Negative Prototypes Guided Contrastive Learning for WSOD
- URL: http://arxiv.org/abs/2406.18576v1
- Date: Tue, 4 Jun 2024 08:16:26 GMT
- Title: Negative Prototypes Guided Contrastive Learning for WSOD
- Authors: Yu Zhang, Chuang Zhu, Guoqing Yang, Siqi Chen,
- Abstract summary: Weakly Supervised Object Detection (WSOD) with only image-level annotation has recently attracted wide attention.
We propose the Negative Prototypes Guided Contrastive learning architecture.
Our proposed method achieves the state-of-the-art performance.
- Score: 8.102080369924911
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Weakly Supervised Object Detection (WSOD) with only image-level annotation has recently attracted wide attention. Many existing methods ignore the inter-image relationship of instances which share similar characteristics while can certainly be determined not to belong to the same category. Therefore, in order to make full use of the weak label, we propose the Negative Prototypes Guided Contrastive learning (NPGC) architecture. Firstly, we define Negative Prototype as the proposal with the highest confidence score misclassified for the category that does not appear in the label. Unlike other methods that only utilize category positive feature, we construct an online updated global feature bank to store both positive prototypes and negative prototypes. Meanwhile, we propose a pseudo label sampling module to mine reliable instances and discard the easily misclassified instances based on the feature similarity with corresponding prototypes in global feature bank. Finally, we follow the contrastive learning paradigm to optimize the proposal's feature representation by attracting same class samples closer and pushing different class samples away in the embedding space. Extensive experiments have been conducted on VOC07, VOC12 datasets, which shows that our proposed method achieves the state-of-the-art performance.
Related papers
- Collaborative Feature-Logits Contrastive Learning for Open-Set Semi-Supervised Object Detection [75.02249869573994]
In open-set scenarios, the unlabeled dataset contains both in-distribution (ID) classes and out-of-distribution (OOD) classes.
Applying semi-supervised detectors in such settings can lead to misclassifying OOD class as ID classes.
We propose a simple yet effective method, termed Collaborative Feature-Logits Detector (CFL-Detector)
arXiv Detail & Related papers (2024-11-20T02:57:35Z) - Prototypical Contrastive Learning through Alignment and Uniformity for
Recommendation [6.790779112538357]
We present underlinePrototypical contrastive learning through underlineAlignment and underlineUniformity for recommendation.
Specifically, we first propose prototypes as a latent space to ensure consistency across different augmentations from the origin graph.
The absence of explicit negatives means that directly optimizing the consistency loss between instance and prototype could easily result in dimensional collapse issues.
arXiv Detail & Related papers (2024-02-03T08:19:26Z) - Decoupled Prototype Learning for Reliable Test-Time Adaptation [50.779896759106784]
Test-time adaptation (TTA) is a task that continually adapts a pre-trained source model to the target domain during inference.
One popular approach involves fine-tuning model with cross-entropy loss according to estimated pseudo-labels.
This study reveals that minimizing the classification error of each sample causes the cross-entropy loss's vulnerability to label noise.
We propose a novel Decoupled Prototype Learning (DPL) method that features prototype-centric loss computation.
arXiv Detail & Related papers (2024-01-15T03:33:39Z) - A Prototypical Semantic Decoupling Method via Joint Contrastive Learning
for Few-Shot Name Entity Recognition [24.916377682689955]
Few-shot named entity recognition (NER) aims at identifying named entities based on only few labeled instances.
We propose a Prototypical Semantic Decoupling method via joint Contrastive learning (PSDC) for few-shot NER.
Experimental results on two few-shot NER benchmarks demonstrate that PSDC consistently outperforms the previous SOTA methods in terms of overall performance.
arXiv Detail & Related papers (2023-02-27T09:20:00Z) - APANet: Adaptive Prototypes Alignment Network for Few-Shot Semantic
Segmentation [56.387647750094466]
Few-shot semantic segmentation aims to segment novel-class objects in a given query image with only a few labeled support images.
Most advanced solutions exploit a metric learning framework that performs segmentation through matching each query feature to a learned class-specific prototype.
We present an adaptive prototype representation by introducing class-specific and class-agnostic prototypes.
arXiv Detail & Related papers (2021-11-24T04:38:37Z) - Dual Prototypical Contrastive Learning for Few-shot Semantic
Segmentation [55.339405417090084]
We propose a dual prototypical contrastive learning approach tailored to the few-shot semantic segmentation (FSS) task.
The main idea is to encourage the prototypes more discriminative by increasing inter-class distance while reducing intra-class distance in prototype feature space.
We demonstrate that the proposed dual contrastive learning approach outperforms state-of-the-art FSS methods on PASCAL-5i and COCO-20i datasets.
arXiv Detail & Related papers (2021-11-09T08:14:50Z) - Explicitly Modeling the Discriminability for Instance-Aware Visual
Object Tracking [13.311777431243296]
We propose a novel Instance-Aware Tracker (IAT) to excavate the discriminability of feature representations.
We implement two variants of the proposed IAT, including a video-level one and an object-level one.
Both versions achieve leading results against state-of-the-art methods while running at 30FPS.
arXiv Detail & Related papers (2021-10-28T11:24:01Z) - Neighborhood Contrastive Learning for Novel Class Discovery [79.14767688903028]
We build a new framework, named Neighborhood Contrastive Learning, to learn discriminative representations that are important to clustering performance.
We experimentally demonstrate that these two ingredients significantly contribute to clustering performance and lead our model to outperform state-of-the-art methods by a large margin.
arXiv Detail & Related papers (2021-06-20T17:34:55Z) - UniT: Unified Knowledge Transfer for Any-shot Object Detection and
Segmentation [52.487469544343305]
Methods for object detection and segmentation rely on large scale instance-level annotations for training.
We propose an intuitive and unified semi-supervised model that is applicable to a range of supervision.
arXiv Detail & Related papers (2020-06-12T22:45:47Z)
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.