Mind the Gap: Polishing Pseudo labels for Accurate Semi-supervised
Object Detection
- URL: http://arxiv.org/abs/2207.08185v1
- Date: Sun, 17 Jul 2022 14:07:49 GMT
- Title: Mind the Gap: Polishing Pseudo labels for Accurate Semi-supervised
Object Detection
- Authors: Lei Zhang, Yuxuan Sun, Wei Wei
- Abstract summary: We propose a dual pseudo-label polishing framework for semi-supervised object detection (SSOD)
Instead of directly exploiting the pseudo labels produced by the teacher detector, we take the first attempt at reducing their deviation from ground truth.
By doing this, both polishing networks can infer more accurate pseudo labels for unannotated objects.
- Score: 18.274860417877093
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Exploiting pseudo labels (e.g., categories and bounding boxes) of unannotated
objects produced by a teacher detector have underpinned much of recent progress
in semi-supervised object detection (SSOD). However, due to the limited
generalization capacity of the teacher detector caused by the scarce
annotations, the produced pseudo labels often deviate from ground truth,
especially those with relatively low classification confidences, thus limiting
the generalization performance of SSOD. To mitigate this problem, we propose a
dual pseudo-label polishing framework for SSOD. Instead of directly exploiting
the pseudo labels produced by the teacher detector, we take the first attempt
at reducing their deviation from ground truth using dual polishing learning,
where two differently structured polishing networks are elaborately developed
and trained using synthesized paired pseudo labels and the corresponding ground
truth for categories and bounding boxes on the given annotated objects,
respectively. By doing this, both polishing networks can infer more accurate
pseudo labels for unannotated objects through sufficiently exploiting their
context knowledge based on the initially produced pseudo labels, and thus
improve the generalization performance of SSOD. Moreover, such a scheme can be
seamlessly plugged into the existing SSOD framework for joint end-to-end
learning. In addition, we propose to disentangle the polished pseudo categories
and bounding boxes of unannotated objects for separate category classification
and bounding box regression in SSOD, which enables introducing more unannotated
objects during model training and thus further improve the performance.
Experiments on both PASCAL VOC and MS COCO benchmarks demonstrate the
superiority of the proposed method over existing state-of-the-art baselines.
Related papers
- Virtual Category Learning: A Semi-Supervised Learning Method for Dense
Prediction with Extremely Limited Labels [63.16824565919966]
This paper proposes to use confusing samples proactively without label correction.
A Virtual Category (VC) is assigned to each confusing sample in such a way that it can safely contribute to the model optimisation.
Our intriguing findings highlight the usage of VC learning in dense vision tasks.
arXiv Detail & Related papers (2023-12-02T16:23:52Z) - Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection [98.66771688028426]
We propose a Ambiguity-Resistant Semi-supervised Learning (ARSL) for one-stage detectors.
Joint-Confidence Estimation (JCE) is proposed to quantifies the classification and localization quality of pseudo labels.
ARSL effectively mitigates the ambiguities and achieves state-of-the-art SSOD performance on MS COCO and PASCAL VOC.
arXiv Detail & Related papers (2023-03-27T07:46:58Z) - Semi-Supervised Object Detection with Object-wise Contrastive Learning
and Regression Uncertainty [46.21528260727673]
We propose a two-step pseudo-label filtering for the classification and regression heads in a teacher-student framework.
By jointly filtering the pseudo-labels for the classification and regression heads, the student network receives better guidance from the teacher network for object detection task.
arXiv Detail & Related papers (2022-12-06T04:37:51Z) - W2N:Switching From Weak Supervision to Noisy Supervision for Object
Detection [64.10643170523414]
We propose a novel WSOD framework with a new paradigm that switches from weak supervision to noisy supervision (W2N)
In the localization adaptation module, we propose a regularization loss to reduce the proportion of discriminative parts in original pseudo ground-truths.
Our W2N outperforms all existing pure WSOD methods and transfer learning methods.
arXiv Detail & Related papers (2022-07-25T12:13:48Z) - Unbiased Teacher v2: Semi-supervised Object Detection for Anchor-free
and Anchor-based Detectors [35.41491696151547]
We present Unbiased Teacher v2, which shows the generalization of SS-OD method to anchor-free detectors.
We also introduce Listen2Student mechanism for the unsupervised regression loss.
arXiv Detail & Related papers (2022-06-19T22:57:48Z) - SIOD: Single Instance Annotated Per Category Per Image for Object
Detection [67.64774488115299]
We propose the Single Instance annotated Object Detection (SIOD), requiring only one instance annotation for each existing category in an image.
Degraded from inter-task (WSOD) or inter-image (SSOD) discrepancies to the intra-image discrepancy, SIOD provides more reliable and rich prior knowledge for mining the rest of unlabeled instances.
Under the SIOD setting, we propose a simple yet effective framework, termed Dual-Mining (DMiner), which consists of a Similarity-based Pseudo Label Generating module (SPLG) and a Pixel-level Group Contrastive Learning module (PGCL)
arXiv Detail & Related papers (2022-03-29T08:49:51Z) - Refining Pseudo Labels with Clustering Consensus over Generations for
Unsupervised Object Re-identification [84.72303377833732]
Unsupervised object re-identification targets at learning discriminative representations for object retrieval without any annotations.
We propose to estimate pseudo label similarities between consecutive training generations with clustering consensus and refine pseudo labels with temporally propagated and ensembled pseudo labels.
The proposed pseudo label refinery strategy is simple yet effective and can be seamlessly integrated into existing clustering-based unsupervised re-identification methods.
arXiv Detail & Related papers (2021-06-11T02:42:42Z) - Rethinking Pseudo Labels for Semi-Supervised Object Detection [84.697097472401]
We introduce certainty-aware pseudo labels tailored for object detection.
We dynamically adjust the thresholds used to generate pseudo labels and reweight loss functions for each category to alleviate the class imbalance problem.
Our approach improves supervised baselines by up to 10% AP using only 1-10% labeled data from COCO.
arXiv Detail & Related papers (2021-06-01T01:32:03Z)
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.