Neural Information Processing Systems http://nips.cc/

Zero-shot learning (ZSL) aims to recognize unseen object classes without any training samples, which can be regarded as a form of transfer learning from seen classes to unseen ones. This is made possible by learning a projection between a feature space and a semantic space (e.g.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

In principle, zero-shot learning makes it possible to train an object recognition model simply by specifying the category's attributes. For example, with classifiers for generic attributes like striped and four-legged, one can construct a classifier for the zebra category by enumerating which properties it possesses --- even without providing zebra training images. In practice, however, the standard zero-shot paradigm suffers because attribute predictions in novel images are hard to get right. We propose a novel random forest approach to train zero-shot models that explicitly accounts for the unreliability of attribute predictions. By leveraging statistics about each attribute's error tendencies, our method obtains more robust discriminative models for the unseen classes. We further devise extensions to handle the few-shot scenario and unreliable attribute descriptions. On three datasets, we demonstrate the benefit for visual category learning with zero or few training examples, a critical domain for rare categories or categories defined on the fly.

The authors present an algorithm for zero-shot learning based on learning a linear projection between the features of a pre-trained convnet and a semantic space in which to do nearest neighbors classification. Overall, I found the exposition of the paper very confusing, and I am still struggling to understand the exact set-up in the experiments and theorems after several re-readings. I'm not 100% certain from the paper what the authors are actually doing and what they have available as training data. In particular, the authors denote the test images by D_u, which they are sure to point out are unlabeled. They then define l_i {(u)} to be the label of test point x_i {(u)} - how can the label be included in a set of test images that is unlabeled?

Vision-language models (VLMs) excel in zero-shot recognition but their performance varies greatly across different visual concepts. For example, although CLIP achieves impressive accuracy on ImageNet (60-80%), its performance drops below 10% for more than ten concepts like night snake, presumably due to their limited presence in the pretraining data. However, measuring the frequency of concepts in VLMs' large-scale datasets is challenging. We address this by using large language models (LLMs) to count the number of pretraining texts that contain synonyms of these concepts. Our analysis confirms that popular datasets, such as LAION, exhibit a long-tailed concept distribution, yielding biased performance in VLMs. We also find that downstream applications of VLMs, including visual chatbots (e.g., GPT-4V) and text-to-image models (e.g., Stable Diffusion), often fail to recognize or generate images of rare concepts identified by our method. To mitigate the imbalanced performance of zero-shot VLMs, we propose REtrieval-Augmented Learning (REAL). First, instead of prompting VLMs using the original class names, REAL uses their most frequent synonyms found in pretraining texts. This simple change already outperforms costly human-engineered and LLM-enriched prompts over nine benchmark datasets. Second, REAL trains a linear classifier on a small yet balanced set of pretraining data retrieved using concept synonyms. REAL surpasses the previous zero-shot SOTA, using 400x less storage and 10,000x less training time!

Chinese characters carry a wealth of morphological and semantic information; therefore, the semantic enhancement of the morphology of Chinese characters has drawn significant attention. The previous methods were intended to directly extract information from a whole Chinese character image, which usually cannot capture both global and local information simultaneously. In this paper, we develop a stroke-based autoencoder(SAE), to model the sophisticated morphology of Chinese characters with the self-supervised method. Following its canonical writing order, we first represent a Chinese character as a series of stroke images with a fixed writing order, and then our SAE model is trained to reconstruct this stroke image sequence. This pre-trained SAE model can predict the stroke image series for unseen characters, as long as their strokes or radicals appeared in the training set. We have designed two contrasting SAE architectures on different forms of stroke images. One is fine-tuned on existing stroke-based method for zero-shot recognition of handwritten Chinese characters, and the other is applied to enrich the Chinese word embeddings from their morphological features. The experimental results validate that after pre-training, our SAE architecture outperforms other existing methods in zero-shot recognition and enhances the representation of Chinese characters with their abundant morphological and semantic information.

In principle, zero-shot learning makes it possible to train an object recognition model simply by specifying the category's attributes. For example, with classifiers for generic attributes like striped and four-legged, one can construct a classifier for the zebra category by enumerating which properties it possesses --- even without providing zebra training images. In practice, however, the standard zero-shot paradigm suffers because attribute predictions in novel images are hard to get right. We propose a novel random forest approach to train zero-shot models that explicitly accounts for the unreliability of attribute predictions. By leveraging statistics about each attribute's error tendencies, our method obtains more robust discriminative models for the unseen classes.

Zero-shot learning (ZSL) aims to recognize unseen object classes without any training samples, which can be regarded as a form of transfer learning from seen classes to unseen ones. This is made possible by learning a projection between a feature space and a semantic space (e.g. Key to ZSL is thus to learn a projection function that is robust against the often large domain gap between the seen and unseen classes. In this paper, we propose a novel ZSL model termed domain-invariant projection learning (DIPL). Our model has two novel components: (1) A domain-invariant feature self-reconstruction task is introduced to the seen/unseen class data, resulting in a simple linear formulation that casts ZSL into a min-min optimization problem.