates CLIP image embeddings with learnable WordNet-relaxed text embeddings under a hierarchical loss.
• Score: 4.479574573760553
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Crossmodal knowledge distillation (KD) aims to enhance a unimodal student using a multimodal teacher model. In particular, when the teacher's modalities include the student's, additional complementary information can be exploited to improve knowledge transfer. In supervised image classification, image datasets typically include class labels that represent high-level concepts, suggesting a natural avenue to incorporate textual cues for crossmodal KD. However, these labels rarely capture the deeper semantic structures in real-world visuals and can lead to label leakage if used directly as inputs, ultimately limiting KD performance. To address these issues, we propose a multi-teacher crossmodal KD framework that integrates CLIP image embeddings with learnable WordNet-relaxed text embeddings under a hierarchical loss. By avoiding direct use of exact class names and instead using semantically richer WordNet expansions, we mitigate label leakage and introduce more diverse textual cues. Experiments show that this strategy significantly boosts student performance, whereas noisy or overly precise text embeddings hinder distillation efficiency. Interpretability analyses confirm that WordNet-relaxed prompts encourage heavier reliance on visual features over textual shortcuts, while still effectively incorporating the newly introduced textual cues. Our method achieves state-of-the-art or second-best results on six public datasets, demonstrating its effectiveness in advancing crossmodal KD.

Related papers

• Data-free Multi-label Image Recognition via LLM-powered Prompt Tuning [23.671999163027284]
  This paper proposes a novel framework for multi-label image recognition without any training data. It uses knowledge of pre-trained Large Language Model to learn prompts to adapt pretrained Vision-Language Model like CLIP to multilabel classification. Our framework presents a new way to explore the synergies between multiple pre-trained models for novel category recognition.
  arXiv  Detail & Related papers  (2024-03-02T13:43:32Z)
• CLIP-Driven Semantic Discovery Network for Visible-Infrared Person Re-Identification [39.262536758248245]
  Cross-modality identity matching poses significant challenges in VIReID. We propose a CLIP-Driven Semantic Discovery Network (CSDN) that consists of Modality-specific Prompt Learner, Semantic Information Integration, and High-level Semantic Embedding.
  arXiv  Detail & Related papers  (2024-01-11T10:20:13Z)
• Leveraging Open-Vocabulary Diffusion to Camouflaged Instance Segmentation [59.78520153338878]
  Text-to-image diffusion techniques have shown exceptional capability of producing high-quality images from text descriptions. We propose a method built upon a state-of-the-art diffusion model, empowered by open-vocabulary to learn multi-scale textual-visual features for camouflaged object representations.
  arXiv  Detail & Related papers  (2023-12-29T07:59:07Z)
• Task-Oriented Multi-Modal Mutual Leaning for Vision-Language Models [52.3032592038514]
  We propose a class-aware text prompt to enrich generated prompts with label-related image information. We achieve an average improvement of 4.03% on new classes and 3.19% on harmonic-mean over eleven classification benchmarks.
  arXiv  Detail & Related papers  (2023-03-30T06:02:40Z)
• CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval [108.48540976175457]
  We propose Coupled Diversity-Sensitive Momentum Constrastive Learning (CODER) for improving cross-modal representation. We introduce dynamic dictionaries for both modalities to enlarge the scale of image-text pairs, and diversity-sensitiveness is achieved by adaptive negative pair weighting. Experiments conducted on two popular benchmarks, i.e. MSCOCO and Flicker30K, validate CODER remarkably outperforms the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-08-21T08:37:50Z)
• Cross-Image Relational Knowledge Distillation for Semantic Segmentation [16.0341383592071]
  Cross-Image KD (CIRK) focuses on transferring structured pixel-to-pixel and pixel-to-region relations among whole images. The motivation is that a good teacher network could construct a well-structured feature space in terms of global pixel dependencies. CIRK makes the student mimic better structured relations from the teacher, thus improving the segmentation performance.
  arXiv  Detail & Related papers  (2022-04-14T14:24:19Z)
• CRIS: CLIP-Driven Referring Image Segmentation [71.56466057776086]
  We propose an end-to-end CLIP-Driven Referring Image framework (CRIS) CRIS resorts to vision-language decoding and contrastive learning for achieving the text-to-pixel alignment. Our proposed framework significantly outperforms the state-of-the-art performance without any post-processing.
  arXiv  Detail & Related papers  (2021-11-30T07:29:08Z)
• Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision [57.031588264841]
  We leverage a noisy dataset of over one billion image alt-text pairs, obtained without expensive filtering or post-processing steps. A simple dual-encoder architecture learns to align visual and language representations of the image and text pairs using a contrastive loss. We show that the scale of our corpus can make up for its noise and leads to state-of-the-art representations even with such a simple learning scheme.
  arXiv  Detail & Related papers  (2021-02-11T10:08:12Z)
• Improving Image Captioning with Better Use of Captions [65.39641077768488]
  We present a novel image captioning architecture to better explore semantics available in captions and leverage that to enhance both image representation and caption generation. Our models first construct caption-guided visual relationship graphs that introduce beneficial inductive bias using weakly supervised multi-instance learning. During generation, the model further incorporates visual relationships using multi-task learning for jointly predicting word and object/predicate tag sequences.
  arXiv  Detail & Related papers  (2020-06-21T14:10:47Z)

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.