Timezone: »
We describe an approach to learning from long-tailed, imbalanced datasets that are prevalent in real-world settings. Here, the challenge is to learn accurate "few-shot'' models for classes in the tail of the class distribution, for which little data is available. We cast this problem as transfer learning, where knowledge from the data-rich classes in the head of the distribution is transferred to the data-poor classes in the tail. Our key insights are as follows. First, we propose to transfer meta-knowledge about learning-to-learn from the head classes. This knowledge is encoded with a meta-network that operates on the space of model parameters, that is trained to predict many-shot model parameters from few-shot model parameters. Second, we transfer this meta-knowledge in a progressive manner, from classes in the head to the "body'', and from the "body'' to the tail. That is, we transfer knowledge in a gradual fashion, regularizing meta-networks for few-shot regression with those trained with more training data. This allows our final network to capture a notion of model dynamics, that predicts how model parameters are likely to change as more training data is gradually added. We demonstrate results on image classification datasets (SUN, Places, and ImageNet) tuned for the long-tailed setting, that significantly outperform common heuristics, such as data resampling or reweighting.
Author Information
Yu-Xiong Wang (Carnegie Mellon University)
Deva Ramanan (Carnegie Mellon University)
Martial Hebert (cmu)
More from the Same Authors
-
2021 Spotlight: ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction »
Gengshan Yang · Deqing Sun · Varun Jampani · Daniel Vlasic · Forrester Cole · Ce Liu · Deva Ramanan -
2021 : Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting »
Benjamin Wilson · William Qi · Tanmay Agarwal · John Lambert · Jagjeet Singh · Siddhesh Khandelwal · Bowen Pan · Ratnesh Kumar · Andrew Hartnett · Jhony Kaesemodel Pontes · Deva Ramanan · Peter Carr · James Hays -
2021 : The CLEAR Benchmark: Continual LEArning on Real-World Imagery »
Zhiqiu Lin · Jia Shi · Deepak Pathak · Deva Ramanan -
2022 Poster: Learning With an Evolving Class Ontology »
Zhiqiu Lin · Deepak Pathak · Yu-Xiong Wang · Deva Ramanan · Shu Kong -
2022 Poster: Learning to Discover and Detect Objects »
Vladimir Fomenko · Ismail Elezi · Deva Ramanan · Laura Leal-TaixĂ© · Aljosa Osep -
2021 Poster: ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction »
Gengshan Yang · Deqing Sun · Varun Jampani · Daniel Vlasic · Forrester Cole · Ce Liu · Deva Ramanan -
2021 Poster: NeRS: Neural Reflectance Surfaces for Sparse-view 3D Reconstruction in the Wild »
Jason Zhang · Gengshan Yang · Shubham Tulsiani · Deva Ramanan -
2019 Poster: Volumetric Correspondence Networks for Optical Flow »
Gengshan Yang · Deva Ramanan -
2017 Poster: Predictive-State Decoders: Encoding the Future into Recurrent Networks »
Arun Venkatraman · Nicholas Rhinehart · Wen Sun · Lerrel Pinto · Martial Hebert · Byron Boots · Kris Kitani · J. Bagnell -
2017 Poster: Attentional Pooling for Action Recognition »
Rohit Girdhar · Deva Ramanan -
2016 Poster: Combining Low-Density Separators with CNNs »
Yu-Xiong Wang · Martial Hebert -
2010 Poster: Estimating Spatial Layout of Rooms using Volumetric Reasoning about Objects and Surfaces »
David C Lee · Abhinav Gupta · Martial Hebert · Takeo Kanade -
2009 Poster: An Integer Projected Fixed Point Method for Graph Matching and MAP Inference »
Marius Leordeanu · Martial Hebert · Rahul Sukthankar