Evaluating knowledge transfer and zero-shot learning in a large-scale setting

By Marcus Rohrbach, Michael Stark, Bernt Schiele. 2011

377 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Evaluation & Benchmarks, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Evaluation & Benchmarks

In Meta & Continual Learning

Citations in the corpus

ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models (2022, neutral): “They are usually in single domain, with a manual split of categories to product disjoint training and test categories, e.g., Animal with Attributes (AwA) [31], Caltech-UCSD Birds-200 (CUB) [64], SUN [47], aPY [14], and ZS-ImageNet [52, 17].”
Learning Deep Representations of Fine-Grained Visual Descriptions (2016, background): “for zero-shot learning [36, 38, 24, 33, 12, 41, 2] and automatically generating image captions for general web images [23, 35, 45, 20, 8].”
Transductive Multi-View Zero-Shot Learning (2015, methodology): “Note that for the auxiliary dataset, Y iS is given as each data point is labelled.”
Deep Metric Learning via Lifted Structured Feature Embedding (2015, background): “Figure 2c illustrates the concept of of transforming a training batch of examples to a fully connected dense matrix of pairwise distances.”
Zero-Shot Learning—A Comprehensive Evaluation of the Good, the Bad and the Ugly (2017, background): “In this work, we evaluated a signiﬁcant number of state-of-the-art zero-shot learning methods, i.e. [1], [13], [11], [9], [10], [14], [12], [15], [7], [30], [33], [41], [71], on several datasets, i.e. SUN, CUB, AWA1, AWA2, aPY and ImageNet, within a uniﬁed evaluation protocol both in zero-shot and g”
Zero-Shot Learning by Convex Combination of Semantic Embeddings (2013, background): “Recently, zero-shot learning [10, 14] has received a growing amount of attention [16, 11, 6, 18].”
Zero-Shot Learning — The Good, the Bad and the Ugly (2017, methodology): “In zero-shot learning setting test and training class sets are disjoint [17, 22, 23, 30, 40] which can be tackled by solving related sub-problems, e.”
Open-vocabulary Object Detection via Vision and Language Knowledge Distillation (2021, background): “…direction, researchers have also explored class hierarchy, class similarity, and object parts as discriminative features to aid the knowledge transfer (Rohrbach et al., 2011; Akata et al., 2016; Zhao et al., 2017; Elhoseiny et al., 2017; Ji et al., 2018; Cacheux et al., 2019; Xie et al., 2020).”
Towards a Visual Turing Challenge (2014, background): “To judge competing architectures and measure the progress on the task, we suggest several directions to further improve existing metrics, and discuss differentexperimental scenarios.”
Latent Embeddings for Zero-Shot Classification (2016, background): “attribute prediction [20, 30, 31], or by a direct approach, e.”
Label-Embedding for Image Classification (2015, neutral): “Possible sources of prior information include attributes [30], [18], [43], [47], [46], semantic class taxonomies [46], [39], class-to-class similarities [47], [70], text features [43], [47], [46], [57], [20] or class co-occurrence statistics [37].”
An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild (2016, methodology): “Existing research on ZSL has been almost entirely focusing on this setting [4,10,11,12,13,14,15,8,16,17,18,19,20,21,22,23,24,25,26,27,28].”
Concept Generalization in Visual Representation Learning (2020, neutral): “Following [44, 45], we define p(c) as the number of concepts that exist under c divided by the total number of concepts in the corpus.”
Transfer Learning in a Transductive Setting (2013, methodology): “It consists of 1000 image categories which are split into 800 training and 200 test categories according to [23].”
The SUN Attribute Database: Beyond Categories for Deeper Scene Understanding (2014, methodology): “because the scene category labels were not used to help learn the mapping from pixel-features to attributes (Rohrbach et al. 2011).”
Enhanced representation and multi-task learning for image annotation (2013, background): “Other algorithms like [17, 18, 19] were proposed for zero-shot learning in a large-scale setting, i.”
A database for fine grained activity detection of cooking activities (2012, methodology): “We train one-vs-all SVMs using mean SGD [27] with a χ 2 kernel approximation [37].”