Towards Reusable Network Components by Learning Compatible
Representations
- URL: http://arxiv.org/abs/2004.03898v3
- Date: Wed, 16 Dec 2020 13:31:27 GMT
- Title: Towards Reusable Network Components by Learning Compatible
Representations
- Authors: Michael Gygli, Jasper Uijlings, Vittorio Ferrari
- Abstract summary: We split a network into two components, a features extractor and a target task head, and propose various approaches to accomplish compatibility between them.
We show that we can produce components which are directly compatible without any fine-tuning or compromising accuracy on the original tasks.
- Score: 45.108375151687966
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper proposes to make a first step towards compatible and hence
reusable network components. Rather than training networks for different tasks
independently, we adapt the training process to produce network components that
are compatible across tasks. In particular, we split a network into two
components, a features extractor and a target task head, and propose various
approaches to accomplish compatibility between them. We systematically analyse
these approaches on the task of image classification on standard datasets. We
demonstrate that we can produce components which are directly compatible
without any fine-tuning or compromising accuracy on the original tasks.
Afterwards, we demonstrate the use of compatible components on three
applications: Unsupervised domain adaptation, transferring classifiers across
feature extractors with different architectures, and increasing the
computational efficiency of transfer learning.
Related papers
- S$^3$M-Net: Joint Learning of Semantic Segmentation and Stereo Matching
for Autonomous Driving [40.305452898732774]
S$3$M-Net is a novel joint learning framework developed to perform semantic segmentation and stereo matching simultaneously.
S$3$M-Net shares the features extracted from RGB images between both tasks, resulting in an improved overall scene understanding capability.
arXiv Detail & Related papers (2024-01-21T06:47:33Z) - Cooperative Learning for Cost-Adaptive Inference [3.301728339780329]
The proposed framework is not tied to any specific architecture but can incorporate any existing models/architectures.
It provides comparable accuracy to its full network while various sizes of models are available.
arXiv Detail & Related papers (2023-12-13T21:42:27Z) - OmniVec: Learning robust representations with cross modal sharing [28.023214572340336]
We present an approach to learn multiple tasks, in multiple modalities, with a unified architecture.
The proposed network is composed of task specific encoders, a common trunk in the middle, followed by task specific prediction heads.
We train the network on all major modalities, e.g. visual, audio, text and 3D, and report results on $22$ diverse and challenging public benchmarks.
arXiv Detail & Related papers (2023-11-07T14:00:09Z) - Multi-task Learning with 3D-Aware Regularization [55.97507478913053]
We propose a structured 3D-aware regularizer which interfaces multiple tasks through the projection of features extracted from an image encoder to a shared 3D feature space.
We show that the proposed method is architecture agnostic and can be plugged into various prior multi-task backbones to improve their performance.
arXiv Detail & Related papers (2023-10-02T08:49:56Z) - Feature Decoupling-Recycling Network for Fast Interactive Segmentation [79.22497777645806]
Recent interactive segmentation methods iteratively take source image, user guidance and previously predicted mask as the input.
We propose the Feature Decoupling-Recycling Network (FDRN), which decouples the modeling components based on their intrinsic discrepancies.
arXiv Detail & Related papers (2023-08-07T12:26:34Z) - Factorizing Knowledge in Neural Networks [65.57381498391202]
We propose a novel knowledge-transfer task, Knowledge Factorization(KF)
KF aims to decompose it into several factor networks, each of which handles only a dedicated task and maintains task-specific knowledge factorized from the source network.
We introduce an information-theoretic objective, InfoMax-Bottleneck(IMB), to carry out KF by optimizing the mutual information between the learned representations and input.
arXiv Detail & Related papers (2022-07-04T09:56:49Z) - Fast Inference and Transfer of Compositional Task Structures for
Few-shot Task Generalization [101.72755769194677]
We formulate it as a few-shot reinforcement learning problem where a task is characterized by a subtask graph.
Our multi-task subtask graph inferencer (MTSGI) first infers the common high-level task structure in terms of the subtask graph from the training tasks.
Our experiment results on 2D grid-world and complex web navigation domains show that the proposed method can learn and leverage the common underlying structure of the tasks for faster adaptation to the unseen tasks.
arXiv Detail & Related papers (2022-05-25T10:44:25Z) - Dual Path Structural Contrastive Embeddings for Learning Novel Objects [6.979491536753043]
Recent research shows that gaining information on a good feature space can be an effective solution to achieve favorable performance on few-shot tasks.
We propose a simple but effective paradigm that decouples the tasks of learning feature representations and classifiers.
Our method can still achieve promising results for both standard and generalized few-shot problems in either an inductive or transductive inference setting.
arXiv Detail & Related papers (2021-12-23T04:43:31Z) - Dynamic Feature Integration for Simultaneous Detection of Salient
Object, Edge and Skeleton [108.01007935498104]
In this paper, we solve three low-level pixel-wise vision problems, including salient object segmentation, edge detection, and skeleton extraction.
We first show some similarities shared by these tasks and then demonstrate how they can be leveraged for developing a unified framework.
arXiv Detail & Related papers (2020-04-18T11:10:11Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.