Dissecting the impact of different loss functions with gradient surgery
- URL: http://arxiv.org/abs/2201.11307v1
- Date: Thu, 27 Jan 2022 03:55:48 GMT
- Title: Dissecting the impact of different loss functions with gradient surgery
- Authors: Hong Xuan and Robert Pless
- Abstract summary: Pair-wise loss is an approach to metric learning that learns a semantic embedding by optimizing a loss function.
Here we decompose the gradient of these loss functions into components that relate to how they push the relative feature positions of the anchor-positive and anchor-negative pairs.
- Score: 7.001832294837659
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Pair-wise loss is an approach to metric learning that learns a semantic
embedding by optimizing a loss function that encourages images from the same
semantic class to be mapped closer than images from different classes. The
literature reports a large and growing set of variations of the pair-wise loss
strategies. Here we decompose the gradient of these loss functions into
components that relate to how they push the relative feature positions of the
anchor-positive and anchor-negative pairs. This decomposition allows the
unification of a large collection of current pair-wise loss functions.
Additionally, explicitly constructing pair-wise gradient updates to separate
out these effects gives insights into which have the biggest impact, and leads
to a simple algorithm that beats the state of the art for image retrieval on
the CAR, CUB and Stanford Online products datasets.
Related papers
- Mitigating the Effect of Incidental Correlations on Part-based Learning [50.682498099720114]
Part-based representations could be more interpretable and generalize better with limited data.
We present two innovative regularization methods for part-based representations.
We exhibit state-of-the-art (SoTA) performance on few-shot learning tasks on benchmark datasets.
arXiv Detail & Related papers (2023-09-30T13:44:48Z) - PAIF: Perception-Aware Infrared-Visible Image Fusion for Attack-Tolerant
Semantic Segmentation [50.556961575275345]
We propose a perception-aware fusion framework to promote segmentation robustness in adversarial scenes.
We show that our scheme substantially enhances the robustness, with gains of 15.3% mIOU, compared with advanced competitors.
arXiv Detail & Related papers (2023-08-08T01:55:44Z) - Class Anchor Margin Loss for Content-Based Image Retrieval [97.81742911657497]
We propose a novel repeller-attractor loss that falls in the metric learning paradigm, yet directly optimize for the L2 metric without the need of generating pairs.
We evaluate the proposed objective in the context of few-shot and full-set training on the CBIR task, by using both convolutional and transformer architectures.
arXiv Detail & Related papers (2023-06-01T12:53:10Z) - Learning the Relation between Similarity Loss and Clustering Loss in
Self-Supervised Learning [27.91000553525992]
Self-supervised learning enables networks to learn discriminative features from massive data itself.
We analyze the relation between similarity loss and feature-level cross-entropy loss.
We provide theoretical analyses and experiments to show that a suitable combination of these two losses can get state-of-the-art results.
arXiv Detail & Related papers (2023-01-08T13:30:39Z) - Dissecting Deep Metric Learning Losses for Image-Text Retrieval [8.248111272824326]
Visual-Semantic Embedding (VSE) is a prevalent approach in image-text retrieval by learning a joint embedding space between the image and language modalities.
The triplet loss with hard-negative mining has become the de-facto objective for most VSE methods.
We present a novel Gradient-based Objective AnaLysis framework, or textitGOAL, to systematically analyze the combinations and reweighting of the gradients in existing DML functions.
arXiv Detail & Related papers (2022-10-21T06:48:27Z) - Do Lessons from Metric Learning Generalize to Image-Caption Retrieval? [67.45267657995748]
The triplet loss with semi-hard negatives has become the de facto choice for image-caption retrieval (ICR) methods that are optimized from scratch.
Recent progress in metric learning has given rise to new loss functions that outperform the triplet loss on tasks such as image retrieval and representation learning.
We ask whether these findings generalize to the setting of ICR by comparing three loss functions on two ICR methods.
arXiv Detail & Related papers (2022-02-14T15:18:00Z) - Robust Contrastive Learning against Noisy Views [79.71880076439297]
We propose a new contrastive loss function that is robust against noisy views.
We show that our approach provides consistent improvements over the state-of-the-art image, video, and graph contrastive learning benchmarks.
arXiv Detail & Related papers (2022-01-12T05:24:29Z) - Contrastive Learning of Visual-Semantic Embeddings [4.7464518249313805]
We propose two loss functions based on normalized cross-entropy to perform the task of learning joint visual-semantic embedding.
We compare our results with existing visual-semantic embedding methods on cross-modal image-to-text and text-to-image retrieval tasks.
arXiv Detail & Related papers (2021-10-17T17:28:04Z) - Can contrastive learning avoid shortcut solutions? [88.249082564465]
implicit feature modification (IFM) is a method for altering positive and negative samples in order to guide contrastive models towards capturing a wider variety of predictive features.
IFM reduces feature suppression, and as a result improves performance on vision and medical imaging tasks.
arXiv Detail & Related papers (2021-06-21T16:22:43Z) - An Elastic Interaction-Based Loss Function for Medical Image
Segmentation [10.851295591782538]
This paper introduces a long-range elastic interaction-based training strategy for medical image segmentation.
In this strategy, CNN learns the target region under the guidance of the elastic interaction energy between the boundary of the predicted region and that of the actual object.
Experimental results show that our method is able to achieve considerable improvements compared to commonly used pixel-wise loss functions.
arXiv Detail & Related papers (2020-07-06T11:49:14Z)
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.