PyTorchKR Papers

최신 논문

총 2,788편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2204.04170공식 코드 · Papers with Code

Automatic Data Augmentation Selection and Parametrization in Contrastive Self-Supervised Speech Representation Learning

Contrastive learning enables learning useful audio and speech representations without ground-truth labels by maximizing the similarity between latent representations of similar signal segments. In this framework various data augmentation techniques are usually exploited to help enforce desired invariances within the learned representations, improving performance on various audio tasks thanks to more robust embeddings. Now, selecting the most relevant augmentations has proven crucial for better downstream performances. Thus, this work introduces a conditional independance-based method which allows for automatically selecting a suitable distribution on the choice of augmentations and their parametrization from a set of predefined ones, for contrastive self-supervised pre-training. This is performed with respect to a downstream task of interest, hence saving a costly hyper-parameter search. Experiments performed on two different downstream tasks validate the proposed approach showing better results than experimenting without augmentation or with baseline augmentations. We furthermore conduct a qualitative analysis of the automatically selected augmentations and their variation according to the considered final downstream dataset.

arXiv:2204.03972공식 코드 · Papers with Code

Contrastive language and vision learning of general fashion concepts

The steady rise of online shopping goes hand in hand with the development of increasingly complex ML and NLP models. While most use cases are cast as specialized supervised learning problems, we argue that practitioners would greatly benefit from more transferable representations of products. In this work, we build on recent developments in contrastive learning to train FashionCLIP, a CLIP-like model for the fashion industry. We showcase its capabilities for retrieval, classification and grounding, and release our model and code to the community.

arXiv:2204.03738공식 코드 · Papers with Code

BankNote-Net: Open dataset for assistive universal currency recognition

Millions of people around the world have low or no vision. Assistive software applications have been developed for a variety of day-to-day tasks, including optical character recognition, scene identification, person recognition, and currency recognition. This last task, the recognition of banknotes from different denominations, has been addressed by the use of computer vision models for image recognition. However, the datasets and models available for this task are limited, both in terms of dataset size and in variety of currencies covered. In this work, we collect a total of 24,826 images of banknotes in variety of assistive settings, spanning 17 currencies and 112 denominations. Using supervised contrastive learning, we develop a machine learning model for universal currency recognition. This model learns compliant embeddings of banknote images in a variety of contexts, which can be shared publicly (as a compressed vector representation), and can be used to train and test specialized downstream models for any currency, including those not covered by our dataset or for which only a few real images per denomination are available (few-shot learning). We deploy a variation of this model for public use in the last version of the Seeing AI app developed by Microsoft. We share our encoder model and the embeddings as an open dataset in our BankNote-Net repository.

arXiv:2204.03083공식 코드 · Papers with Code

Audio-Visual Person-of-Interest DeepFake Detection

Face manipulation technology is advancing very rapidly, and new methods are being proposed day by day. The aim of this work is to propose a deepfake detector that can cope with the wide variety of manipulation methods and scenarios encountered in the real world. Our key insight is that each person has specific characteristics that a synthetic generator likely cannot reproduce. Accordingly, we extract audio-visual features which characterize the identity of a person, and use them to create a person-of-interest (POI) deepfake detector. We leverage a contrastive learning paradigm to learn the moving-face and audio segment embeddings that are most discriminative for each identity. As a result, when the video and/or audio of a person is manipulated, its representation in the embedding space becomes inconsistent with the real identity, allowing reliable detection. Training is carried out exclusively on real talking-face video; thus, the detector does not depend on any specific manipulation method and yields the highest generalization ability. In addition, our method can detect both single-modality (audio-only, video-only) and multi-modality (audio-video) attacks, and is robust to low-quality or corrupted videos. Experiments on a wide variety of datasets confirm that our method ensures a SOTA performance, especially on low quality videos. Code is publicly available on-line at https://github.com/grip-unina/poi-forensics.

arXiv:2204.03610공식 코드 · Papers with Code

Unified Contrastive Learning in Image-Text-Label Space

Visual recognition is recently learned via either supervised learning on human-annotated image-label data or language-image contrastive learning with webly-crawled image-text pairs. While supervised learning may result in a more discriminative representation, language-image pretraining shows unprecedented zero-shot recognition capability, largely due to the different properties of data sources and learning objectives. In this work, we introduce a new formulation by combining the two data sources into a common image-text-label space. In this space, we propose a new learning paradigm, called Unified Contrastive Learning (UniCL) with a single learning objective to seamlessly prompt the synergy of two data types. Extensive experiments show that our UniCL is an effective way of learning semantically rich yet discriminative representations, universally for image recognition in zero-shot, linear-probe, fully finetuning and transfer learning scenarios. Particularly, it attains gains up to 9.2% and 14.5% in average on zero-shot recognition benchmarks over the language-image contrastive learning and supervised learning methods, respectively. In linear probe setting, it also boosts the performance over the two methods by 7.3% and 3.4%, respectively. Our study also indicates that UniCL stand-alone is a good learner on pure image-label data, rivaling the supervised learning methods across three image classification datasets and two types of vision backbones, ResNet and Swin Transformer. Code is available at https://github.com/microsoft/UniCL.

arXiv:2204.02772공식 코드 · Papers with Code

Detail-recovery Image Deraining via Dual Sample-augmented Contrastive Learning

The intricacy of rainy image contents often leads cutting-edge deraining models to image degradation including remnant rain, wrongly-removed details, and distorted appearance. Such degradation is further exacerbated when applying the models trained on synthetic data to real-world rainy images. We observe two types of domain gaps between synthetic and real-world rainy images: one exists in rain streak patterns; the other is the pixel-level appearance of rain-free images. To bridge the two domain gaps, we propose a semi-supervised detail-recovery image deraining network (Semi-DRDNet) with dual sample-augmented contrastive learning. Semi-DRDNet consists of three sub-networks:i) for removing rain streaks without remnants, we present a squeeze-and-excitation based rain residual network; ii) for encouraging the lost details to return, we construct a structure detail context aggregation based detail repair network; to our knowledge, this is the first time; and iii) for building efficient contrastive constraints for both rain streaks and clean backgrounds, we exploit a novel dual sample-augmented contrastive regularization network.Semi-DRDNet operates smoothly on both synthetic and real-world rainy data in terms of deraining robustness and detail accuracy. Comparisons on four datasets including our established Real200 show clear improvements of Semi-DRDNet over fifteen state-of-the-art methods. Code and dataset are available at https://github.com/syy-whu/DRD-Net.

arXiv:2204.02553공식 코드 · Papers with Code

RODD: A Self-Supervised Approach for Robust Out-of-Distribution Detection

Recent studies have addressed the concern of detecting and rejecting the out-of-distribution (OOD) samples as a major challenge in the safe deployment of deep learning (DL) models. It is desired that the DL model should only be confident about the in-distribution (ID) data which reinforces the driving principle of the OOD detection. In this paper, we propose a simple yet effective generalized OOD detection method independent of out-of-distribution datasets. Our approach relies on self-supervised feature learning of the training samples, where the embeddings lie on a compact low-dimensional space. Motivated by the recent studies that show self-supervised adversarial contrastive learning helps robustify the model, we empirically show that a pre-trained model with self-supervised contrastive learning yields a better model for uni-dimensional feature learning in the latent space. The method proposed in this work referred to as RODD outperforms SOTA detection performance on an extensive suite of benchmark datasets on OOD detection tasks. On the CIFAR-100 benchmarks, RODD achieves a 26.97 $\%$ lower false-positive rate (FPR@95) compared to SOTA methods.

arXiv:2204.02287공식 코드 · Papers with Code

Rethinking Visual Geo-localization for Large-Scale Applications

Visual Geo-localization (VG) is the task of estimating the position where a given photo was taken by comparing it with a large database of images of known locations. To investigate how existing techniques would perform on a real-world city-wide VG application, we build San Francisco eXtra Large, a new dataset covering a whole city and providing a wide range of challenging cases, with a size 30x bigger than the previous largest dataset for visual geo-localization. We find that current methods fail to scale to such large datasets, therefore we design a new highly scalable training technique, called CosPlace, which casts the training as a classification problem avoiding the expensive mining needed by the commonly used contrastive learning. We achieve state-of-the-art performance on a wide range of datasets and find that CosPlace is robust to heavy domain changes. Moreover, we show that, compared to the previous state-of-the-art, CosPlace requires roughly 80% less GPU memory at train time, and it achieves better results with 8x smaller descriptors, paving the way for city-wide real-world visual geo-localization. Dataset, code and trained models are available for research purposes at https://github.com/gmberton/CosPlace.

arXiv:2204.02078공식 코드 · Papers with Code

Semi-supervised Semantic Segmentation with Error Localization Network

This paper studies semi-supervised learning of semantic segmentation, which assumes that only a small portion of training images are labeled and the others remain unlabeled. The unlabeled images are usually assigned pseudo labels to be used in training, which however often causes the risk of performance degradation due to the confirmation bias towards errors on the pseudo labels. We present a novel method that resolves this chronic issue of pseudo labeling. At the heart of our method lies error localization network (ELN), an auxiliary module that takes an image and its segmentation prediction as input and identifies pixels whose pseudo labels are likely to be wrong. ELN enables semi-supervised learning to be robust against inaccurate pseudo labels by disregarding label noises during training and can be naturally integrated with self-training and contrastive learning. Moreover, we introduce a new learning strategy for ELN that simulates plausible and diverse segmentation errors during training of ELN to enhance its generalization. Our method is evaluated on PASCAL VOC 2012 and Cityscapes, where it outperforms all existing methods in every evaluation setting.

arXiv:2204.01726공식 코드 · Papers with Code

Lip to Speech Synthesis with Visual Context Attentional GAN

In this paper, we propose a novel lip-to-speech generative adversarial network, Visual Context Attentional GAN (VCA-GAN), which can jointly model local and global lip movements during speech synthesis. Specifically, the proposed VCA-GAN synthesizes the speech from local lip visual features by finding a mapping function of viseme-to-phoneme, while global visual context is embedded into the intermediate layers of the generator to clarify the ambiguity in the mapping induced by homophene. To achieve this, a visual context attention module is proposed where it encodes global representations from the local visual features, and provides the desired global visual context corresponding to the given coarse speech representation to the generator through audio-visual attention. In addition to the explicit modelling of local and global visual representations, synchronization learning is introduced as a form of contrastive learning that guides the generator to synthesize a speech in sync with the given input lip movements. Extensive experiments demonstrate that the proposed VCA-GAN outperforms existing state-of-the-art and is able to effectively synthesize the speech from multi-speaker that has been barely handled in the previous works.

arXiv:2204.00791공식 코드 · Papers with Code

CL-XABSA: Contrastive Learning for Cross-lingual Aspect-based Sentiment Analysis

As an extensive research in the field of natural language processing (NLP), aspect-based sentiment analysis (ABSA) is the task of predicting the sentiment expressed in a text relative to the corresponding aspect. Unfortunately, most languages lack sufficient annotation resources, thus more and more recent researchers focus on cross-lingual aspect-based sentiment analysis (XABSA). However, most recent researches only concentrate on cross-lingual data alignment instead of model alignment. To this end, we propose a novel framework, CL-XABSA: Contrastive Learning for Cross-lingual Aspect-Based Sentiment Analysis. Based on contrastive learning, we close the distance between samples with the same label in different semantic spaces, thus achieving a convergence of semantic spaces of different languages. Specifically, we design two contrastive strategies, token level contrastive learning of token embeddings (TL-CTE) and sentiment level contrastive learning of token embeddings (SL-CTE), to regularize the semantic space of source and target language to be more uniform. Since our framework can receive datasets in multiple languages during training, our framework can be adapted not only for XABSA task but also for multilingual aspect-based sentiment analysis (MABSA). To further improve the performance of our model, we perform knowledge distillation technology leveraging data from unlabeled target language. In the distillation XABSA task, we further explore the comparative effectiveness of different data (source dataset, translated dataset, and code-switched dataset). The results demonstrate that the proposed method has a certain improvement in the three tasks of XABSA, distillation XABSA and MABSA. For reproducibility, our code for this paper is available at https://github.com/GKLMIP/CL-XABSA.

arXiv:2204.00989공식 코드 · Papers with Code

POS-BERT: Point Cloud One-Stage BERT Pre-Training

Recently, the pre-training paradigm combining Transformer and masked language modeling has achieved tremendous success in NLP, images, and point clouds, such as BERT. However, directly extending BERT from NLP to point clouds requires training a fixed discrete Variational AutoEncoder (dVAE) before pre-training, which results in a complex two-stage method called Point-BERT. Inspired by BERT and MoCo, we propose POS-BERT, a one-stage BERT pre-training method for point clouds. Specifically, we use the mask patch modeling (MPM) task to perform point cloud pre-training, which aims to recover masked patches information under the supervision of the corresponding tokenizer output. Unlike Point-BERT, its tokenizer is extra-trained and frozen. We propose to use the dynamically updated momentum encoder as the tokenizer, which is updated and outputs the dynamic supervision signal along with the training process. Further, in order to learn high-level semantic representation, we combine contrastive learning to maximize the class token consistency between different transformation point clouds. Extensive experiments have demonstrated that POS-BERT can extract high-quality pre-training features and promote downstream tasks to improve performance. Using the pre-training model without any fine-tuning to extract features and train linear SVM on ModelNet40, POS-BERT achieves the state-of-the-art classification accuracy, which exceeds Point-BERT by 3.5\%. In addition, our approach has significantly improved many downstream tasks, such as fine-tuned classification, few-shot classification, part segmentation. The code and trained-models will be available at: \url{https://github.com/fukexue/POS-BERT}.

arXiv:2204.00391공식 코드 · Papers with Code

Automatic Biomedical Term Clustering by Learning Fine-grained Term Representations

Term clustering is important in biomedical knowledge graph construction. Using similarities between terms embedding is helpful for term clustering. State-of-the-art term embeddings leverage pretrained language models to encode terms, and use synonyms and relation knowledge from knowledge graphs to guide contrastive learning. These embeddings provide close embeddings for terms belonging to the same concept. However, from our probing experiments, these embeddings are not sensitive to minor textual differences which leads to failure for biomedical term clustering. To alleviate this problem, we adjust the sampling strategy in pretraining term embeddings by providing dynamic hard positive and negative samples during contrastive learning to learn fine-grained representations which result in better biomedical term clustering. We name our proposed method as CODER++, and it has been applied in clustering biomedical concepts in the newly released Biomedical Knowledge Graph named BIOS.

arXiv:2204.00203공식 코드 · Papers with Code

Graph Enhanced Contrastive Learning for Radiology Findings Summarization

The impression section of a radiology report summarizes the most prominent observation from the findings section and is the most important section for radiologists to communicate to physicians. Summarizing findings is time-consuming and can be prone to error for inexperienced radiologists, and thus automatic impression generation has attracted substantial attention. With the encoder-decoder framework, most previous studies explore incorporating extra knowledge (e.g., static pre-defined clinical ontologies or extra background information). Yet, they encode such knowledge by a separate encoder to treat it as an extra input to their models, which is limited in leveraging their relations with the original findings. To address the limitation, we propose a unified framework for exploiting both extra knowledge and the original findings in an integrated way so that the critical information (i.e., key words and their relations) can be extracted in an appropriate way to facilitate impression generation. In detail, for each input findings, it is encoded by a text encoder, and a graph is constructed through its entities and dependency tree. Then, a graph encoder (e.g., graph neural networks (GNNs)) is adopted to model relation information in the constructed graph. Finally, to emphasize the key words in the findings, contrastive learning is introduced to map positive samples (constructed by masking non-key words) closer and push apart negative ones (constructed by masking key words). The experimental results on OpenI and MIMIC-CXR confirm the effectiveness of our proposed method.

arXiv:2204.00185공식 코드 · Papers with Code

Distill-VQ: Learning Retrieval Oriented Vector Quantization By Distilling Knowledge from Dense Embeddings

Vector quantization (VQ) based ANN indexes, such as Inverted File System (IVF) and Product Quantization (PQ), have been widely applied to embedding based document retrieval thanks to the competitive time and memory efficiency. Originally, VQ is learned to minimize the reconstruction loss, i.e., the distortions between the original dense embeddings and the reconstructed embeddings after quantization. Unfortunately, such an objective is inconsistent with the goal of selecting ground-truth documents for the input query, which may cause severe loss of retrieval quality. Recent works identify such a defect, and propose to minimize the retrieval loss through contrastive learning. However, these methods intensively rely on queries with ground-truth documents, whose performance is limited by the insufficiency of labeled data. In this paper, we propose Distill-VQ, which unifies the learning of IVF and PQ within a knowledge distillation framework. In Distill-VQ, the dense embeddings are leveraged as "teachers", which predict the query's relevance to the sampled documents. The VQ modules are treated as the "students", which are learned to reproduce the predicted relevance, such that the reconstructed embeddings may fully preserve the retrieval result of the dense embeddings. By doing so, Distill-VQ is able to derive substantial training signals from the massive unlabeled data, which significantly contributes to the retrieval quality. We perform comprehensive explorations for the optimal conduct of knowledge distillation, which may provide useful insights for the learning of VQ based ANN index. We also experimentally show that the labeled data is no longer a necessity for high-quality vector quantization, which indicates Distill-VQ's strong applicability in practice.

arXiv:2204.00166공식 코드 · Papers with Code

Making Pre-trained Language Models End-to-end Few-shot Learners with Contrastive Prompt Tuning

Pre-trained Language Models (PLMs) have achieved remarkable performance for various language understanding tasks in IR systems, which require the fine-tuning process based on labeled training data. For low-resource scenarios, prompt-based learning for PLMs exploits prompts as task guidance and turns downstream tasks into masked language problems for effective few-shot fine-tuning. In most existing approaches, the high performance of prompt-based learning heavily relies on handcrafted prompts and verbalizers, which may limit the application of such approaches in real-world scenarios. To solve this issue, we present CP-Tuning, the first end-to-end Contrastive Prompt Tuning framework for fine-tuning PLMs without any manual engineering of task-specific prompts and verbalizers. It is integrated with the task-invariant continuous prompt encoding technique with fully trainable prompt parameters. We further propose the pair-wise cost-sensitive contrastive learning procedure to optimize the model in order to achieve verbalizer-free class mapping and enhance the task-invariance of prompts. It explicitly learns to distinguish different classes and makes the decision boundary smoother by assigning different costs to easy and hard cases. Experiments over a variety of language understanding tasks used in IR systems and different PLMs show that CP-Tuning outperforms state-of-the-art methods.

arXiv:2203.17248공식 코드 · Papers with Code

Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo

Contrastive learning (CL) is widely known to require many negative samples, 65536 in MoCo for instance, for which the performance of a dictionary-free framework is often inferior because the negative sample size (NSS) is limited by its mini-batch size (MBS). To decouple the NSS from the MBS, a dynamic dictionary has been adopted in a large volume of CL frameworks, among which arguably the most popular one is MoCo family. In essence, MoCo adopts a momentum-based queue dictionary, for which we perform a fine-grained analysis of its size and consistency. We point out that InfoNCE loss used in MoCo implicitly attract anchors to their corresponding positive sample with various strength of penalties and identify such inter-anchor hardness-awareness property as a major reason for the necessity of a large dictionary. Our findings motivate us to simplify MoCo v2 via the removal of its dictionary as well as momentum. Based on an InfoNCE with the proposed dual temperature, our simplified frameworks, SimMoCo and SimCo, outperform MoCo v2 by a visible margin. Moreover, our work bridges the gap between CL and non-CL frameworks, contributing to a more unified understanding of these two mainstream frameworks in SSL. Code is available at: https://bit.ly/3LkQbaT.

arXiv:2203.16800공식 코드 · Papers with Code

Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization

We target at the task of weakly-supervised action localization (WSAL), where only video-level action labels are available during model training. Despite the recent progress, existing methods mainly embrace a localization-by-classification paradigm and overlook the fruitful fine-grained temporal distinctions between video sequences, thus suffering from severe ambiguity in classification learning and classification-to-localization adaption. This paper argues that learning by contextually comparing sequence-to-sequence distinctions offers an essential inductive bias in WSAL and helps identify coherent action instances. Specifically, under a differentiable dynamic programming formulation, two complementary contrastive objectives are designed, including Fine-grained Sequence Distance (FSD) contrasting and Longest Common Subsequence (LCS) contrasting, where the first one considers the relations of various action/background proposals by using match, insert, and delete operators and the second one mines the longest common subsequences between two videos. Both contrasting modules can enhance each other and jointly enjoy the merits of discriminative action-background separation and alleviated task gap between classification and localization. Extensive experiments show that our method achieves state-of-the-art performance on two popular benchmarks. Our code is available at https://github.com/MengyuanChen21/CVPR2022-FTCL.

arXiv:2203.16784공식 코드 · Papers with Code

Video-Text Representation Learning via Differentiable Weak Temporal Alignment

Learning generic joint representations for video and text by a supervised method requires a prohibitively substantial amount of manually annotated video datasets. As a practical alternative, a large-scale but uncurated and narrated video dataset, HowTo100M, has recently been introduced. But it is still challenging to learn joint embeddings of video and text in a self-supervised manner, due to its ambiguity and non-sequential alignment. In this paper, we propose a novel multi-modal self-supervised framework Video-Text Temporally Weak Alignment-based Contrastive Learning (VT-TWINS) to capture significant information from noisy and weakly correlated data using a variant of Dynamic Time Warping (DTW). We observe that the standard DTW inherently cannot handle weakly correlated data and only considers the globally optimal alignment path. To address these problems, we develop a differentiable DTW which also reflects local information with weak temporal alignment. Moreover, our proposed model applies a contrastive learning scheme to learn feature representations on weakly correlated data. Our extensive experiments demonstrate that VT-TWINS attains significant improvements in multi-modal representation learning and outperforms various challenging downstream tasks. Code is available at https://github.com/mlvlab/VT-TWINS.

arXiv:2203.16209공식 코드 · Papers with Code

Fair Contrastive Learning for Facial Attribute Classification

Learning visual representation of high quality is essential for image classification. Recently, a series of contrastive representation learning methods have achieved preeminent success. Particularly, SupCon outperformed the dominant methods based on cross-entropy loss in representation learning. However, we notice that there could be potential ethical risks in supervised contrastive learning. In this paper, we for the first time analyze unfairness caused by supervised contrastive learning and propose a new Fair Supervised Contrastive Loss (FSCL) for fair visual representation learning. Inheriting the philosophy of supervised contrastive learning, it encourages representation of the same class to be closer to each other than that of different classes, while ensuring fairness by penalizing the inclusion of sensitive attribute information in representation. In addition, we introduce a group-wise normalization to diminish the disparities of intra-group compactness and inter-class separability between demographic groups that arouse unfair classification. Through extensive experiments on CelebA and UTK Face, we validate that the proposed method significantly outperforms SupCon and existing state-of-the-art methods in terms of the trade-off between top-1 accuracy and fairness. Moreover, our method is robust to the intensity of data bias and effectively works in incomplete supervised settings. Our code is available at https://github.com/sungho-CoolG/FSCL.