Simultaneous Deep Transfer Across Domains and Tasks

By Judy Hoffman, Eric Tzeng, Trevor Darrell, Kate Saenko. 2015

1,414 citations recorded by the source corpus.

Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias. Fine-tuning deep models in a new domain can require a significant amount of labeled data, which for many applications is simply not available. We propose a new CNN architecture to exploit unlabeled and sparsely labeled target domain data. Our approach simultaneously optimizes for domain invariance to facilitate domain transfer and uses a soft label distribution matching loss to transfer information between tasks. Our proposed adaptation method offers empirical performance which exceeds previously published results on two standard benchmark visual domain adaptation tasks, evaluated across supervised and semi-supervised adaptation settings.

Subfields: Artificial Intelligence, Representation & Self-Supervised 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 Representation & Self-Supervised Learning

Citations in the corpus

Growing a Brain: Fine-Tuning by Increasing Model Capacity (2017, background): “Transfer learning is related to both multi-task learning [32, 4, 28, 10, 11, 45, 24, 2] and learning novel categories from few examples [49, 19, 21, 35, 51, 22, 5, 13, 50, 47, 31].”
Learning Robust Global Representations by Penalizing Local Predictive Power (2019, methodology): “At a high level these methods comprise two subtypes: fine-tuning over target domain (Long et al., 2016; Hoffman et al., 2017; Motiian et al., 2017a; Gebru et al., 2017; Volpi et al., 2018) and coercing domain invariance via adversarial learning (or further extensions) (Ganin et al.”
Women also Snowboard: Overcoming Bias in Captioning Models (2018, neutral): “Similar techniques which incorporate distribution matching have been used for other problems including domain adaptation [18,19] and transduction learning [20].”
A Joint Sequence Fusion Model for Video Question Answering and Retrieval (2018, neutral): “Fusion-VGG-noaudio 68.7 75.6 JSFusion-noaudio 72.5 82.9 JSFusion 73.5 83.4 Fill-in-the-Blank Accuracy Text-only BLSTM [34] 32.0 Text-only Human [34] 30.2 GoogleNet-2D + C3D [34] 35.7 Ask Your Neurons [46] 33.2 Merging-LSTM [35] 34.2 SNUVL [29] 38.0 CT-SAN [9] 41.9 LR/RL LSTMs [36] 40.9 LR/RL LSTMs (”
Multiple-Source Adaptation with Domain Classifiers (2020, neutral): “…al., 2008, 2009a, Hoffman et al., 2018, Pan and Yang, 2010, Muandet et al., 2013, Xu et al., 2014, Hoffman et al., 2012, Gong et al., 2013a,b, Zhang et al., 2015, Ganin et al., 2016, Tzeng et al., 2015, Motiian et al., 2017b,a, Wang et al., 2019, Konstantinov and Lampert, 2019, Liu et al., 2015].”
A Theory of Multiple-Source Adaptation with Limited Target Labeled Data (2020, background): “Tzeng et al. (2015) proposed a CNN architecture to exploit unlabeled and sparsely labeled target domain data.”
Agnostic Federated Learning (2019, methodology): “…Mohri, and Mu˜noz Medina, 2015), either through unsupervised adaptation techniques (Gong et al., 2012; Long et al., 2015; Ganin and Lempitsky, 2015; Tzeng et al., 2015), or via lightly supervised ones (some amount of labeled data from the target domain) (Saenko et al., 2010; Yang et al., 2007;…”
Algorithms and Theory for Multiple-Source Adaptation (2018, background): “The problem of transfer from a single source to a known target domain (Ben-David, Blitzer, Crammer, and Pereira, 2006; Mansour, Mohri, and Rostamizadeh, 2009b; Cortes and Mohri, 2014; Cortes, Mohri, and Muñoz Medina, 2015), either through unsupervised adaptation techniques (Gong et al., 2012; Long e”
Knowledge Flow: Improve Upon Your Teachers (2019, background): “…2016), learning without forgetting (Li & Hoiem, 2016), growing a brain (Wang et al., 2017), policy distillation (Rusu et al., 2016a), domain adaptation (Pan & Yang, 2010; Long et al., 2015; Tzeng et al., 2015), knowledge distillation (Hin-ton et al., 2015) or lifelong learning (Chen & Liu, 2016).”
Few-Shot Adversarial Domain Adaptation (2017, methodology): “Domain Adaptation can be supervised [58, 27], unsupervised [15, 34], or semi-supervised [16, 21, 63], depending on what data is available in a labeled format and how much can be collected.”
Sim-to-Real Robot Learning from Pixels with Progressive Nets (2016, background): “In [13], a ‘confusion’ loss is proposed which forces the model to ignore variations in the data that separate the two domains [24, 25].”
Incremental Learning of Object Detectors without Catastrophic Forgetting (2017, background): “It has found several applications in domain adaptation and model compression [17, 34, 39].”
Cross Modal Distillation for Supervision Transfer (2015, methodology): “in [45]).”
The limits and potentials of deep learning for robotics (2018, background): “In [70], a ‘confusion’ loss is proposed which forces the model to ignore variations in the data that separate the two domains [122], [123], and [121] attempts to address the simulation to reality gap by using aligned data.”
Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience (2018, background): “to account for potential domain shifts between observations [16, 39, 40].”