Timezone: »

 
Revisiting Visual Product for Compositional Zero-Shot Learning
Shyamgopal Karthik · Massimiliano Mancini · Zeynep Akata
Event URL: https://openreview.net/forum?id=Yc9Vh1nn-2I »

Compositional Zero-Shot Learning (CZSL) aims to recognize compositions of objects and states in images, and generalize to the unseen compositions of objects and states. Recent works tackled this problem effectively by using side information (e.g., word embeddings) together with either consistency constraints or specific network designs modeling the relationships between objects, states, compositions, and visual features. In this work, we take a step back, and we revisit the simplest baseline for this task, i.e., Visual Product (VisProd). VisProd considers CZSL as a multi-task problem, predicting objects and states separately. Despite its appealing simplicity, this baseline showed low performance in early CZSL studies. Here we identify the two main reasons behind such unimpressive initial results: network capacity and bias on the seen classes. We show that simple modifications to the object and state predictors allow the model to achieve either comparable or superior results w.r.t. the recent state of the art in both the open-world and closed-world CZSL settings on three different benchmarks.

Author Information

Shyamgopal Karthik (University of Tübingen)

Hi! I am a final year Master's at IIIT Hyderabad currently pursuing my Master's degree at the Center for Visual Information Technology. My primary areas of research are in the fields of Computer Vision and Machine Learning. In particular, I have been working on visual object tracking in various settings. In addition to this, I have worked on hierarchical classification and explored calibration of deep neural networks. I also maintain an avid interest in Discrete and Combinatorial Optimization.

Massimiliano Mancini (University of Tuebingen)
Zeynep Akata (Max Planck Institute for Informatics)

More from the Same Authors

  • 2022 Spotlight: Lightning Talks 6A-4 »
    Xiu-Shen Wei · Konstantina Dritsa · Guillaume Huguet · ABHRA CHAUDHURI · Zhenbin Wang · Kevin Qinghong Lin · Yutong Chen · Jianan Zhou · Yongsen Mao · Junwei Liang · Jinpeng Wang · Mao Ye · Yiming Zhang · Aikaterini Thoma · H.-Y. Xu · Daniel Sumner Magruder · Enwei Zhang · Jianing Zhu · Ronglai Zuo · Massimiliano Mancini · Hanxiao Jiang · Jun Zhang · Fangyun Wei · Faen Zhang · Ioannis Pavlopoulos · Zeynep Akata · Xiatian Zhu · Jingfeng ZHANG · Alexander Tong · Mattia Soldan · Chunhua Shen · Yuxin Peng · Liuhan Peng · Michael Wray · Tongliang Liu · Anjan Dutta · Yu Wu · Oluwadamilola Fasina · Panos Louridas · Angel Chang · Manik Kuchroo · Manolis Savva · Shujie LIU · Wei Zhou · Rui Yan · Gang Niu · Liang Tian · Bo Han · Eric Z. XU · Guy Wolf · Yingying Zhu · Brian Mak · Difei Gao · Masashi Sugiyama · Smita Krishnaswamy · Rong-Cheng Tu · Wenzhe Zhao · Weijie Kong · Chengfei Cai · WANG HongFa · Dima Damen · Bernard Ghanem · Wei Liu · Mike Zheng Shou
  • 2022 Spotlight: Relational Proxies: Emergent Relationships as Fine-Grained Discriminators »
    ABHRA CHAUDHURI · Massimiliano Mancini · Zeynep Akata · Anjan Dutta
  • 2022 Poster: Relational Proxies: Emergent Relationships as Fine-Grained Discriminators »
    ABHRA CHAUDHURI · Massimiliano Mancini · Zeynep Akata · Anjan Dutta
  • 2021 Poster: Fine-Grained Zero-Shot Learning with DNA as Side Information »
    Sarkhan Badirli · Zeynep Akata · George Mohler · Christine Picard · Mehmet M Dundar
  • 2021 Poster: Robustness via Uncertainty-aware Cycle Consistency »
    Uddeshya Upadhyay · Yanbei Chen · Zeynep Akata
  • 2016 Poster: Learning What and Where to Draw »
    Scott E Reed · Zeynep Akata · Santosh Mohan · Samuel Tenka · Bernt Schiele · Honglak Lee
  • 2016 Oral: Learning What and Where to Draw »
    Scott E Reed · Zeynep Akata · Santosh Mohan · Samuel Tenka · Bernt Schiele · Honglak Lee