ترغب بنشر مسار تعليمي؟ اضغط هنا

Zero-Shot Detection via Vision and Language Knowledge Distillation

103   0   0.0 ( 0 )
 نشر من قبل Xiuye Gu
 تاريخ النشر 2021
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

Zero-shot image classification has made promising progress by training the aligned image and text encoders. The goal of this work is to advance zero-shot object detection, which aims to detect novel objects without bounding box nor mask annotations. We propose ViLD, a training method via Vision and Language knowledge Distillation. We distill the knowledge from a pre-trained zero-shot image classification model (e.g., CLIP) into a two-stage detector (e.g., Mask R-CNN). Our method aligns the region embeddings in the detector to the text and image embeddings inferred by the pre-trained model. We use the text embeddings as the detection classifier, obtained by feeding category names into the pre-trained text encoder. We then minimize the distance between the region embeddings and image embeddings, obtained by feeding region proposals into the pre-trained image encoder. During inference, we include text embeddings of novel categories into the detection classifier for zero-shot detection. We benchmark the performance on LVIS dataset by holding out all rare categories as novel categories. ViLD obtains 16.1 mask AP$_r$ with a Mask R-CNN (ResNet-50 FPN) for zero-shot detection, outperforming the supervised counterpart by 3.8. The model can directly transfer to other datasets, achieving 72.2 AP$_{50}$, 36.6 AP and 11.8 AP on PASCAL VOC, COCO and Objects365, respectively.



قيم البحث

اقرأ أيضاً

Multi-label image classification is a fundamental but challenging task towards general visual understanding. Existing methods found the region-level cues (e.g., features from RoIs) can facilitate multi-label classification. Nevertheless, such methods usually require laborious object-level annotations (i.e., object labels and bounding boxes) for effective learning of the object-level visual features. In this paper, we propose a novel and efficient deep framework to boost multi-label classification by distilling knowledge from weakly-supervised detection task without bounding box annotations. Specifically, given the image-level annotations, (1) we first develop a weakly-supervised detection (WSD) model, and then (2) construct an end-to-end multi-label image classification framework augmented by a knowledge distillation module that guides the classification model by the WSD model according to the class-level predictions for the whole image and the object-level visual features for object RoIs. The WSD model is the teacher model and the classification model is the student model. After this cross-task knowledge distillation, the performance of the classification model is significantly improved and the efficiency is maintained since the WSD model can be safely discarded in the test phase. Extensive experiments on two large-scale datasets (MS-COCO and NUS-WIDE) show that our framework achieves superior performances over the state-of-the-art methods on both performance and efficiency.
It is challenging to perform lifelong language learning (LLL) on a stream of different tasks without any performance degradation comparing to the multi-task counterparts. To address this issue, we present Lifelong Language Knowledge Distillation (L2K D), a simple but efficient method that can be easily applied to existing LLL architectures in order to mitigate the degradation. Specifically, when the LLL model is trained on a new task, we assign a teacher model to first learn the new task, and pass the knowledge to the LLL model via knowledge distillation. Therefore, the LLL model can better adapt to the new task while keeping the previously learned knowledge. Experiments show that the proposed L2KD consistently improves previous state-of-the-art models, and the degradation comparing to multi-task models in LLL tasks is well mitigated for both sequence generation and text classification tasks.
Traditional computer vision models are trained to predict a fixed set of predefined categories. Recently, natural language has been shown to be a broader and richer source of supervision that provides finer descriptions to visual concepts than superv ised gold labels. Previous works, such as CLIP, use a simple pretraining task of predicting the pairings between images and text captions. CLIP, however, is data hungry and requires more than 400M image text pairs for training. We propose a data-efficient contrastive distillation method that uses soft labels to learn from noisy image-text pairs. Our model transfers knowledge from pretrained image and sentence encoders and achieves strong performance with only 3M image text pairs, 133x smaller than CLIP. Our method exceeds the previous SoTA of general zero-shot learning on ImageNet 21k+1k by 73% relatively with a ResNet50 image encoder and DeCLUTR text encoder. We also beat CLIP by 10.5% relatively on zero-shot evaluation on Google Open Images (19,958 classes).
Large-scale vision and language representation learning has shown promising improvements on various vision-language tasks. Most existing methods employ a transformer-based multimodal encoder to jointly model visual tokens (region-based image features ) and word tokens. Because the visual tokens and word tokens are unaligned, it is challenging for the multimodal encoder to learn image-text interactions. In this paper, we introduce a contrastive loss to ALign the image and text representations BEfore Fusing (ALBEF) them through cross-modal attention, which enables more grounded vision and language representation learning. Unlike most existing methods, our method does not require bounding box annotations nor high-resolution images. In order to improve learning from noisy web data, we propose momentum distillation, a self-training method which learns from pseudo-targets produced by a momentum model. We provide a theoretical analysis of ALBEF from a mutual information maximization perspective, showing that different training tasks can be interpreted as different ways to generate views for an image-text pair. ALBEF achieves state-of-the-art performance on multiple downstream vision-language tasks. On image-text retrieval, ALBEF outperforms methods that are pre-trained on orders of magnitude larger datasets. On VQA and NLVR$^2$, ALBEF achieves absolute improvements of 2.37% and 3.84% compared to the state-of-the-art, while enjoying faster inference speed. Code and pre-trained models are available at https://github.com/salesforce/ALBEF/.
Zero-Shot Learning (ZSL) is an emerging research that aims to solve the classification problems with very few training data. The present works on ZSL mainly focus on the mapping of learning semantic space to visual space. It encounters many challenge s that obstruct the progress of ZSL research. First, the representation of the semantic feature is inadequate to represent all features of the categories. Second, the domain drift problem still exists during the transfer from semantic space to visual space. In this paper, we introduce knowledge sharing (KS) to enrich the representation of semantic features. Based on KS, we apply a generative adversarial network to generate pseudo visual features from semantic features that are very close to the real visual features. Abundant experimental results from two benchmark datasets of ZSL show that the proposed approach has a consistent improvement.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا