Search Results for author: Pengkai Zhu

Found 10 papers, 1 papers with code

Zero-Shot Detection

1 code implementation19 Mar 2018 Pengkai Zhu, Hanxiao Wang, Venkatesh Saligrama

While we utilize semantic features during training, our method is agnostic to semantic information for unseen classes at test-time.

Attribute Object +2

Learning Classifiers for Domain Adaptation, Zero and Few-Shot Recognition Based on Learning Latent Semantic Parts

no code implementations25 Jan 2019 Pengkai Zhu, Hanxiao Wang, Venkatesh Saligrama

In computer vision applications, such as domain adaptation (DA), few shot learning (FSL) and zero-shot learning (ZSL), we encounter new objects and environments, for which insufficient examples exist to allow for training "models from scratch," and methods that adapt existing models, trained on the presented training environment, to the new scenario are required.

Attribute Domain Adaptation +2

Dont Even Look Once: Synthesizing Features for Zero-Shot Detection

no code implementations18 Nov 2019 Pengkai Zhu, Hanxiao Wang, Venkatesh Saligrama

Zero-shot detection, namely, localizing both seen and unseen objects, increasingly gains importance for large-scale applications, with large number of object classes, since, collecting sufficient annotated data with ground truth bounding boxes is simply not scalable.

Object object-detection +1

Don't Even Look Once: Synthesizing Features for Zero-Shot Detection

no code implementations CVPR 2020 Pengkai Zhu, Hanxiao Wang, Venkatesh Saligrama

Zero-shot detection, namely, localizing both seen and unseen objects, increasingly gains importance for large-scale applications, with large number of object classes, since, collecting sufficient annotated data with ground truth bounding boxes is simply not scalable.

Object object-detection +1

Contrastive Neighborhood Alignment

no code implementations6 Jan 2022 Pengkai Zhu, Zhaowei Cai, Yuanjun Xiong, Zhuowen Tu, Luis Goncalves, Vijay Mahadevan, Stefano Soatto

We present Contrastive Neighborhood Alignment (CNA), a manifold learning approach to maintain the topology of learned features whereby data points that are mapped to nearby representations by the source (teacher) model are also mapped to neighbors by the target (student) model.

Learning Compositional Representations for Effective Low-Shot Generalization

no code implementations17 Apr 2022 Samarth Mishra, Pengkai Zhu, Venkatesh Saligrama

RPC encodes images by first decomposing them into salient parts, and then encoding each part as a mixture of a small number of prototypes, each representing a certain concept.

Attribute Few-Shot Learning +2

Fine-grained Few-shot Recognition by Deep Object Parsing

no code implementations14 Jul 2022 Ruizhao Zhu, Pengkai Zhu, Samarth Mishra, Venkatesh Saligrama

An object is parsed by estimating the locations of these K parts and a set of active templates that can reconstruct the part features.

Few-Shot Learning Object

DEED: Dynamic Early Exit on Decoder for Accelerating Encoder-Decoder Transformer Models

no code implementations15 Nov 2023 Peng Tang, Pengkai Zhu, Tian Li, Srikar Appalaraju, Vijay Mahadevan, R. Manmatha

Based on the multi-exit model, we perform step-level dynamic early exit during inference, where the model may decide to use fewer decoder layers based on its confidence of the current layer at each individual decoding step.

Enhancing Vision-Language Pre-training with Rich Supervisions

no code implementations5 Mar 2024 Yuan Gao, Kunyu Shi, Pengkai Zhu, Edouard Belval, Oren Nuriel, Srikar Appalaraju, Shabnam Ghadar, Vijay Mahadevan, Zhuowen Tu, Stefano Soatto

We propose Strongly Supervised pre-training with ScreenShots (S4) - a novel pre-training paradigm for Vision-Language Models using data from large-scale web screenshot rendering.

Table Detection

Cannot find the paper you are looking for? You can Submit a new open access paper.