Despite the tremendous progress in zero-shot learning (ZSL), the majority of existing methods still rely on human-annotated attributes, which are difficult to annotate and scale. An unsupervised alternative is to represent each class using the word embedding associated with its semantic class name. However, word embeddings extracted from pre-trained language models do not necessarily capture visual similarities, resulting in poor zero-shot performance. In this work, we argue that online textual documents e.g., Wikipedia, contain rich visual descriptions about object classes, therefore can be used as powerful unsupervised side information for ZSL. To this end, we propose I2DFormer, a novel transformer-based ZSL framework that jointly learns to encode images and documents by aligning both modalities in a shared embedding space. In order to distill discriminative visual words from noisy documents, we introduce a new cross-modal attention module that learns fine-grained interactions between image patches and document words. Consequently, our I2DFormer not only learns highly discriminative document embeddings that capture visual similarities but also gains the ability to localize visually relevant words in image regions. Quantitatively, we demonstrate that our I2DFormer significantly outperforms previous unsupervised semantic embeddings under both zero-shot and generalized zero-shot learning settings on three public datasets. Qualitatively, we show that our method leads to highly interpretable results where document words can be grounded in the image regions.

Abstract--While deep learning, including Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs), has significantly advanced classification performance, its typical reliance on extensive annotated datasets presents a major obstacle in many practical scenarios where such data is scarce. Vision-language models (VLMs) and transfer learning with pre-trained visual models appear as promising techniques to deal with this problem. This paper proposes a novel zero-shot image classification framework that combines a VLM and a pre-trained visual model within a self-learning cycle. Requiring only the set of class names and no labeled training data, our method utilizes a confidence-based pseudo-labeling strategy to train a lightweight classifier directly on the test data, enabling dynamic adaptation. The VLM identifies high-confidence samples, and the pre-trained visual model enhances their visual representations. These enhanced features then iteratively train the classifier, allowing the system to capture complementary semantic and visual cues without supervision. Notably, our approach avoids VLM fine-tuning and the use of large language models, relying on the visual-only model to reduce the dependence on semantic representation. Experimental evaluations on ten diverse datasets demonstrate that our approach outperforms the baseline zero-shot method. Recent advancements in deep learning have significantly improved image classification performance, making these techniques dominant in current research.

Contrastive Language-Image Pretraining (CLIP) performs zero-shot image classification by mapping images and textual class representation into a shared embedding space, then retrieving the class closest to the image. This work provides a new approach for interpreting CLIP models for image classification from the lens of mutual knowledge between the two modalities. Specifically, we ask: what concepts do both vision and language CLIP encoders learn in common that influence the joint embedding space, causing points to be closer or further apart? We answer this question via an approach of textual concept-based explanations, showing their effectiveness, and perform an analysis encompassing a pool of 13 CLIP models varying in architecture, size and pretraining datasets. We explore those different aspects in relation to mutual knowledge, and analyze zero-shot predictions.

Writing ---------- The paper is well written and well positioned wrt previous work, overall. However, the main technical core of the paper is only about 1.5 pages long. It would have been better imho to have less detailed results tables and reuse that space for explaining the technique in greater detail. Novelty ---------- While I agree that this paper is the first to address zero-shot semantic segmentation, there have been many papers on zero-shot image classification, abd also some papers on zero-shot object class detection. Importantly, the technique proposed is a direct adaptation of [7], a previous technique for zero-shot image classification.

Despite the tremendous progress in zero-shot learning (ZSL), the majority of existing methods still rely on human-annotated attributes, which are difficult to annotate and scale. An unsupervised alternative is to represent each class using the word embedding associated with its semantic class name. However, word embeddings extracted from pre-trained language models do not necessarily capture visual similarities, resulting in poor zero-shot performance. In this work, we argue that online textual documents e.g., Wikipedia, contain rich visual descriptions about object classes, therefore can be used as powerful unsupervised side information for ZSL. To this end, we propose I2DFormer, a novel transformer-based ZSL framework that jointly learns to encode images and documents by aligning both modalities in a shared embedding space.

Recent advancements in medical vision-language pre-training (MedVLP) have significantly enhanced zero-shot medical vision tasks such as image classification by leveraging large-scale medical image-text pair pre-training. However, the performance of these tasks can be heavily influenced by the variability in textual prompts describing the categories, necessitating robustness in MedVLP models to diverse prompt styles. Yet, this sensitivity remains underexplored. In this work, we are the first to systematically assess the sensitivity of three widely-used MedVLP methods to a variety of prompts across 15 different diseases. To achieve this, we designed six unique prompt styles to mirror real clinical scenarios, which were subsequently ranked by interpretability. Our findings indicate that all MedVLP models evaluated show unstable performance across different prompt styles, suggesting a lack of robustness. Additionally, the models' performance varied with increasing prompt interpretability, revealing difficulties in comprehending complex medical concepts. This study underscores the need for further development in MedVLP methodologies to enhance their robustness to diverse zero-shot prompts.

Cross-modal pre-training has shown impressive performance on a wide range of downstream tasks, benefiting from massive image-text pairs collected from the Internet. In practice, online data are growing constantly, highlighting the importance of the ability of pre-trained model to learn from data that is continuously growing. Existing works on cross-modal pre-training mainly focus on training a network with fixed architecture. However, it is impractical to limit the model capacity when considering the continuously growing nature of pre-training data in real-world applications. On the other hand, it is important to utilize the knowledge in the current model to obtain efficient training and better performance. To address the above issues, in this paper, we propose GrowCLIP, a data-driven automatic model growing algorithm for contrastive language-image pre-training with continuous image-text pairs as input. Specially, we adopt a dynamic growth space and seek out the optimal architecture at each growth step to adapt to online learning scenarios. And the shared encoder is proposed in our growth space to enhance the degree of cross-modal fusion. Besides, we explore the effect of growth in different dimensions, which could provide future references for the design of cross-modal model architecture. Finally, we employ parameter inheriting with momentum (PIM) to maintain the previous knowledge and address the issue of the local minimum dilemma. Compared with the existing methods, GrowCLIP improves 2.3% average top-1 accuracy on zero-shot image classification of 9 downstream tasks. As for zero-shot image retrieval, GrowCLIP can improve 1.2% for top-1 image-to-text recall on Flickr30K dataset.

Language-vision models like CLIP have made significant progress in zero-shot vision tasks, such as zero-shot image classification (ZSIC). However, generating specific and expressive class descriptions remains a major challenge. Existing approaches suffer from granularity and label ambiguity issues. To tackle these challenges, we propose V-GLOSS: Visual Glosses, a novel method leveraging modern language models and semantic knowledge bases to produce visually-grounded class descriptions. We demonstrate V-GLOSS's effectiveness by achieving state-of-the-art results on benchmark ZSIC datasets including ImageNet and STL-10. In addition, we introduce a silver dataset with class descriptions generated by V-GLOSS, and show its usefulness for vision tasks. We make available our code and dataset.

Open vocabulary models (e.g. CLIP) have shown strong performance on zero-shot classification through their ability generate embeddings for each class based on their (natural language) names. Prior work has focused on improving the accuracy of these models through prompt engineering or by incorporating a small amount of labeled downstream data (via finetuning). However, there has been little focus on improving the richness of the class names themselves, which can pose issues when class labels are coarsely-defined and are uninformative. We propose Classification with Hierarchical Label Sets (or CHiLS), an alternative strategy for zero-shot classification specifically designed for datasets with implicit semantic hierarchies. CHiLS proceeds in three steps: (i) for each class, produce a set of subclasses, using either existing label hierarchies or by querying GPT-3; (ii) perform the standard zero-shot CLIP procedure as though these subclasses were the labels of interest; (iii) map the predicted subclass back to its parent to produce the final prediction. Across numerous datasets with underlying hierarchical structure, CHiLS leads to improved accuracy in situations both with and without ground-truth hierarchical information. CHiLS is simple to implement within existing zero-shot pipelines and requires no additional training cost. Code is available at: https://github.com/acmi-lab/CHILS.