Correlation Loss: Enforcing Correlation between Classification and Localization

• URL: http://arxiv.org/abs/2301.01019v1
• Date: Tue, 3 Jan 2023 09:36:48 GMT
• Title: Correlation Loss: Enforcing Correlation between Classification and Localization
• Authors: Fehmi Kahraman, Kemal Oksuz, Sinan Kalkan, Emre Akbas
• Abstract summary: Correlation Loss is a novel plug-in loss function that improves the performance of various object detectors by directly optimizing correlation coefficients. Our best model on Sparse R-CNN reaches 51.0 AP without test-time augmentation on COCO test-dev, reaching state-of-the-art.
• Score: 18.195355848127285
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Object detectors are conventionally trained by a weighted sum of classification and localization losses. Recent studies (e.g., predicting IoU with an auxiliary head, Generalized Focal Loss, Rank & Sort Loss) have shown that forcing these two loss terms to interact with each other in non-conventional ways creates a useful inductive bias and improves performance. Inspired by these works, we focus on the correlation between classification and localization and make two main contributions: (i) We provide an analysis about the effects of correlation between classification and localization tasks in object detectors. We identify why correlation affects the performance of various NMS-based and NMS-free detectors, and we devise measures to evaluate the effect of correlation and use them to analyze common detectors. (ii) Motivated by our observations, e.g., that NMS-free detectors can also benefit from correlation, we propose Correlation Loss, a novel plug-in loss function that improves the performance of various object detectors by directly optimizing correlation coefficients: E.g., Correlation Loss on Sparse R-CNN, an NMS-free method, yields 1.6 AP gain on COCO and 1.8 AP gain on Cityscapes dataset. Our best model on Sparse R-CNN reaches 51.0 AP without test-time augmentation on COCO test-dev, reaching state-of-the-art. Code is available at https://github.com/fehmikahraman/CorrLoss

Related papers

• Measuring and Improving Attentiveness to Partial Inputs with Counterfactuals [91.59906995214209]
  We propose a new evaluation method, Counterfactual Attentiveness Test (CAT) CAT uses counterfactuals by replacing part of the input with its counterpart from a different example, expecting an attentive model to change its prediction. We show that GPT3 becomes less attentive with an increased number of demonstrations, while its accuracy on the test data improves.
  arXiv  Detail & Related papers  (2023-11-16T06:27:35Z)
• ReAct: Temporal Action Detection with Relational Queries [84.76646044604055]
  This work aims at advancing temporal action detection (TAD) using an encoder-decoder framework with action queries. We first propose a relational attention mechanism in the decoder, which guides the attention among queries based on their relations. Lastly, we propose to predict the localization quality of each action query at inference in order to distinguish high-quality queries.
  arXiv  Detail & Related papers  (2022-07-14T17:46:37Z)
• Fine-grained Correlation Loss for Regression [20.175415393263037]
  We propose to revisit the classic regression tasks with novel investigations on directly optimizing the fine-grained correlation losses. We extensively validate our method on two typical ultrasound image regression tasks, including the image quality assessment and bio-metric measurement.
  arXiv  Detail & Related papers  (2022-07-01T11:25:50Z)
• Exploiting the Relationship Between Kendall's Rank Correlation and Cosine Similarity for Attribution Protection [21.341303776931532]
  We first show that the expected Kendall's rank correlation is positively correlated to cosine similarity and then indicate that the direction of attribution is the key to attribution robustness. Our analysis further exposes that IGR encourages neurons with the same activation states for natural samples and the corresponding perturbed samples, which is shown to induce robustness to gradient-based attribution methods.
  arXiv  Detail & Related papers  (2022-05-15T13:08:50Z)
• ACP++: Action Co-occurrence Priors for Human-Object Interaction Detection [102.9428507180728]
  A common problem in the task of human-object interaction (HOI) detection is that numerous HOI classes have only a small number of labeled examples. We observe that there exist natural correlations and anti-correlations among human-object interactions. We present techniques to learn these priors and leverage them for more effective training, especially on rare classes.
  arXiv  Detail & Related papers  (2021-09-09T06:02:50Z)
• Reconcile Prediction Consistency for Balanced Object Detection [10.61438063305309]
  We propose a Harmonic loss to harmonize the optimization of classification branch and localization branch. The Harmonic loss enables these two branches to supervise and promote each other during training. In order to prevent the localization loss from being dominated by outliers during training phase, a Harmonic IoU loss is proposed to harmonize the weight of the localization loss of different IoU-level samples.
  arXiv  Detail & Related papers  (2021-08-24T15:52:11Z)
• Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization [89.73665256847858]
  We show that out-of-distribution performance is strongly correlated with in-distribution performance for a wide range of models and distribution shifts. Specifically, we demonstrate strong correlations between in-distribution and out-of-distribution performance on variants of CIFAR-10 & ImageNet. We also investigate cases where the correlation is weaker, for instance some synthetic distribution shifts from CIFAR-10-C and the tissue classification dataset Camelyon17-WILDS.
  arXiv  Detail & Related papers  (2021-07-09T19:48:23Z)
• Adversarial Feature Augmentation and Normalization for Visual Recognition [109.6834687220478]
  Recent advances in computer vision take advantage of adversarial data augmentation to ameliorate the generalization ability of classification models. Here, we present an effective and efficient alternative that advocates adversarial augmentation on intermediate feature embeddings. We validate the proposed approach across diverse visual recognition tasks with representative backbone networks.
  arXiv  Detail & Related papers  (2021-03-22T20:36:34Z)
• Modulating Localization and Classification for Harmonized Object Detection [40.82723262074911]
  We propose a mutual learning framework to modulate the two tasks. In particular, the two tasks are forced to learn from each other with a novel mutual labeling strategy. We achieve a significant performance gain over the baseline detectors on the COCO dataset.
  arXiv  Detail & Related papers  (2021-03-16T10:36:02Z)
• Optimized Loss Functions for Object detection: A Case Study on Nighttime Vehicle Detection [0.0]
  In this paper, we optimize both two loss functions for classification and localization simultaneously. Compared to the existing studies, in which the correlation is only applied to improve the localization accuracy for positive samples, this paper utilizes the correlation to obtain the really hard negative samples. A novel localization loss named MIoU is proposed by incorporating a Mahalanobis distance between predicted box and target box, which eliminate the gradients inconsistency problem in the DIoU loss.
  arXiv  Detail & Related papers  (2020-11-11T03:00:49Z)
• Detecting Human-Object Interactions with Action Co-occurrence Priors [108.31956827512376]
  A common problem in human-object interaction (HOI) detection task is that numerous HOI classes have only a small number of labeled examples. We observe that there exist natural correlations and anti-correlations among human-object interactions. We present techniques to learn these priors and leverage them for more effective training, especially in rare classes.
  arXiv  Detail & Related papers  (2020-07-17T02:47:45Z)

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.