On zero-shot recognition of generic objects
Many recent advances in computer vision are the result of a healthy competition among researchers on high quality, task-specific, benchmarks. After a decade of active research, zero-shot learning (ZSL) models accuracy on the Imagenet benchmark remains far too low to be considered for practical object recognition applications. In this paper, we argue that the main reason behind this apparent lack of progress is the poor quality of this benchmark. We highlight major structural flaws of the current benchmark and analyze different factors impacting the accuracy of ZSL models. We show that the actual classification accuracy of existing ZSL models is significantly higher than was previously thought as we account for these flaws. We then introduce the notion of structural bias specific to ZSL datasets. We discuss how the presence of this new form of bias allows for a trivial solution to the standard benchmark and conclude on the need for a new benchmark. We then detail the semi-automated construction of a new benchmark to address these flaws.
Code (1)
Tasks
Object RecognitionZero-Shot LearningSimilar Papers 제목 키워드 기반
AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection
Zero-shot anomaly detection (ZSAD) requires detection models trained using auxiliary data to detect anomalies without any training sample in a target dataset. It is a crucial task when training data is not accessible due…
Anomaly DetectionPrompt Learningzero-shot anomaly detectionZero-Shot LearningSAVE: Self-Attention on Visual Embedding for Zero-Shot Generic Object Counting
Zero-shot counting is a subcategory of Generic Visual Object Counting, which aims to count objects from an arbitrary class in a given image. While few-shot counting relies on delivering exemplars to the model to count si…
Exemplar-Free CountingObjectObject CountingZero-Shot CountingContext-Aware Zero-Shot Recognition
We present a novel problem setting in zero-shot learning, zero-shot object recognition and detection in the context. Contrary to the traditional zero-shot learning methods, which simply infers unseen categories by transf…
Object RecognitionZero-Shot LearningZero-Shot Visual Classification with Guided Cropping
Pretrained vision-language models, such as CLIP, show promising zero-shot performance across a wide variety of datasets. For closed-set classification tasks, however, there is an inherent limitation: CLIP image encoders …
ClassificationObjectobject-detectionObject Detection+3Can masking background and object reduce static bias for zero-shot action recognition?
In this paper, we address the issue of static bias in zero-shot action recognition. Action recognition models need to represent the action itself, not the appearance. However, some fully-supervised works show that models…
Action RecognitionZero-Shot Action Recognition