Fast Hierarchical Learning for Few-Shot Object Detection
- URL: http://arxiv.org/abs/2210.05008v1
- Date: Mon, 10 Oct 2022 20:31:19 GMT
- Title: Fast Hierarchical Learning for Few-Shot Object Detection
- Authors: Yihang She, Goutam Bhat, Martin Danelljan, Fisher Yu
- Abstract summary: Transfer learning approaches have recently achieved promising results on the few-shot detection task.
These approaches suffer from catastrophic forgetting'' issue due to finetuning of base detector.
We tackle the aforementioned issues in this work.
- Score: 57.024072600597464
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Transfer learning based approaches have recently achieved promising results
on the few-shot detection task. These approaches however suffer from
``catastrophic forgetting'' issue due to finetuning of base detector, leading
to sub-optimal performance on the base classes. Furthermore, the slow
convergence rate of stochastic gradient descent (SGD) results in high latency
and consequently restricts real-time applications. We tackle the aforementioned
issues in this work. We pose few-shot detection as a hierarchical learning
problem, where the novel classes are treated as the child classes of existing
base classes and the background class. The detection heads for the novel
classes are then trained using a specialized optimization strategy, leading to
significantly lower training times compared to SGD. Our approach obtains
competitive novel class performance on few-shot MS-COCO benchmark, while
completely retaining the performance of the initial model on the base classes.
We further demonstrate the application of our approach to a new class-refined
few-shot detection task.
Related papers
- Meta-tuning Loss Functions and Data Augmentation for Few-shot Object
Detection [7.262048441360132]
Few-shot object detection is an emerging topic in the area of few-shot learning and object detection.
We propose a training scheme that allows learning inductive biases that can boost few-shot detection.
The proposed approach yields interpretable loss functions, as opposed to highly parametric and complex few-shot meta-models.
arXiv Detail & Related papers (2023-04-24T15:14:16Z) - Harmonizing Base and Novel Classes: A Class-Contrastive Approach for
Generalized Few-Shot Segmentation [78.74340676536441]
We propose a class contrastive loss and a class relationship loss to regulate prototype updates and encourage a large distance between prototypes.
Our proposed approach achieves new state-of-the-art performance for the generalized few-shot segmentation task on PASCAL VOC and MS COCO datasets.
arXiv Detail & Related papers (2023-03-24T00:30:25Z) - Margin-Based Few-Shot Class-Incremental Learning with Class-Level
Overfitting Mitigation [19.975435754433754]
Few-shot class-incremental learning (FSCIL) is designed to incrementally recognize novel classes with only few training samples.
A well known modification to the base-class training is to apply a margin to the base-class classification.
We propose a novel margin-based FSCIL method to mitigate the CO problem by providing the pattern learning process with extra constraint from the margin-based patterns themselves.
arXiv Detail & Related papers (2022-10-10T09:45:53Z) - Zero-Shot Temporal Action Detection via Vision-Language Prompting [134.26292288193298]
We propose a novel zero-Shot Temporal Action detection model via Vision-LanguagE prompting (STALE)
Our model significantly outperforms state-of-the-art alternatives.
Our model also yields superior results on supervised TAD over recent strong competitors.
arXiv Detail & Related papers (2022-07-17T13:59:46Z) - Demystifying the Base and Novel Performances for Few-shot
Class-incremental Learning [15.762281194023462]
Few-shot class-incremental learning (FSCIL) has addressed challenging real-world scenarios where unseen novel classes continually arrive with few samples.
It is required to develop a model that recognizes the novel classes without forgetting prior knowledge.
It is shown that our straightforward method has comparable performance with the sophisticated state-of-the-art algorithms.
arXiv Detail & Related papers (2022-06-18T00:39:47Z) - CFA: Constraint-based Finetuning Approach for Generalized Few-Shot
Object Detection [0.0]
Generalized few-shot object detection (G-FSOD) aims to tackle FSOD without forgetting previously seen base classes.
CFA adapts a continual learning method, namely Average Gradient Episodic Memory (A-GEM) to G-FSOD.
Our method outperforms current FSOD and G-FSOD approaches on the novel task with minor degeneration on the base task.
arXiv Detail & Related papers (2022-04-11T16:04:54Z) - Bridging Non Co-occurrence with Unlabeled In-the-wild Data for
Incremental Object Detection [56.22467011292147]
Several incremental learning methods are proposed to mitigate catastrophic forgetting for object detection.
Despite the effectiveness, these methods require co-occurrence of the unlabeled base classes in the training data of the novel classes.
We propose the use of unlabeled in-the-wild data to bridge the non-occurrence caused by the missing base classes during the training of additional novel classes.
arXiv Detail & Related papers (2021-10-28T10:57:25Z) - Revisiting Deep Local Descriptor for Improved Few-Shot Classification [56.74552164206737]
We show how one can improve the quality of embeddings by leveraging textbfDense textbfClassification and textbfAttentive textbfPooling.
We suggest to pool feature maps by applying attentive pooling instead of the widely used global average pooling (GAP) to prepare embeddings for few-shot classification.
arXiv Detail & Related papers (2021-03-30T00:48:28Z) - Few-shot Action Recognition with Prototype-centered Attentive Learning [88.10852114988829]
Prototype-centered Attentive Learning (PAL) model composed of two novel components.
First, a prototype-centered contrastive learning loss is introduced to complement the conventional query-centered learning objective.
Second, PAL integrates a attentive hybrid learning mechanism that can minimize the negative impacts of outliers.
arXiv Detail & Related papers (2021-01-20T11:48:12Z)
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.